Authors: Ming Cheung
Abstract: Large language models (LLMs) have achieved remarkable performance in language understanding and generation tasks by leveraging vast amounts of online texts. Unlike conventional models, LLMs can adapt to new domains through prompt engineering without the need for retraining, making them suitable for various business functions, such as strategic planning, project implementation, and data-driven decision-making. However, their limitations in terms of bias, contextual understanding, and sensitivity to prompts raise concerns about their readiness for real-world applications. This paper thoroughly examines the usefulness and readiness of LLMs for business processes. The limitations and capacities of LLMs are evaluated through experiments conducted on four accessible LLMs using real-world data. The findings have significant implications for organizations seeking to leverage generative AI and provide valuable insights into future research directions. To the best of our knowledge, this represents the first quantified study of LLMs applied to core business operations and challenges.
Authors: Chenyan Zhao, Mariana Silva, Seth Poulsen
Abstract: In mathematical proof education, there remains a need for interventions that help students learn to write mathematical proofs. Research has shown that timely feedback can be very helpful to students learning new skills. While for many years natural language processing models have struggled to perform well on tasks related to mathematical texts, recent developments in natural language processing have created the opportunity to complete the task of giving students instant feedback on their mathematical proofs. In this paper, we present a set of training methods and models capable of autograding freeform mathematical proofs by leveraging existing large language models and other machine learning techniques. The models are trained using proof data collected from four different proof by induction problems. We use four different robust large language models to compare their performances, and all achieve satisfactory performances to various degrees. Additionally, we recruit human graders to grade the same proofs as the training data, and find that the best grading model is also more accurate than most human graders. With the development of these grading models, we create and deploy an autograder for proof by induction problems and perform a user study with students. Results from the study shows that students are able to make significant improvements to their proofs using the feedback from the autograder, but students still do not trust the AI autograders as much as they trust human graders. Future work can improve on the autograder feedback and figure out ways to help students trust AI autograders.
Authors: Hao Kang, Chenyan Xiong
Abstract: Large language models (LLMs) have exhibited remarkable performance across various tasks in natural language processing. Nevertheless, challenges still arise when these tasks demand domain-specific expertise and advanced analytical skills, such as conducting research surveys on a designated topic. In this research, we develop ResearchArena, a benchmark that measures LLM agents' ability to conduct academic surveys, an initial step of academic research process. Specifically, we deconstructs the surveying process into three stages 1) information discovery: locating relevant papers, 2) information selection: assessing papers' importance to the topic, and 3) information organization: organizing papers into meaningful structures. In particular, we establish an offline environment comprising 12.0M full-text academic papers and 7.9K survey papers, which evaluates agents' ability to locate supporting materials for composing the survey on a topic, rank the located papers based on their impact, and organize these into a hierarchical knowledge mind-map. With this benchmark, we conduct preliminary evaluations of existing techniques and find that all LLM-based methods under-performing when compared to basic keyword-based retrieval techniques, highlighting substantial opportunities for future research.
Authors: Chufan Gao, Jathurshan Pradeepkumar, Trisha Das, Shivashankar Thati, Jimeng Sun
Abstract: The global cost of drug discovery and development exceeds $200 billion annually. The main results of drug discovery and development are the outcomes of clinical trials, which directly influence the regulatory approval of new drug candidates and ultimately affect patient outcomes. Despite their significance, large-scale, high-quality clinical trial outcome data are not readily available to the public. Suppose a large clinical trial outcome dataset is provided; machine learning researchers can potentially develop accurate prediction models using past trials and outcome labels, which could help prioritize and optimize therapeutic programs, ultimately benefiting patients. This paper introduces Clinical Trial Outcome (CTO) dataset, the largest trial outcome dataset with around 479K clinical trials, aggregating outcomes from multiple sources of weakly supervised labels, minimizing the noise from individual sources, and eliminating the need for human annotation. These sources include large language model (LLM) decisions on trial-related documents, news headline sentiments, stock prices of trial sponsors, trial linkages across phases, and other signals such as patient dropout rates and adverse events. CTO's labels show unprecedented agreement with supervised clinical trial outcome labels from test split of the supervised TOP dataset, with a 91 F1.
Authors: Haruka Kita, Sotetsu Koyamada, Yotaro Yamaguchi, Shin Ishii
Abstract: Contract bridge, a cooperative game characterized by imperfect information and multi-agent dynamics, poses significant challenges and serves as a critical benchmark in artificial intelligence (AI) research. Success in this domain requires agents to effectively cooperate with their partners. This study demonstrates that an appropriate combination of existing methods can perform surprisingly well in bridge bidding against WBridge5, a leading benchmark in the bridge bidding system and a multiple-time World Computer-Bridge Championship winner. Our approach is notably simple, yet it outperforms the current state-of-the-art methodologies in this field. Furthermore, we have made our code and models publicly available as open-source software. This initiative provides a strong starting foundation for future bridge AI research, facilitating the development and verification of new strategies and advancements in the field.
Authors: Bin Xiao, Burak Kantarci, Jiawen Kang, Dusit Niyato, Mohsen Guizani
Abstract: Large language models (LLMs) have demonstrated remarkable capacities on various tasks, and integrating the capacities of LLMs into the Internet of Things (IoT) applications has drawn much research attention recently. Due to security concerns, many institutions avoid accessing state-of-the-art commercial LLM services, requiring the deployment and utilization of open-source LLMs in a local network setting. However, open-source LLMs usually have more limitations regarding their performance, such as their arithmetic calculation and reasoning capacities, and practical systems of applying LLMs to IoT have yet to be well-explored. Therefore, we propose a text-based generative IoT (GIoT) system deployed in the local network setting in this study. To alleviate the limitations of LLMs and provide service with competitive performance, we apply prompt engineering methods to enhance the capacities of the open-source LLMs, design a Prompt Management Module and a Post-processing Module to manage the tailored prompts for different tasks and process the results generated by the LLMs. To demonstrate the effectiveness of the proposed system, we discuss a challenging Table Question Answering (Table-QA) task as a case study of the proposed system, as tabular data is usually more challenging than plain text because of their complex structures, heterogeneous data types and sometimes huge sizes. We conduct comprehensive experiments on two popular Table-QA datasets, and the results show that our proposal can achieve competitive performance compared with state-of-the-art LLMs, demonstrating that the proposed LLM-based GIoT system can provide competitive performance with tailored prompting methods and is easily extensible to new tasks without training.
Authors: Wenjun Li, Changyu Chen, Pradeep Varakantham
Abstract: Large language models (LLMs) have demonstrated impressive task-solving capabilities, achieved through either prompting techniques or system designs. However, concerns have arisen regarding their proficiency in planning tasks, as they often struggle to generate valid plans. This paper investigates the impact of fine-tuning on LLMs' planning capabilities. Our findings indicate that LLMs can achieve good performance in planning through substantial (thousands of specific examples) fine-tuning. However, fine-tuning is associated with significant economic and computational costs. To address this challenge, we propose the Maximum Diversity Fine-Tuning (MDFT) strategy to improve the sample efficiency of fine-tuning in the planning domain. Specifically, our algorithm, referred to as MDFT-g, encodes the planning task instances with their graph representations and selects a subset of samples in the vector space that maximizes data diversity. We empirically demonstrate that MDFT-g consistently outperforms existing baselines at various scales across multiple benchmark domains.
Authors: Gurusha Juneja, Nagarajan Natarajan, Hua Li, Jian Jiao, Amit Sharma
Abstract: Given a task in the form of a basic description and its training examples, prompt optimization is the problem of synthesizing the given information into a text prompt for a large language model (LLM). Humans solve this problem by also considering the different facets that define a task (e.g., counter-examples, explanations, analogies) and including them in the prompt. However, it is unclear whether existing algorithmic approaches, based on iteratively editing a given prompt or automatically selecting a few in-context examples, can cover the multiple facets required to solve a complex task. In this work, we view prompt optimization as that of learning multiple facets of a task from a set of training examples. We identify and exploit structure in the prompt optimization problem -- first, we find that prompts can be broken down into loosely coupled semantic sections that have a relatively independent effect on the prompt's performance; second, we cluster the input space and use clustered batches so that the optimization procedure can learn the different facets of a task across batches. The resulting algorithm, UniPrompt, consists of a generative model to generate initial candidates for each prompt section; and a feedback mechanism that aggregates suggested edits from multiple mini-batches into a conceptual description for the section. Empirical evaluation on multiple datasets and a real-world task shows that prompts generated using UniPrompt obtain higher accuracy than human-tuned prompts and those from state-of-the-art methods. In particular, our algorithm can generate long, complex prompts that existing methods are unable to generate. Code for UniPrompt will be available at \url{https://aka.ms/uniprompt}.
URLs: https://aka.ms/uniprompt
Authors: TJ Dunham, Henry Syahputra
Abstract: The paper presents the performance results of Reactor Mk.1, ARCs flagship large language model, through a benchmarking process analysis. The model utilizes the Lychee AI engine and possesses less than 100 billion parameters, resulting in a combination of efficiency and potency. The Reactor Mk.1 outperformed models such as GPT-4o, Claude Opus, and Llama 3, with achieved scores of 92% on the MMLU dataset, 91% on HumanEval dataset, and 88% on BBH dataset. It excels in both managing difficult jobs and reasoning, establishing as a prominent AI solution in the present cutting-edge AI technology.
Authors: Xu Han, Qiannan Yang, Xianda Chen, Xiaowen Chu, Meixin Zhu
Abstract: Reinforcement Learning (RL) plays a crucial role in advancing autonomous driving technologies by maximizing reward functions to achieve the optimal policy. However, crafting these reward functions has been a complex, manual process in many practices. To reduce this complexity, we introduce a novel framework that integrates Large Language Models (LLMs) with RL to improve reward function design in autonomous driving. This framework utilizes the coding capabilities of LLMs, proven in other areas, to generate and evolve reward functions for highway scenarios. The framework starts with instructing LLMs to create an initial reward function code based on the driving environment and task descriptions. This code is then refined through iterative cycles involving RL training and LLMs' reflection, which benefits from their ability to review and improve the output. We have also developed a specific prompt template to improve LLMs' understanding of complex driving simulations, ensuring the generation of effective and error-free code. Our experiments in a highway driving simulator across three traffic configurations show that our method surpasses expert handcrafted reward functions, achieving a 22% higher average success rate. This not only indicates safer driving but also suggests significant gains in development productivity.
Authors: Gianmarco Mengaldo
Abstract: The scientific method is the cornerstone of human progress across all branches of the natural and applied sciences, from understanding the human body to explaining how the universe works. The scientific method is based on identifying systematic rules or principles that describe the phenomenon of interest in a reproducible way that can be validated through experimental evidence. In the era of artificial intelligence (AI), there are discussions on how AI systems may discover new knowledge. We argue that, before the advent of artificial general intelligence, human complex reasoning for scientific discovery remains of vital importance. Yet, AI can be leveraged for scientific discovery via explainable AI. More specifically, knowing what data AI systems used to make decisions can be a point of contact with domain experts and scientists, that can lead to divergent or convergent views on a given scientific problem. Divergent views may spark further scientific investigations leading to new scientific knowledge. Convergent views may instead reassure that the AI system is operating within bounds deemed reasonable to humans. The latter point addresses the trustworthiness requirement that is indispensable for critical applications in the applied sciences, such as medicine.
Authors: Yinggang Sun, Ziming Guo, Haining Yu, Chuanyi Liu, Xiang Li, Bingxuan Wang, Xiangzhan Yu, Tiancheng Zhao
Abstract: Fine-tuning large language models (LLMs) for specific domain tasks has achieved great success in Text-to-SQL tasks. However, these fine-tuned models often face challenges with multi-turn Text-to-SQL tasks caused by ambiguous or unanswerable questions. It is desired to enhance LLMs to handle multiple types of questions in multi-turn Text-to-SQL tasks. To address this, we propose a novel data augmentation method, called QDA-SQL, which generates multiple types of multi-turn Q\&A pairs by using LLMs. In QDA-SQL, we introduce a novel data augmentation method incorporating validation and correction mechanisms to handle complex multi-turn Text-to-SQL tasks. Experimental results demonstrate that QDA-SQL enables fine-tuned models to exhibit higher performance on SQL statement accuracy and enhances their ability to handle complex, unanswerable questions in multi-turn Text-to-SQL tasks. The generation script and test set are released at https://github.com/mcxiaoxiao/QDA-SQL.
Authors: Jun Zhang, Wenxuan Ao, Junbo Yan, Depeng Jin, Yong Li
Abstract: With the development of artificial intelligence techniques, transportation system optimization is evolving from traditional methods relying on expert experience to simulation and learning-based decision optimization methods. Learning-based optimization methods require extensive interaction with highly realistic microscopic traffic simulators for optimization. However, existing microscopic traffic simulators are computationally inefficient in large-scale scenarios and therefore significantly reduce the efficiency of the data sampling process of optimization algorithms. In addition, the optimization scenarios supported by existing simulators are limited, mainly focusing on the traffic signal control. To address these challenges and limitations, we propose the first open-source GPU-accelerated large-scale microscopic simulator for transportation system simulation. The simulator is able to iterate at 84.09Hz, which achieves 88.92 times computational acceleration in the large-scale scenario with more than a million vehicles compared to the best baseline. Based on the simulator, we implement a set of microscopic and macroscopic controllable objects and metrics to support most typical transportation system optimization scenarios. These controllable objects and metrics are all provided by Python API for ease of use. We choose five important and representative transportation system optimization scenarios and benchmark classical rule-based algorithms, reinforcement learning, and black-box optimization in four cities. The codes are available at \url{https://github.com/tsinghua-fib-lab/moss-benchmark} with the MIT License.
Authors: Jeffery L. Painter, Venkateswara Rao Chalamalasetti, Raymond Kassekert, Andrew Bate
Abstract: Pharmacovigilance (PV) is essential for drug safety, primarily focusing on adverse event monitoring. Traditionally, accessing safety data required database expertise, limiting broader use. This paper introduces a novel application of Large Language Models (LLMs) to democratize database access for non-technical users. Utilizing OpenAI's GPT-4, we developed a chatbot that generates structured query language (SQL) queries from natural language, bridging the gap between domain knowledge and technical requirements. The proposed application aims for more inclusive and efficient data access, enhancing decision making in drug safety. By providing LLMs with plain language summaries of expert knowledge, our approach significantly improves query accuracy over methods relying solely on database schemas. The application of LLMs in this context not only optimizes PV data analysis, ensuring timely and precise drug safety reporting -- a crucial component in adverse drug reaction monitoring -- but also promotes safer pharmacological practices and informed decision making across various data intensive fields.
Authors: Ziije Zhong, Linqing Zhong, Zhaoze Sun, Qingyun Jin, Zengchang Qin, Xiaofan Zhang
Abstract: Integrating Large Language Models (LLMs) with existing Knowledge Graph (KG) databases presents a promising avenue for enhancing LLMs' efficacy and mitigating their "hallucinations". Given that most KGs reside in graph databases accessible solely through specialized query languages (e.g., Cypher), there exists a critical need to bridge the divide between LLMs and KG databases by automating the translation of natural language into Cypher queries (commonly termed the "Text2Cypher" task). Prior efforts tried to bolster LLMs' proficiency in Cypher generation through Supervised Fine-Tuning. However, these explorations are hindered by the lack of annotated datasets of Query-Cypher pairs, resulting from the labor-intensive and domain-specific nature of annotating such datasets. In this study, we propose SyntheT2C, a methodology for constructing a synthetic Query-Cypher pair dataset, comprising two distinct pipelines: (1) LLM-based prompting and (2) template-filling. SyntheT2C facilitates the generation of extensive Query-Cypher pairs with values sampled from an underlying Neo4j graph database. Subsequently, SyntheT2C is applied to two medical databases, culminating in the creation of a synthetic dataset, MedT2C. Comprehensive experiments demonstrate that the MedT2C dataset effectively enhances the performance of backbone LLMs on the Text2Cypher task. Both the SyntheT2C codebase and the MedT2C dataset will be released soon.
Authors: Zhengxiang Wang, Jordan Kodner, Owen Rambow
Abstract: Current LLM evaluation predominantly performs evaluation with prompts comprising single problems. We propose multi-problem evaluation as an additional approach to study the multiple problem handling capabilities of LLMs. We present a systematic study in this regard by comprehensively examining 7 LLMs on 4 related types of tasks constructed from 6 classification benchmarks. The 4 task types include traditional single-problem tasks, homogeneous multi-problem tasks, and two index selection tasks that embed the multi-problem tasks. We find that LLMs are competent multi-problem solvers: they generally perform (nearly) as well on multi-problem tasks as on single-problem tasks. Furthermore, contrary to common expectation, they often do not suffer from a positional bias with long inputs. This makes multi-problem prompting a simple and cost-efficient prompting method of practical significance. However, our results also strongly indicate that LLMs lack true understanding: they perform significantly worse in the two index selection tasks than in the multi-problem task under various evaluation settings, although they can indeed do index selection in general.
Authors: William Watson, Nicole Cho, Tucker Balch, Manuela Veloso
Abstract: A myriad of different Large Language Models (LLMs) face a common challenge in contextually analyzing table question-answering tasks. These challenges are engendered from (1) finite context windows for large tables, (2) multi-faceted discrepancies amongst tokenization patterns against cell boundaries, and (3) various limitations stemming from data confidentiality in the process of using external models such as gpt-3.5-turbo. We propose a cooperative game dubbed "HiddenTables" as a potential resolution to this challenge. In essence, "HiddenTables" is played between the code-generating LLM "Solver" and the "Oracle" which evaluates the ability of the LLM agents to solve Table QA tasks. This game is based on natural language schemas and importantly, ensures the security of the underlying data. We provide evidential experiments on a diverse set of tables that demonstrate an LLM's collective inability to generalize and perform on complex queries, handle compositional dependencies, and align natural language to programmatic commands when concrete table schemas are provided. Unlike encoder-based models, we have pushed the boundaries of "HiddenTables" to not be limited by the number of rows - therefore we exhibit improved efficiency in prompt and completion tokens. Our infrastructure has spawned a new dataset "PyQTax" that spans across 116,671 question-table-answer triplets and provides additional fine-grained breakdowns & labels for varying question taxonomies. Therefore, in tandem with our academic contributions regarding LLMs' deficiency in TableQA tasks, "HiddenTables" is a tactile manifestation of how LLMs can interact with massive datasets while ensuring data security and minimizing generation costs.
Authors: Carmel Shabalin, Omri Kaduri, Roni Stern
Abstract: Multi-agent path finding (MAPF) is the problem of finding paths for multiple agents such that they do not collide. This problem manifests in numerous real-world applications such as controlling transportation robots in automated warehouses, moving characters in video games, and coordinating self-driving cars in intersections. Finding optimal solutions to MAPF is NP-Hard, yet modern optimal solvers can scale to hundreds of agents and even thousands in some cases. Different solvers employ different approaches, and there is no single state-of-the-art approach for all problems. Furthermore, there are no clear, provable, guidelines for choosing when each optimal MAPF solver to use. Prior work employed Algorithm Selection (AS) techniques to learn such guidelines from past data. A major challenge when employing AS for choosing an optimal MAPF algorithm is how to encode the given MAPF problem. Prior work either used hand-crafted features or an image representation of the problem. We explore graph-based encodings of the MAPF problem and show how they can be used on-the-fly with a modern graph embedding algorithm called FEATHER. Then, we show how this encoding can be effectively joined with existing encodings, resulting in a novel AS method we call MAPF Algorithm selection via Graph embedding (MAG). An extensive experimental evaluation of MAG on several MAPF algorithm selection tasks reveals that it is either on-par or significantly better than existing methods.
Authors: Shanshan Han, Yuhang Yao, Zijian Hu, Dimitris Stripelis, Zhaozhuo Xu, Chaoyang He
Abstract: We introduce TorchOpera, a compound AI system for enhancing the safety and quality of prompts and responses for Large Language Models. TorchOpera ensures that all user prompts are safe, contextually grounded, and effectively processed, while enhancing LLM responses to be relevant and high quality. TorchOpera utilizes the vector database for contextual grounding, rule-based wrappers for flexible modifications, and specialized mechanisms for detecting and adjusting unsafe or incorrect content. We also provide a view of the compound AI system to reduce the computational cost. Extensive experiments show that TorchOpera ensures the safety, reliability, and applicability of LLMs in real-world settings while maintaining the efficiency of LLM responses.
Authors: Yiming Tang, Bin Dong
Abstract: Large language models (LLMs) benefit greatly from prompt engineering, with in-context learning standing as a pivital technique. While former approaches have provided various ways to construct the demonstrations used for in-context learning, they often ignore the inherent heterogeneity within datasets, applying the same demonstrations to all reasoning questions. We observed that the effectiveness of demonstrations varies depending on the specific question. This motivates our exploration of using prompt engineering to select appropriate demonstrations. To address the challenge of automatically creating and choosing demonstrations tailored to each question, we propose a novel prompt engineering workflow built around a novel object called the "demonstration notebook." This notebook helps identify the most suitable in-context learning example for a question by gathering and reusing information from the LLM's past interactions. Our experiments show that this approach outperforms all existing methods for automatic demonstration construction and selection (as far as we know), achieving state-of-the-art results on serveral reasoning benchmarks. The method's versatility is further demonstrated by its success in text summarization and prompt compression tasks. Additionally, we contribute a rigorous analysis method to reveal the "demonstrative regime" of a demonstration, providing valuable insights into how demonstrations relate to different question types within a dataset.
Authors: Kevin Leyton-Brown, Yoav Shoham
Abstract: Motivated by the rapid ascent of Large Language Models (LLMs) and debates about the extent to which they possess human-level qualities, we propose a framework for testing whether any agent (be it a machine or a human) understands a subject matter. In Turing-test fashion, the framework is based solely on the agent's performance, and specifically on how well it answers questions. Elements of the framework include circumscribing the set of questions (the "scope of understanding"), requiring general competence ("passing grade"), avoiding "ridiculous answers", but still allowing wrong and "I don't know" answers to some questions. Reaching certainty about these conditions requires exhaustive testing of the questions which is impossible for nontrivial scopes, but we show how high confidence can be achieved via random sampling and the application of probabilistic confidence bounds. We also show that accompanying answers with explanations can improve the sample complexity required to achieve acceptable bounds, because an explanation of an answer implies the ability to answer many similar questions. According to our framework, current LLMs cannot be said to understand nontrivial domains, but as the framework provides a practical recipe for testing understanding, it thus also constitutes a tool for building AI agents that do understand.
Authors: Soroush Saghafian, Lihi Idan
Abstract: Advanced analytics science methods have enabled combining the power of artificial and human intelligence, creating \textit{centaurs} that allow superior decision-making. Centaurs are hybrid human-algorithm AI models that combine both formal analytics and human intuition in a symbiotic manner within their learning and reasoning process. We argue that the future of AI development and use in many domains needs to focus on centaurs as opposed to traditional AI approaches. This paradigm shift from traditional AI methods to centaur-based AI methods raises some fundamental questions: How are centaurs different from traditional human-in-the-loop methods? What are the most effective methods for creating centaurs? When should centaurs be used, and when should the lead be given to traditional AI models? Doesn't the incorporation of human intuition -- which at times can be misleading -- in centaurs' decision-making process degrade its performance compared to traditional AI methods? This work aims to address these fundamental questions, focusing on recent advancements in generative AI, and especially in Large Language Models (LLMs), as a main case study to illustrate centaurs' critical essentiality to future AI endeavors.
Authors: Jiaoyan Chen, Olga Mashkova, Fernando Zhapa-Camacho, Robert Hoehndorf, Yuan He, Ian Horrocks
Abstract: Ontologies are widely used for representing domain knowledge and meta data, playing an increasingly important role in Information Systems, the Semantic Web, Bioinformatics and many other domains. However, logical reasoning that ontologies can directly support are quite limited in learning, approximation and prediction. One straightforward solution is to integrate statistical analysis and machine learning. To this end, automatically learning vector representation for knowledge of an ontology i.e., ontology embedding has been widely investigated in recent years. Numerous papers have been published on ontology embedding, but a lack of systematic reviews hinders researchers from gaining a comprehensive understanding of this field. To bridge this gap, we write this survey paper, which first introduces different kinds of semantics of ontologies, and formally defines ontology embedding from the perspectives of both mathematics and machine learning, as well as its property of faithfulness. Based on this, it systematically categorises and analyses a relatively complete set of over 80 papers, according to the ontologies and semantics that they aim at, and their technical solutions including geometric modeling, sequence modeling and graph propagation. This survey also introduces the applications of ontology embedding in ontology engineering, machine learning augmentation and life sciences, presents a new library mOWL, and discusses the challenges and future directions.
Authors: Nicholas Kluge Corr\^ea
Abstract: The critical inquiry pervading the realm of Philosophy, and perhaps extending its influence across all Humanities disciplines, revolves around the intricacies of morality and normativity. Surprisingly, in recent years, this thematic thread has woven its way into an unexpected domain, one not conventionally associated with pondering "what ought to be": the field of artificial intelligence (AI) research. Central to morality and AI, we find "alignment", a problem related to the challenges of expressing human goals and values in a manner that artificial systems can follow without leading to unwanted adversarial effects. More explicitly and with our current paradigm of AI development in mind, we can think of alignment as teaching human values to non-anthropomorphic entities trained through opaque, gradient-based learning techniques. This work addresses alignment as a technical-philosophical problem that requires solid philosophical foundations and practical implementations that bring normative theory to AI system development. To accomplish this, we propose two sets of necessary and sufficient conditions that, we argue, should be considered in any alignment process. While necessary conditions serve as metaphysical and metaethical roots that pertain to the permissibility of alignment, sufficient conditions establish a blueprint for aligning AI systems under a learning-based paradigm. After laying such foundations, we present implementations of this approach by using state-of-the-art techniques and methods for aligning general-purpose language systems. We call this framework Dynamic Normativity. Its central thesis is that any alignment process under a learning paradigm that cannot fulfill its necessary and sufficient conditions will fail in producing aligned systems.
Authors: Miko{\l}aj Ma{\l}ki\'nski, Jacek Ma\'ndziuk
Abstract: We study generalization and knowledge reuse capabilities of deep neural networks in the domain of abstract visual reasoning (AVR), employing Raven's Progressive Matrices (RPMs), a recognized benchmark task for assessing AVR abilities. Two knowledge transfer scenarios referring to the I-RAVEN dataset are investigated. Firstly, inspired by generalization assessment capabilities of the PGM dataset and popularity of I-RAVEN, we introduce Attributeless-I-RAVEN, a benchmark with four generalization regimes that allow to test generalization of abstract rules applied to held-out attributes. Secondly, we construct I-RAVEN-Mesh, a dataset that enriches RPMs with a novel component structure comprising line-based patterns, facilitating assessment of progressive knowledge acquisition in transfer learning setting. The developed benchmarks reveal shortcomings of the contemporary deep learning models, which we partly address with Pathways of Normalized Group Convolution (PoNG) model, a novel neural architecture for solving AVR tasks. PoNG excels in both presented challenges, as well as the standard I-RAVEN and PGM setups.
Authors: Miko{\l}aj Ma{\l}ki\'nski, Jacek Ma\'ndziuk
Abstract: The field of Abstract Visual Reasoning (AVR) encompasses a wide range of problems, many of which are inspired by human IQ tests. The variety of AVR tasks has resulted in state-of-the-art AVR methods being task-specific approaches. Furthermore, contemporary methods consider each AVR problem instance not as a whole, but in the form of a set of individual panels with particular locations and roles (context vs. answer panels) pre-assigned according to the task-specific arrangements. While these highly specialized approaches have recently led to significant progress in solving particular AVR tasks, considering each task in isolation hinders the development of universal learning systems in this domain. In this paper, we introduce a unified view of AVR tasks, where each problem instance is rendered as a single image, with no a priori assumptions about the number of panels, their location, or role. The main advantage of the proposed unified view is the ability to develop universal learning models applicable to various AVR tasks. What is more, the proposed approach inherently facilitates transfer learning in the AVR domain, as various types of problems share a common representation. The experiments conducted on four AVR datasets with Raven's Progressive Matrices and Visual Analogy Problems, and one real-world visual analogy dataset show that the proposed unified representation of AVR tasks poses a challenge to state-of-the-art Deep Learning (DL) AVR models and, more broadly, contemporary DL image recognition methods. In order to address this challenge, we introduce the Unified Model for Abstract Visual Reasoning (UMAVR) capable of dealing with various types of AVR problems in a unified manner. UMAVR outperforms existing AVR methods in selected single-task learning experiments, and demonstrates effective knowledge reuse in transfer learning and curriculum learning setups.
Authors: Ghada Zamzmi, Adarsh Subbaswamy, Elena Sizikova, Edward Margerrison, Jana Delfino, Aldo Badano
Abstract: The growing utilization of synthetic medical data (SMD) in training and testing AI-driven tools in healthcare necessitates a systematic framework for assessing SMD quality. The current lack of a standardized methodology to evaluate SMD, particularly in terms of its applicability in various medical scenarios, is a significant hindrance to its broader acceptance and utilization in healthcare applications. Here, we outline an evaluation framework designed to meet the unique requirements of medical applications, and introduce the concept of SMD scorecards, which can serve as comprehensive reports that accompany artificially generated datasets. This can help standardize evaluation and enable SMD developers to assess and further enhance the quality of SMDs by identifying areas in need of attention and ensuring that the synthetic data more accurately approximate patient data.
Authors: Chengjin Xu, Muzhi Li, Cehao Yang, Xuhui Jiang, Lumingyuan Tang, Yiyan Qi, Jian Guo
Abstract: Knowledge Graphs (KGs) are foundational structures in many AI applications, representing entities and their interrelations through triples. However, triple-based KGs lack the contextual information of relational knowledge, like temporal dynamics and provenance details, which are crucial for comprehensive knowledge representation and effective reasoning. Instead, \textbf{Contextual Knowledge Graphs} (CKGs) expand upon the conventional structure by incorporating additional information such as time validity, geographic location, and source provenance. This integration provides a more nuanced and accurate understanding of knowledge, enabling KGs to offer richer insights and support more sophisticated reasoning processes. In this work, we first discuss the inherent limitations of triple-based KGs and introduce the concept of contextual KGs, highlighting their advantages in knowledge representation and reasoning. We then present \textbf{KGR$^3$, a context-enriched KG reasoning paradigm} that leverages large language models (LLMs) to retrieve candidate entities and related contexts, rank them based on the retrieved information, and reason whether sufficient information has been obtained to answer a query. Our experimental results demonstrate that KGR$^3$ significantly improves performance on KG completion (KGC) and KG question answering (KGQA) tasks, validating the effectiveness of incorporating contextual information on KG representation and reasoning.
Authors: Zebang Cheng, Zhi-Qi Cheng, Jun-Yan He, Jingdong Sun, Kai Wang, Yuxiang Lin, Zheng Lian, Xiaojiang Peng, Alexander Hauptmann
Abstract: Accurate emotion perception is crucial for various applications, including human-computer interaction, education, and counseling. However, traditional single-modality approaches often fail to capture the complexity of real-world emotional expressions, which are inherently multimodal. Moreover, existing Multimodal Large Language Models (MLLMs) face challenges in integrating audio and recognizing subtle facial micro-expressions. To address this, we introduce the MERR dataset, containing 28,618 coarse-grained and 4,487 fine-grained annotated samples across diverse emotional categories. This dataset enables models to learn from varied scenarios and generalize to real-world applications. Furthermore, we propose Emotion-LLaMA, a model that seamlessly integrates audio, visual, and textual inputs through emotion-specific encoders. By aligning features into a shared space and employing a modified LLaMA model with instruction tuning, Emotion-LLaMA significantly enhances both emotional recognition and reasoning capabilities. Extensive evaluations show Emotion-LLaMA outperforms other MLLMs, achieving top scores in Clue Overlap (7.83) and Label Overlap (6.25) on EMER, an F1 score of 0.9036 on MER2023 challenge, and the highest UAR (45.59) and WAR (59.37) in zero-shot evaluations on DFEW dataset.
Authors: Chengqian Ma, Zhanxiang Hua, Alexandra Anderson-Frey, Vikram Iyer, Xin Liu, Lianhui Qin
Abstract: Severe convective weather events, such as hail, tornadoes, and thunderstorms, often occur quickly yet cause significant damage, costing billions of dollars every year. This highlights the importance of forecasting severe weather threats hours in advance to better prepare meteorologists and residents in at-risk areas. Can modern large foundation models perform such forecasting? Existing weather benchmarks typically focus only on predicting time-series changes in certain weather parameters (e.g., temperature, moisture) with text-only features. In this work, we introduce WeatherQA, the first multimodal dataset designed for machines to reason about complex combinations of weather parameters (a.k.a., ingredients) and predict severe weather in real-world scenarios. The dataset includes over 8,000 (multi-images, text) pairs for diverse severe weather events. Each pair contains rich information crucial for forecasting -- the images describe the ingredients capturing environmental instability, surface observations, and radar reflectivity, and the text contains forecast analyses written by human experts. With WeatherQA, we evaluate state-of-the-art vision language models , including GPT4, Claude3, Gemini-1.5, and a fine-tuned Llama3-based VLM, by designing two challenging tasks: (1) multi-choice QA for predicting affected area and (2) classification of the development potential of severe convection. These tasks require deep understanding of domain knowledge (e.g., atmospheric dynamics) and complex reasoning over multimodal data (e.g., interactions between weather parameters). We show a substantial gap between the strongest VLM, GPT4o, and human reasoning. Our comprehensive case study with meteorologists further reveals the weaknesses of the models, suggesting that better training and data integration are necessary to bridge this gap. WeatherQA link: https://github.com/chengqianma/WeatherQA.
Authors: Yang Chen, Cong Fang, Zhouchen Lin, Bing Liu
Abstract: Foundation Models (FMs) have demonstrated remarkable insights into the relational dynamics of the world, leading to the crucial question: how do these models acquire an understanding of world hybrid relations? Traditional statistical learning, particularly for prediction problems, may overlook the rich and inherently structured information from the data, especially regarding the relationships between objects. We introduce a mathematical model that formalizes relational learning as hypergraph recovery to study pre-training of FMs. In our framework, the world is represented as a hypergraph, with data abstracted as random samples from hyperedges. We theoretically examine the feasibility of a Pre-Trained Model (PTM) to recover this hypergraph and analyze the data efficiency in a minimax near-optimal style. By integrating rich graph theories into the realm of PTMs, our mathematical framework offers powerful tools for an in-depth understanding of pre-training from a unique perspective and can be used under various scenarios. As an example, we extend the framework to entity alignment in multimodal learning.
Authors: Jeremy Straub
Abstract: Producing an artificial general intelligence (AGI) has been an elusive goal in artificial intelligence (AI) research for some time. An AGI would have the capability, like a human, to be exposed to a new problem domain, learn about it and then use reasoning processes to make decisions. While AI techniques have been used across a wide variety of problem domains, an AGI would require an AI that could reason beyond its programming and training. This paper presents a small step towards producing an AGI. It describes a mechanism for an AI to learn about and develop reasoning pathways to make decisions in an a priori unknown domain. It combines a classical AI technique, the expert system, with a its modern adaptation - the gradient descent trained expert system (GDTES) - and utilizes generative artificial intelligence (GAI) to create a network and training data set for this system. These can be created from available sources or may draw upon knowledge incorporated in a GAI's own pre-trained model. The learning process in GDTES is used to optimize the AI's decision-making. While this approach does not meet the standards that many have defined for an AGI, it provides a somewhat similar capability, albeit one which requires a learning process before use.
Authors: Jiuding Yang, Weidong Guo, Kaitong Yang, Xiangyang Li, Zhuwei Rao, Yu Xu, Di Niu
Abstract: The effective alignment of Large Language Models (LLMs) with precise instructions is essential for their application in diverse real-world scenarios. Current methods focus on enhancing the diversity and complexity of training and evaluation samples, yet they fall short in accurately assessing LLMs' ability to follow similar instruction variants. We introduce an effective data augmentation technique that decomposes complex instructions into simpler sub-components, modifies these, and reconstructs them into new variants, thereby preserves the original instruction's context and complexity while introducing variability, which is critical for training and evaluating LLMs' instruction-following precision. We developed the DeMoRecon dataset using this method to both fine-tune and evaluate LLMs. Our findings show that LLMs fine-tuned with DeMoRecon will gain significant performance boost on both ours and commonly used instructions-following benchmarks.
Authors: Wentong Chen, Junbo Cui, Jinyi Hu, Yujia Qin, Junjie Fang, Yue Zhao, Chongyi Wang, Jun Liu, Guirong Chen, Yupeng Huo, Yuan Yao, Yankai Lin, Zhiyuan Liu, Maosong Sun
Abstract: Utilizing Graphic User Interface (GUI) for human-computer interaction is essential for accessing a wide range of digital tools. Recent advancements in Vision Language Models (VLMs) highlight the compelling potential to develop versatile agents to help humans finish GUI navigation tasks. However, current VLMs are challenged in terms of fundamental abilities (OCR and grounding) and GUI knowledge (the functions and control methods of GUI elements), preventing them from becoming practical GUI agents. To solve these challenges, we contribute GUICourse, a suite of datasets to train visual-based GUI agents from general VLMs. First, we introduce the GUIEnv dataset to strengthen the OCR and grounding capabilities of VLMs. Then, we introduce the GUIAct and GUIChat datasets to enrich their knowledge of GUI components and interactions. Experiments demonstrate that our GUI agents have better performance on common GUI tasks than their baseline VLMs. Even the small-size GUI agent (with 3.1B parameters) can still work well on single-step and multi-step GUI tasks. Finally, we analyze the different varieties in the training stage of this agent by ablation study. Our source codes and datasets are released at https://github.com/yiye3/GUICourse.
Authors: Chao Wen, Jacqueline Staub, Adish Singla
Abstract: Large language and multimodal models have shown remarkable successes on various benchmarks focused on specific skills such as general-purpose programming, natural language understanding, math word problem-solving, and visual question answering. However, it is unclear how well these models perform on tasks that require a combination of these skills. In this paper, we curate a novel program synthesis benchmark based on the XLogoOnline visual programming environment. The benchmark comprises 85 real-world tasks from the Mini-level of the XLogoOnline environment, each requiring a combination of different skills such as spatial planning, basic programming, and logical reasoning. Our evaluation shows that current state-of-the-art models like GPT-4V and Llama3-70B struggle to solve these tasks, achieving only 20% and 2.35% success rates. Next, we develop a fine-tuning pipeline to boost the performance of models by leveraging a large-scale synthetic training dataset with over 80000 tasks. Moreover, we showcase how emulator-driven feedback can be used to design a curriculum over training data distribution. We showcase that a fine-tuned Llama3-8B drastically outperforms GPT-4V and Llama3-70B models, and provide an in-depth analysis of the models' expertise across different skill dimensions. We will publicly release the benchmark for future research on program synthesis in visual programming.
Authors: Ahmed M Salih
Abstract: Explainable Artificial Intelligence (XAI) methods help to understand the internal mechanism of machine learning models and how they reach a specific decision or made a specific action. The list of informative features is one of the most common output of XAI methods. Multicollinearity is one of the big issue that should be considered when XAI generates the explanation in terms of the most informative features in an AI system. No review has been dedicated to investigate the current approaches to handle such significant issue. In this paper, we provide a review of the current state-of-the-art approaches in relation to the XAI in the context of recent advances in dealing with the multicollinearity issue. To do so, we searched in three repositories that are: Web of Science, Scopus and IEEE Xplore to find pertinent published papers. After excluding irrelevant papers, seven papers were considered in the review. In addition, we discuss the current XAI methods and their limitations in dealing with the multicollinearity and suggest future directions.
Authors: Andr\'e Platzer
Abstract: This perspective piece calls for the study of the new field of Intersymbolic AI, by which we mean the combination of symbolic AI, whose building blocks have inherent significance/meaning, with subsymbolic AI, whose entirety creates significance/effect despite the fact that individual building blocks escape meaning. Canonical kinds of symbolic AI are logic, games and planning. Canonical kinds of subsymbolic AI are (un)supervised machine and reinforcement learning. Intersymbolic AI interlinks the worlds of symbolic AI with its compositional symbolic significance and meaning and of subsymbolic AI with its summative significance or effect to enable culminations of insights from both worlds by going between and across symbolic AI insights with subsymbolic AI techniques that are being helped by symbolic AI principles. For example, Intersymbolic AI may start with symbolic AI to understand a dynamic system, continue with subsymbolic AI to learn its control, and end with symbolic AI to safely use the outcome of the learned subsymbolic AI controller in the dynamic system. Intersymbolic AI combines both symbolic and subsymbolic AI to increase the effectiveness of AI compared to either kind of AI alone, in much the same way that the combination of both conscious and subconscious thought increases the effectiveness of human thought compared to either kind of thought alone. Some successful contributions to the Intersymbolic AI paradigm are surveyed here but many more are considered possible by advancing Intersymbolic AI.
Authors: Daman Arora, Atharv Sonwane, Nalin Wadhwa, Abhav Mehrotra, Saiteja Utpala, Ramakrishna Bairi, Aditya Kanade, Nagarajan Natarajan
Abstract: A common method to solve complex problems in software engineering, is to divide the problem into multiple sub-problems. Inspired by this, we propose a Modular Architecture for Software-engineering AI (MASAI) agents, where different LLM-powered sub-agents are instantiated with well-defined objectives and strategies tuned to achieve those objectives. Our modular architecture offers several advantages: (1) employing and tuning different problem-solving strategies across sub-agents, (2) enabling sub-agents to gather information from different sources scattered throughout a repository, and (3) avoiding unnecessarily long trajectories which inflate costs and add extraneous context. MASAI enabled us to achieve the highest performance (28.33% resolution rate) on the popular and highly challenging SWE-bench Lite dataset consisting of 300 GitHub issues from 11 Python repositories. We conduct a comprehensive evaluation of MASAI relative to other agentic methods and analyze the effects of our design decisions and their contribution to the success of MASAI.
Authors: Laura Weidinger, John Mellor, Bernat Guillen Pegueroles, Nahema Marchal, Ravin Kumar, Kristian Lum, Canfer Akbulut, Mark Diaz, Stevie Bergman, Mikel Rodriguez, Verena Rieser, William Isaac
Abstract: This research introduces STAR, a sociotechnical framework that improves on current best practices for red teaming safety of large language models. STAR makes two key contributions: it enhances steerability by generating parameterised instructions for human red teamers, leading to improved coverage of the risk surface. Parameterised instructions also provide more detailed insights into model failures at no increased cost. Second, STAR improves signal quality by matching demographics to assess harms for specific groups, resulting in more sensitive annotations. STAR further employs a novel step of arbitration to leverage diverse viewpoints and improve label reliability, treating disagreement not as noise but as a valuable contribution to signal quality.
Authors: Xinyu Zhang, Abdeslam Boularias
Abstract: Learning a single universal policy that can perform a diverse set of manipulation tasks is a promising new direction in robotics. However, existing techniques are limited to learning policies that can only perform tasks that are encountered during training, and require a large number of demonstrations to learn new tasks. Humans, on the other hand, often can learn a new task from a single unannotated demonstration. In this work, we propose the Invariance-Matching One-shot Policy Learning (IMOP) algorithm. In contrast to the standard practice of learning the end-effector's pose directly, IMOP first learns invariant regions of the state space for a given task, and then computes the end-effector's pose through matching the invariant regions between demonstrations and test scenes. Trained on the 18 RLBench tasks, IMOP achieves a success rate that outperforms the state-of-the-art consistently, by 4.5% on average over the 18 tasks. More importantly, IMOP can learn a novel task from a single unannotated demonstration, and without any fine-tuning, and achieves an average success rate improvement of $11.5\%$ over the state-of-the-art on 22 novel tasks selected across nine categories. IMOP can also generalize to new shapes and learn to manipulate objects that are different from those in the demonstration. Further, IMOP can perform one-shot sim-to-real transfer using a single real-robot demonstration.
Authors: Jie Liu, Yao Wu, Xiaotong Luo, Zongze Wu
Abstract: In industrial scenarios, it is crucial not only to identify anomalous items but also to classify the type of anomaly. However, research on anomaly multi-classification remains largely unexplored. This paper proposes a novel and valuable research task called anomaly multi-classification. Given the challenges in applying few-shot learning to this task, due to limited training data and unique characteristics of anomaly images, we introduce a baseline model that combines RelationNet and PatchCore. We propose a data generation method that creates pseudo classes and a corresponding proxy task, aiming to bridge the gap in transferring few-shot learning to industrial scenarios. Furthermore, we utilize contrastive learning to improve the vanilla baseline, achieving much better performance than directly fine-tune a ResNet. Experiments conducted on MvTec AD and MvTec3D AD demonstrate that our approach shows superior performance in this novel task.
Authors: Juzheng Zhang, Lanning Wei, Zhen Xu, Quanming Yao
Abstract: Link prediction is a fundamental task in graph learning, inherently shaped by the topology of the graph. While traditional heuristics are grounded in graph topology, they encounter challenges in generalizing across diverse graphs. Recent research efforts have aimed to leverage the potential of heuristics, yet a unified formulation accommodating both local and global heuristics remains undiscovered. Drawing insights from the fact that both local and global heuristics can be represented by adjacency matrix multiplications, we propose a unified matrix formulation to accommodate and generalize various heuristics. We further propose the Heuristic Learning Graph Neural Network (HL-GNN) to efficiently implement the formulation. HL-GNN adopts intra-layer propagation and inter-layer connections, allowing it to reach a depth of around 20 layers with lower time complexity than GCN. Extensive experiments on the Planetoid, Amazon, and OGB datasets underscore the effectiveness and efficiency of HL-GNN. It outperforms existing methods by a large margin in prediction performance. Additionally, HL-GNN is several orders of magnitude faster than heuristic-inspired methods while requiring only a few trainable parameters. The case study further demonstrates that the generalized heuristics and learned weights are highly interpretable.
Authors: Andrea Ceccarelli, Leonardo Montecchi
Abstract: Object detection in autonomous driving consists in perceiving and locating instances of objects in multi-dimensional data, such as images or lidar scans. Very recently, multiple works are proposing to evaluate object detectors by measuring their ability to detect the objects that are most likely to interfere with the driving task. Detectors are then ranked according to their ability to detect the most relevant objects, rather than the highest number of objects. However there is little evidence so far that the relevance of predicted object may contribute to the safety and reliability improvement of the driving task. This position paper elaborates on a strategy, together with partial results, to i) configure and deploy object detectors that successfully extract knowledge on object relevance, and ii) use such knowledge to improve the trajectory planning task. We show that, given an object detector, filtering objects based on their relevance, in combination with the traditional confidence threshold, reduces the risk of missing relevant objects, decreases the likelihood of dangerous trajectories, and improves the quality of trajectories in general.
Authors: Ben Fei, Yixuan Li, Weidong Yang, Hengjun Gao, Jingyi Xu, Lipeng Ma, Yatian Yang, Pinghong Zhou
Abstract: The development of medical imaging techniques has made a significant contribution to clinical decision-making. However, the existence of suboptimal imaging quality, as indicated by irregular illumination or imbalanced intensity, presents significant obstacles in automating disease screening, analysis, and diagnosis. Existing approaches for natural image enhancement are mostly trained with numerous paired images, presenting challenges in data collection and training costs, all while lacking the ability to generalize effectively. Here, we introduce a pioneering training-free Diffusion Model for Universal Medical Image Enhancement, named UniMIE. UniMIE demonstrates its unsupervised enhancement capabilities across various medical image modalities without the need for any fine-tuning. It accomplishes this by relying solely on a single pre-trained model from ImageNet. We conduct a comprehensive evaluation on 13 imaging modalities and over 15 medical types, demonstrating better qualities, robustness, and accuracy than other modality-specific and data-inefficient models. By delivering high-quality enhancement and corresponding accuracy downstream tasks across a wide range of tasks, UniMIE exhibits considerable potential to accelerate the advancement of diagnostic tools and customized treatment plans.
Authors: Sheng Zhang, Maolin Wang, Xiangyu Zhao
Abstract: In the rapidly evolving field of artificial intelligence, transformer-based models have gained significant attention in the context of Sequential Recommender Systems (SRSs), demonstrating remarkable proficiency in capturing user-item interactions. However, such attention-based frameworks result in substantial computational overhead and extended inference time. To address this problem, this paper proposes a novel efficient sequential recommendation framework GLINT-RU that leverages dense selective Gated Recurrent Units (GRU) module to accelerate the inference speed, which is a pioneering work to further exploit the potential of efficient GRU modules in SRSs. The GRU module lies at the heart of GLINT-RU, playing a crucial role in substantially reducing both inference time and GPU memory usage. Through the integration of a dense selective gate, our framework adeptly captures both long-term and short-term item dependencies, enabling the adaptive generation of item scores. GLINT-RU further integrates a mixing block, enriching it with global user-item interaction information to bolster recommendation quality. Moreover, we design a gated Multi-layer Perceptron (MLP) for our framework where the information is deeply filtered. Extensive experiments on three datasets are conducted to highlight the effectiveness and efficiency of GLINT-RU. Our GLINT-RU achieves exceptional inference speed and prediction accuracy, outperforming existing baselines based on Recurrent Neural Network (RNN), Transformer, MLP and State Space Model (SSM). These results establish a new standard in sequential recommendation, highlighting the potential of GLINT-RU as a renewing approach in the realm of recommender systems.
Authors: A. Fuster-L\'opez, J. M. Cruz, P. Guerrero-Garc\'ia, E. M. T. Hendrix, A. Ko\v{s}ir, I. Nowak, L. Oneto, S. Sirmakessis, M. F. Pacheco, F. P. Fernandes, A. I. Pereira
Abstract: The use of e-learning systems has a long tradition, where students can study online helped by a system. In this context, the use of recommender systems is relatively new. In our research project, we investigated various ways to create a recommender system. They all aim at facilitating the learning and understanding of a student. We present a common concept of the learning path and its learning indicators and embed 5 different recommenders in this context.
Authors: Mingming Li, Fuqing Zhu, Feng Yuan, Songlin Hu
Abstract: Recently, relational metric learning methods have been received great attention in recommendation community, which is inspired by the translation mechanism in knowledge graph. Different from the knowledge graph where the entity-to-entity relations are given in advance, historical interactions lack explicit relations between users and items in recommender systems. Currently, many researchers have succeeded in constructing the implicit relations to remit this issue. However, in previous work, the learning process of the induction function only depends on a single source of data (i.e., user-item interaction) in a supervised manner, resulting in the co-occurrence relation that is free of any semantic information. In this paper, to tackle the above problem in recommender systems, we propose a joint Semantic-Enhanced Relational Metric Learning (SERML) framework that incorporates the semantic information. Specifically, the semantic signal is first extracted from the target reviews containing abundant item features and personalized user preferences. A novel regression model is then designed via leveraging the extracted semantic signal to improve the discriminative ability of original relation-based training process. On four widely-used public datasets, experimental results demonstrate that SERML produces a competitive performance compared with several state-of-the-art methods in recommender systems.
Authors: Vinay Joshi, Prashant Laddha, Shambhavi Sinha, Om Ji Omer, Sreenivas Subramoney
Abstract: Excessive memory requirements of key and value features (KV-cache) present significant challenges in the autoregressive inference of large language models (LLMs), restricting both the speed and length of text generation. Approaches such as Multi-Query Attention (MQA) and Grouped Query Attention (GQA) mitigate these challenges by grouping query heads and consequently reducing the number of corresponding key and value heads. However, MQA and GQA decrease the KV-cache size requirements at the expense of LLM accuracy (quality of text generation). These methods do not ensure an optimal tradeoff between KV-cache size and text generation quality due to the absence of quality-aware grouping of query heads. To address this issue, we propose Quality and Capacity-Aware Grouped Query Attention (QCQA), which identifies optimal query head groupings using an evolutionary algorithm with a computationally efficient and inexpensive fitness function. We demonstrate that QCQA achieves a significantly better tradeoff between KV-cache capacity and LLM accuracy compared to GQA. For the Llama2 $7\,$B model, QCQA achieves $\mathbf{20}$\% higher accuracy than GQA with similar KV-cache size requirements in the absence of fine-tuning. After fine-tuning both QCQA and GQA, for a similar KV-cache size, QCQA provides $\mathbf{10.55}\,$\% higher accuracy than GQA. Furthermore, QCQA requires $40\,$\% less KV-cache size than GQA to attain similar accuracy. The proposed quality and capacity-aware grouping of query heads can serve as a new paradigm for KV-cache optimization in autoregressive LLM inference.
Authors: Bowen Cao, Deng Cai, Zhisong Zhang, Yuexian Zou, Wai Lam
Abstract: The performance of large language models (LLMs) is acutely sensitive to the phrasing of prompts, which raises significant concerns about their reliability in real-world scenarios. Existing studies often divide prompts into task-level instructions and case-level inputs and primarily focus on evaluating and improving robustness against variations in tasks-level instructions. However, this setup fails to fully address the diversity of real-world user queries and assumes the existence of task-specific datasets. To address these limitations, we introduce RobustAlpacaEval, a new benchmark that consists of semantically equivalent case-level queries and emphasizes the importance of using the worst prompt performance to gauge the lower bound of model performance. Extensive experiments on RobustAlpacaEval with ChatGPT and six open-source LLMs from the Llama, Mistral, and Gemma families uncover substantial variability in model performance; for instance, a difference of 45.48% between the worst and best performance for the Llama-2-70B-chat model, with its worst performance dipping as low as 9.38%. We further illustrate the difficulty in identifying the worst prompt from both model-agnostic and model-dependent perspectives, emphasizing the absence of a shortcut to characterize the worst prompt. We also attempt to enhance the worst prompt performance using existing prompt engineering and prompt consistency methods, but find that their impact is limited. These findings underscore the need to create more resilient LLMs that can maintain high performance across diverse prompts.
Authors: Mert Yazan, Suzan Verberne, Frederik Situmeang
Abstract: Post-training quantization reduces the computational demand of Large Language Models (LLMs) but can weaken some of their capabilities. Since LLM abilities emerge with scale, smaller LLMs are more sensitive to quantization. In this paper, we explore how quantization affects smaller LLMs' ability to perform retrieval-augmented generation (RAG), specifically in longer contexts. We chose personalization for evaluation because it is a challenging domain to perform using RAG as it requires long-context reasoning over multiple documents. We compare the original FP16 and the quantized INT4 performance of multiple 7B and 8B LLMs on two tasks while progressively increasing the number of retrieved documents to test how quantized models fare against longer contexts. To better understand the effect of retrieval, we evaluate three retrieval models in our experiments. Our findings reveal that if a 7B LLM performs the task well, quantization does not impair its performance and long-context reasoning capabilities. We conclude that it is possible to utilize RAG with quantized smaller LLMs.
Authors: Yidong Wang, Qi Guo, Wenjin Yao, Hongbo Zhang, Xin Zhang, Zhen Wu, Meishan Zhang, Xinyu Dai, Min Zhang, Qingsong Wen, Wei Ye, Shikun Zhang, Yue Zhang
Abstract: This paper introduces AutoSurvey, a speedy and well-organized methodology for automating the creation of comprehensive literature surveys in rapidly evolving fields like artificial intelligence. Traditional survey paper creation faces challenges due to the vast volume and complexity of information, prompting the need for efficient survey methods. While large language models (LLMs) offer promise in automating this process, challenges such as context window limitations, parametric knowledge constraints, and the lack of evaluation benchmarks remain. AutoSurvey addresses these challenges through a systematic approach that involves initial retrieval and outline generation, subsection drafting by specialized LLMs, integration and refinement, and rigorous evaluation and iteration. Our contributions include a comprehensive solution to the survey problem, a reliable evaluation method, and experimental validation demonstrating AutoSurvey's effectiveness.
Authors: Jovan Andonov, Octavian Ganea, Paulina Grnarova, Gary B\'ecigneul, Thomas Hofmann
Abstract: Language Modelling has been a central part of Natural Language Processing for a very long time and in the past few years LSTM-based language models have been the go-to method for commercial language modeling. Recently, it has been shown that when looking at language modelling from a matrix factorization point of view, the final Softmax layer limits the expressiveness of the model, by putting an upper bound on the rank of the resulting matrix. Additionally, a new family of neural networks based called NeuralODEs, has been introduced as a continuous alternative to Residual Networks. Moreover, it has been shown that there is a connection between these models and Normalizing Flows. In this work we propose a new family of language models based on NeuralODEs and the continuous analogue of Normalizing Flows and manage to improve on some of the baselines.
Authors: Pengfei Zhou, Weiqing Min, Chaoran Fu, Ying Jin, Mingyu Huang, Xiangyang Li, Shuhuan Mei, Shuqiang Jiang
Abstract: Food is foundational to human life, serving not only as a source of nourishment but also as a cornerstone of cultural identity and social interaction. As the complexity of global dietary needs and preferences grows, food intelligence is needed to enable food perception and reasoning for various tasks, ranging from recipe generation and dietary recommendation to diet-disease correlation discovery and understanding. Towards this goal, for powerful capabilities across various domains and tasks in Large Language Models (LLMs), we introduce Food-oriented LLM FoodSky to comprehend food data through perception and reasoning. Considering the complexity and typicality of Chinese cuisine, we first construct one comprehensive Chinese food corpus FoodEarth from various authoritative sources, which can be leveraged by FoodSky to achieve deep understanding of food-related data. We then propose Topic-based Selective State Space Model (TS3M) and the Hierarchical Topic Retrieval Augmented Generation (HTRAG) mechanism to enhance FoodSky in capturing fine-grained food semantics and generating context-aware food-relevant text, respectively. Our extensive evaluations demonstrate that FoodSky significantly outperforms general-purpose LLMs in both chef and dietetic examinations, with an accuracy of 67.2% and 66.4% on the Chinese National Chef Exam and the National Dietetic Exam, respectively. FoodSky not only promises to enhance culinary creativity and promote healthier eating patterns, but also sets a new standard for domain-specific LLMs that address complex real-world issues in the food domain. An online demonstration of FoodSky is available at http://222.92.101.211:8200.
Authors: Yuki Uehara, Shunnosuke Ikeda, Naoki Nishimura, Koya Ohashi, Yilin Li, Jie Yang, Deddy Jobson, Xingxia Zha, Takeshi Matsumoto, Noriyoshi Sukegawa, Yuichi Takano
Abstract: In two-sided marketplaces such as online flea markets, recommender systems for providing consumers with personalized item rankings play a key role in promoting transactions between providers and consumers. Meanwhile, two-sided marketplaces face the problem of balancing consumer satisfaction and fairness among items to stimulate activity of item providers. Saito and Joachims (2022) devised an impact-based fair ranking method for maximizing the Nash social welfare based on fair division; however, this method, which requires solving a large-scale constrained nonlinear optimization problem, is very difficult to apply to practical-scale recommender systems. We thus propose a fast solution to the impact-based fair ranking problem. We first transform the fair ranking problem into an unconstrained optimization problem and then design a gradient ascent method that repeatedly executes the Sinkhorn algorithm. Experimental results demonstrate that our algorithm provides fair rankings of high quality and is about 1000 times faster than application of commercial optimization software.
Authors: Krystian Zawistowski
Abstract: LLM text decoding is key component for perceived LLM quality. We demonstrate two experiments showing that decoding methods could be improved by manipulation of token probabilities. First, we test few LLM on SummEval summary scoring dataset, to measure reading comprehension. We compare scores from greedy decoding to expected values over the next token distribution. We scale logits by large temperature to increase the entropy of scores. This allows strong improvement of performance on SummEval (in terms of correlations to human judgement). We see improvement from 6-8% to 13-28% for 7B Mistral and from 20%-46% to 37%-56% for Mixtral, beating GPT 4 0314 result on two metrics. Part of the gain seems related to positional bias. Secondly, we use probability-based tree sampling algorithm, to examine all most probable generations for given prompt.
Authors: Alexandre Bonlarron, Jean-Charles R\'egin
Abstract: This paper presents NgramMarkov, a variant of the Markov constraints. It is dedicated to text generation in constraint programming (CP). It involves a set of n-grams (i.e., sequence of n words) associated with probabilities given by a large language model (LLM). It limits the product of the probabilities of the n-gram of a sentence. The propagator of this constraint can be seen as an extension of the ElementaryMarkov constraint propagator, incorporating the LLM distribution instead of the maximum likelihood estimation of n-grams. It uses a gliding threshold, i.e., it rejects n-grams whose local probabilities are too low, to guarantee balanced solutions. It can also be combined with a "look-ahead" approach to remove n-grams that are very unlikely to lead to acceptable sentences for a fixed-length horizon. This idea is based on the MDDMarkovProcess constraint propagator, but without explicitly using an MDD (Multi-Valued Decision Diagram). The experimental results show that the generated text is valued in a similar way to the LLM perplexity function. Using this new constraint dramatically reduces the number of candidate sentences produced, improves computation times, and allows larger corpora or smaller n-grams to be used. A real-world problem has been solved for the first time using 4-grams instead of 5-grams.
Authors: Matteo Esposito, Francesco Palagiano, Valentina Lenarduzzi
Abstract: Context. Risk analysis assesses potential risks in specific scenarios. Risk analysis principles are context-less; the same methodology can be applied to a risk connected to health and information technology security. Risk analysis requires a vast knowledge of national and international regulations and standards and is time and effort-intensive. A large language model can quickly summarize information in less time than a human and can be fine-tuned to specific tasks. Aim. Our empirical study aims to investigate the effectiveness of Retrieval-Augmented Generation and fine-tuned LLM in Risk analysis. To our knowledge, no prior study has explored its capabilities in risk analysis. Method. We manually curated \totalscenarios unique scenarios leading to \totalsamples representative samples from over 50 mission-critical analyses archived by the industrial context team in the last five years. We compared the base GPT-3.5 and GPT-4 models versus their Retrieval-Augmented Generation and fine-tuned counterparts. We employ two human experts as competitors of the models and three other three human experts to review the models and the former human expert's analysis. The reviewers analyzed 5,000 scenario analyses. Results and Conclusions. HEs demonstrated higher accuracy, but LLMs are quicker and more actionable. Moreover, our findings show that RAG-assisted LLMs have the lowest hallucination rates, effectively uncovering hidden risks and complementing human expertise. Thus, the choice of model depends on specific needs, with FTMs for accuracy, RAG for hidden risks discovery, and base models for comprehensiveness and actionability. Therefore, experts can leverage LLMs for an effective complementing companion in risk analysis within a condensed timeframe. They can also save costs by averting unnecessary expenses associated with implementing unwarranted countermeasures.
Authors: Renlong Jie, Xiaojun Meng, Lifeng Shang, Xin Jiang, Qun Liu
Abstract: Large language models (LLMs) have attracted great attention given their strong performance on a wide range of NLP tasks. In practice, users often expect generated texts to fall within a specific length range, making length controlled generation an important topic, especially for GPT-style models. Existing length control methods mostly focus on a simple control type of "equal to" a target length. Different from them, we propose a prompt-based method to achieve length controlled generation under different control types with high accuracy. In particular, we adopt reinforcement learning (RL) and sample filtering with the reward signal given by rule-based reward models, which enhances the length control ability of models by rewarding outputs that follow certain control instructions. In addition, we introduce a standard prompt extractor to parse arbitrary users' input into standard control instructions. Experiments show that our method significantly improves the accuracy of prompt-based length control on popular summarization datasets like CNNDM and NYT under multiple control types. Moreover, both the standard prompt extractor and RL-tuned model show strong generalization to unseen control prompt templates.
Authors: Joseph Spracklen, Raveen Wijewickrama, A H M Nazmus Sakib, Anindya Maiti, Murtuza Jadliwala
Abstract: The reliance of popular programming languages such as Python and JavaScript on centralized package repositories and open-source software, combined with the emergence of code-generating Large Language Models (LLMs), has created a new type of threat to the software supply chain: package hallucinations. These hallucinations, which arise from fact-conflicting errors when generating code using LLMs, represent a novel form of package confusion attack that poses a critical threat to the integrity of the software supply chain. This paper conducts a rigorous and comprehensive evaluation of package hallucinations across different programming languages, settings, and parameters, exploring how different configurations of LLMs affect the likelihood of generating erroneous package recommendations and identifying the root causes of this phenomena. Using 16 different popular code generation models, across two programming languages and two unique prompt datasets, we collect 576,000 code samples which we analyze for package hallucinations. Our findings reveal that 19.7% of generated packages across all the tested LLMs are hallucinated, including a staggering 205,474 unique examples of hallucinated package names, further underscoring the severity and pervasiveness of this threat. We also implemented and evaluated mitigation strategies based on Retrieval Augmented Generation (RAG), self-detected feedback, and supervised fine-tuning. These techniques demonstrably reduced package hallucinations, with hallucination rates for one model dropping below 3%. While the mitigation efforts were effective in reducing hallucination rates, our study reveals that package hallucinations are a systemic and persistent phenomenon that pose a significant challenge for code generating LLMs.
Authors: Zijin Lin, Yue Zhao, Kai Chen, Jinwen He
Abstract: Deep neural networks (DNNs) have revolutionized the field of computer vision like object detection with their unparalleled performance. However, existing research has shown that DNNs are vulnerable to adversarial attacks. In the physical world, an adversary could exploit adversarial patches to implement a Hiding Attack (HA) which patches the target object to make it disappear from the detector, and an Appearing Attack (AA) which fools the detector into misclassifying the patch as a specific object. Recently, many defense methods for detectors have been proposed to mitigate the potential threats of adversarial patches. However, such methods still have limitations in generalization, robustness and efficiency. Most defenses are only effective against the HA, leaving the detector vulnerable to the AA. In this paper, we propose \textit{NutNet}, an innovative model for detecting adversarial patches, with high generalization, robustness and efficiency. With experiments for six detectors including YOLOv2-v4, SSD, Faster RCNN and DETR on both digital and physical domains, the results show that our proposed method can effectively defend against both the HA and AA, with only 0.4\% sacrifice of the clean performance. We compare NutNet with four baseline defense methods for detectors, and our method exhibits an average defense performance that is over 2.4 times and 4.7 times higher than existing approaches for HA and AA, respectively. In addition, NutNet only increases the inference time by 8\%, which can meet the real-time requirements of the detection systems. Demos of NutNet are available at: \url{https://sites.google.com/view/nutnet}.
Authors: Jens Otto, Niels Gr\"uttemeier, Felix Specht
Abstract: Cyber-physical production systems consist of highly specialized software and hardware components. Most components and communication protocols are not built according to the Secure by Design principle. Therefore, their resilience to cyberattacks is limited. This limitation can be overcome with common operational pictures generated by security monitoring solutions. These pictures provide information about communication relationships of both attacked and non-attacked devices, and serve as a decision-making basis for security officers in the event of cyberattacks. The objective of these decisions is to isolate a limited number of devices rather than shutting down the entire production system. In this work, we propose and evaluate a concept for finding the devices to isolate. Our approach is based on solving the Critical Node Cut Problem with Vulnerable Vertices (CNP-V) - an NP-hard computational problem originally motivated by isolating vulnerable people in case of a pandemic. To the best of our knowledge, this is the first work on applying CNP-V in context of cybersecurity.
Authors: Cheng Niu, Yang Guan, Yuanhao Wu, Juno Zhu, Juntong Song, Randy Zhong, Kaihua Zhu, Siliang Xu, Shizhe Diao, Tong Zhang
Abstract: The proliferation of fake news poses a significant threat not only by disseminating misleading information but also by undermining the very foundations of democracy. The recent advance of generative artificial intelligence has further exacerbated the challenge of distinguishing genuine news from fabricated stories. In response to this challenge, we introduce VeraCT Scan, a novel retrieval-augmented system for fake news detection. This system operates by extracting the core facts from a given piece of news and subsequently conducting an internet-wide search to identify corroborating or conflicting reports. Then sources' credibility is leveraged for information verification. Besides determining the veracity of news, we also provide transparent evidence and reasoning to support its conclusions, resulting in the interpretability and trust in the results. In addition to GPT-4 Turbo, Llama-2 13B is also fine-tuned for news content understanding, information verification, and reasoning. Both implementations have demonstrated state-of-the-art accuracy in the realm of fake news detection.
Authors: Rithesh Murthy, Liangwei Yang, Juntao Tan, Tulika Manoj Awalgaonkar, Yilun Zhou, Shelby Heinecke, Sachin Desai, Jason Wu, Ran Xu, Sarah Tan, Jianguo Zhang, Zhiwei Liu, Shirley Kokane, Zuxin Liu, Ming Zhu, Huan Wang, Caiming Xiong, Silvio Savarese
Abstract: The deployment of Large Language Models (LLMs) and Large Multimodal Models (LMMs) on mobile devices has gained significant attention due to the benefits of enhanced privacy, stability, and personalization. However, the hardware constraints of mobile devices necessitate the use of models with fewer parameters and model compression techniques like quantization. Currently, there is limited understanding of quantization's impact on various task performances, including LLM tasks, LMM tasks, and, critically, trust and safety. There is a lack of adequate tools for systematically testing these models on mobile devices. To address these gaps, we introduce MobileAIBench, a comprehensive benchmarking framework for evaluating mobile-optimized LLMs and LMMs. MobileAIBench assesses models across different sizes, quantization levels, and tasks, measuring latency and resource consumption on real devices. Our two-part open-source framework includes a library for running evaluations on desktops and an iOS app for on-device latency and hardware utilization measurements. Our thorough analysis aims to accelerate mobile AI research and deployment by providing insights into the performance and feasibility of deploying LLMs and LMMs on mobile platforms.
Authors: Heeseok Jung, Jaesang Yoo, Yohaan Yoon, Yeonju Jang
Abstract: Knowledge tracing (KT), wherein students' problem-solving histories are used to estimate their current levels of knowledge, has attracted significant interest from researchers. However, most existing KT models were developed with an ID-based paradigm, which exhibits limitations in cold-start performance. These limitations can be mitigated by leveraging the vast quantities of external knowledge possessed by generative large language models (LLMs). In this study, we propose cold-start mitigation in knowledge tracing by aligning a generative language model as a students' knowledge tracer (CLST) as a framework that utilizes a generative LLM as a knowledge tracer. Upon collecting data from math, social studies, and science subjects, we framed the KT task as a natural language processing task, wherein problem-solving data are expressed in natural language, and fine-tuned the generative LLM using the formatted KT dataset. Subsequently, we evaluated the performance of the CLST in situations of data scarcity using various baseline models for comparison. The results indicate that the CLST significantly enhanced performance with a dataset of fewer than 100 students in terms of prediction, reliability, and cross-domain generalization.
Authors: Shuyi Li, Shaojuan Wu, Xiaowang Zhang, Zhiyong Feng
Abstract: Recognizing relations between two words is a fundamental task with the broad applications. Different from extracting relations from text, it is difficult to identify relations among words without their contexts. Especially for long-tail relations, it becomes more difficult due to inadequate semantic features. Existing approaches based on language models (LMs) utilize rich knowledge of LMs to enhance the semantic features of relations. However, they capture uncommon relations while overlooking less frequent but meaningful ones since knowledge of LMs seriously relies on trained data where often represents common relations. On the other hand, long-tail relations are often uncommon in training data. It is interesting but not trivial to use external knowledge to enrich LMs due to collecting corpus containing long-tail relationships is hardly feasible. In this paper, we propose a sememe knowledge enhanced method (SememeLM) to enhance the representation of long-tail relations, in which sememes can break the contextual constraints between wors. Firstly, we present a sememe relation graph and propose a graph encoding method. Moreover, since external knowledge base possibly consisting of massive irrelevant knowledge, the noise is introduced. We propose a consistency alignment module, which aligns the introduced knowledge with LMs, reduces the noise and integrates the knowledge into the language model. Finally, we conducted experiments on word analogy datasets, which evaluates the ability to distinguish relation representations subtle differences, including long-tail relations. Extensive experiments show that our approach outperforms some state-of-the-art methods.
Authors: Jinqiang Wang, Huansheng Ning, Yi Peng, Qikai Wei, Daniel Tesfai, Wenwei Mao, Tao Zhu, Runhe Huang
Abstract: Large Language Models (LLMs) have demonstrated surprising performance across various natural language processing tasks. Recently, medical LLMs enhanced with domain-specific knowledge have exhibited excellent capabilities in medical consultation and diagnosis. These models can smoothly simulate doctor-patient dialogues and provide professional medical advice. Most medical LLMs are developed through continued training of open-source general LLMs, which require significantly fewer computational resources than training LLMs from scratch. Additionally, this approach offers better protection of patient privacy compared to API-based solutions. This survey systematically explores how to train medical LLMs based on general LLMs. It covers: (a) how to acquire training corpus and construct customized medical training sets, (b) how to choose a appropriate training paradigm, (c) how to choose a suitable evaluation benchmark, and (d) existing challenges and promising future research directions are discussed. This survey can provide guidance for the development of LLMs focused on various medical applications, such as medical education, diagnostic planning, and clinical assistants.
Authors: Jie Chen, Xintian Han, Yu Ma, Xun Zhou, Liang Xiang
Abstract: Automatic code generation has been a longstanding research topic. With the advancement of general-purpose large language models (LLMs), the ability to code stands out as one important measure to the model's reasoning performance. Usually, a two-stage training paradigm is implemented to obtain a Code LLM, namely the pretraining and the fine-tuning. Within the fine-tuning, supervised fine-tuning (SFT), and reinforcement learning (RL) are often used to improve the model's zero-shot ability. A large number of work has been conducted to improve the model's performance on code-related benchmarks with either modifications to the algorithm or refinement of the dataset. However, we still lack a deep insight into the correlation between SFT and RL. For instance, what kind of dataset should be used to ensure generalization, or what if we abandon the SFT phase in fine-tuning. In this work, we make an attempt to understand the correlation between SFT and RL. To facilitate our research, we manually craft 100 basis python functions, called atomic functions, and then a synthesizing pipeline is deployed to create a large number of synthetic functions on top of the atomic ones. In this manner, we ensure that the train and test sets remain distinct, preventing data contamination. Through comprehensive ablation study, we find: (1) Both atomic and synthetic functions are indispensable for SFT's generalization, and only a handful of synthetic functions are adequate; (2) Through RL, the SFT's generalization to target domain can be greatly enhanced, even with the same training prompts; (3) Training RL from scratch can alleviate the over-fitting issue introduced in the SFT phase.
Authors: Shiguo Lian, Kaikai Zhao, Xinhui Liu, Xuejiao Lei, Bikun Yang, Wenjing Zhang, Kai Wang, Zhaoxiang Liu
Abstract: General large language models enhanced with supervised fine-tuning and reinforcement learning from human feedback are increasingly popular in academia and industry as they generalize foundation models to various practical tasks in a prompt manner. To assist users in selecting the best model in practical application scenarios, i.e., choosing the model that meets the application requirements while minimizing cost, we introduce A-Eval, an application-driven LLMs evaluation benchmark for general large language models. First, we categorize evaluation tasks into five main categories and 27 sub-categories from a practical application perspective. Next, we construct a dataset comprising 678 question-and-answer pairs through a process of collecting, annotating, and reviewing. Then, we design an objective and effective evaluation method and evaluate a series of LLMs of different scales on A-Eval. Finally, we reveal interesting laws regarding model scale and task difficulty level and propose a feasible method for selecting the best model. Through A-Eval, we provide clear empirical and engineer guidance for selecting the best model, reducing barriers to selecting and using LLMs and promoting their application and development. Our benchmark is publicly available at https://github.com/UnicomAI/DataSet/tree/main/TestData/GeneralAbility.
URLs: https://github.com/UnicomAI/DataSet/tree/main/TestData/GeneralAbility.
Authors: Zhuofeng Li, Zixing Gou, Xiangnan Zhang, Zhongyuan Liu, Sirui Li, Yuntong Hu, Chen Ling, Zheng Zhang, Liang Zhao
Abstract: Text-Attributed Graphs (TAGs) augment graph structures with natural language descriptions, facilitating detailed depictions of data and their interconnections across various real-world settings. However, existing TAG datasets predominantly feature textual information only at the nodes, with edges typically represented by mere binary or categorical attributes. This lack of rich textual edge annotations significantly limits the exploration of contextual relationships between entities, hindering deeper insights into graph-structured data. To address this gap, we introduce Textual-Edge Graphs Datasets and Benchmark (TEG-DB), a comprehensive and diverse collection of benchmark textual-edge datasets featuring rich textual descriptions on nodes and edges. The TEG-DB datasets are large-scale and encompass a wide range of domains, from citation networks to social networks. In addition, we conduct extensive benchmark experiments on TEG-DB to assess the extent to which current techniques, including pre-trained language models, graph neural networks, and their combinations, can utilize textual node and edge information. Our goal is to elicit advancements in textual-edge graph research, specifically in developing methodologies that exploit rich textual node and edge descriptions to enhance graph analysis and provide deeper insights into complex real-world networks. The entire TEG-DB project is publicly accessible as an open-source repository on Github, accessible at https://github.com/Zhuofeng-Li/TEG-Benchmark.
Authors: Wenjing Zhang, Xuejiao Lei, Zhaoxiang Liu, Meijuan An, Bikun Yang, KaiKai Zhao, Kai Wang, Shiguo Lian
Abstract: With the profound development of large language models(LLMs), their safety concerns have garnered increasing attention. However, there is a scarcity of Chinese safety benchmarks for LLMs, and the existing safety taxonomies are inadequate, lacking comprehensive safety detection capabilities in authentic Chinese scenarios. In this work, we introduce CHiSafetyBench, a dedicated safety benchmark for evaluating LLMs' capabilities in identifying risky content and refusing answering risky questions in Chinese contexts. CHiSafetyBench incorporates a dataset that covers a hierarchical Chinese safety taxonomy consisting of 5 risk areas and 31 categories. This dataset comprises two types of tasks: multiple-choice questions and question-answering, evaluating LLMs from the perspectives of risk content identification and the ability to refuse answering risky questions respectively. Utilizing this benchmark, we validate the feasibility of automatic evaluation as a substitute for human evaluation and conduct comprehensive automatic safety assessments on mainstream Chinese LLMs. Our experiments reveal the varying performance of different models across various safety domains, indicating that all models possess considerable potential for improvement in Chinese safety capabilities. Our dataset is publicly available at https://github.com/UnicomAI/DataSet/tree/main/TestData/Safety.
URLs: https://github.com/UnicomAI/DataSet/tree/main/TestData/Safety.
Authors: Tuo Zhang, Tiantian Feng, Yibin Ni, Mengqin Cao, Ruying Liu, Katharine Butler, Yanjun Weng, Mi Zhang, Shrikanth S. Narayanan, Salman Avestimehr
Abstract: Large vision-language models (VLMs) have demonstrated remarkable abilities in understanding everyday content. However, their performance in the domain of art, particularly culturally rich art forms, remains less explored. As a pearl of human wisdom and creativity, art encapsulates complex cultural narratives and symbolism. In this paper, we offer the Pun Rebus Art Dataset, a multimodal dataset for art understanding deeply rooted in traditional Chinese culture. We focus on three primary tasks: identifying salient visual elements, matching elements with their symbolic meanings, and explanations for the conveyed messages. Our evaluation reveals that state-of-the-art VLMs struggle with these tasks, often providing biased and hallucinated explanations and showing limited improvement through in-context learning. By releasing the Pun Rebus Art Dataset, we aim to facilitate the development of VLMs that can better understand and interpret culturally specific content, promoting greater inclusiveness beyond English-based corpora.
Authors: Karl Munson, Chih-Kai Ting, Serenity Wade, Anish Savla, Julian Dolby, Kiran Kate, Kavitha Srinivas
Abstract: Like text, programs have styles, and certain programming styles are more desirable than others for program readability, maintainability, and performance. Code style transfer, however, is difficult to automate except for trivial style guidelines such as limits on line length. Inspired by the success of using language models for text style transfer, we investigate if code language models can perform code style transfer. Code style transfer, unlike text transfer, has rigorous requirements: the system needs to identify lines of code to change, change them correctly, and leave the rest of the program untouched. We designed CSB (Code Style Benchmark), a benchmark suite of code style transfer tasks across five categories including converting for-loops to list comprehensions, eliminating duplication in code, adding decorators to methods, etc. We then used these tests to see if large pre-trained code language models or fine-tuned models perform style transfer correctly, based on rigorous metrics to test that the transfer did occur, and the code still passes functional tests. Surprisingly, language models failed to perform all of the tasks, suggesting that they perform poorly on tasks that require code understanding. We will make available the large-scale corpora to help the community build better code models.
Authors: Samuele Bortolotti, Emanuele Marconato, Tommaso Carraro, Paolo Morettin, Emile van Krieken, Antonio Vergari, Stefano Teso, Andrea Passerini
Abstract: The advent of powerful neural classifiers has increased interest in problems that require both learning and reasoning. These problems are critical for understanding important properties of models, such as trustworthiness, generalization, interpretability, and compliance to safety and structural constraints. However, recent research observed that tasks requiring both learning and reasoning on background knowledge often suffer from reasoning shortcuts (RSs): predictors can solve the downstream reasoning task without associating the correct concepts to the high-dimensional data. To address this issue, we introduce rsbench, a comprehensive benchmark suite designed to systematically evaluate the impact of RSs on models by providing easy access to highly customizable tasks affected by RSs. Furthermore, rsbench implements common metrics for evaluating concept quality and introduces novel formal verification procedures for assessing the presence of RSs in learning tasks. Using rsbench, we highlight that obtaining high quality concepts in both purely neural and neuro-symbolic models is a far-from-solved problem. rsbench is available at: https://unitn-sml.github.io/rsbench.
Authors: Gasser Elbanna
Abstract: Speaker identity plays a significant role in human communication and is being increasingly used in societal applications, many through advances in machine learning. Speaker identity perception is an essential cognitive phenomenon that can be broadly reduced to two main tasks: recognizing a voice or discriminating between voices. Several studies have attempted to identify acoustic correlates of identity perception to pinpoint salient parameters for such a task. Unlike other communicative social signals, most efforts have yielded inefficacious conclusions. Furthermore, current neurocognitive models of voice identity processing consider the bases of perception as acoustic dimensions such as fundamental frequency, harmonics-to-noise ratio, and formant dispersion. However, these findings do not account for naturalistic speech and within-speaker variability. Representational spaces of current self-supervised models have shown significant performance in various speech-related tasks. In this work, we demonstrate that self-supervised representations from different families (e.g., generative, contrastive, and predictive models) are significantly better for speaker identification over acoustic representations. We also show that such a speaker identification task can be used to better understand the nature of acoustic information representation in different layers of these powerful networks. By evaluating speaker identification accuracy across acoustic, phonemic, prosodic, and linguistic variants, we report similarity between model performance and human identity perception. We further examine these similarities by juxtaposing the encoding spaces of models and humans and challenging the use of distance metrics as a proxy for speaker proximity. Lastly, we show that some models can predict brain responses in Auditory and Language regions during naturalistic stimuli.
Authors: Ryan Yu, Alex Olshevsky, Peter Chin
Abstract: Neural network supported tree-search has shown strong results in a variety of perfect information multi-agent tasks. However, the performance of these methods on partial information games has generally been below competing approaches. Here we study the class of simultaneous-move games, which are a subclass of partial information games which are most similar to perfect information games: both agents know the game state with the exception of the opponent's move, which is revealed only after each agent makes its own move. Simultaneous move games include popular benchmarks such as Google Research Football and Starcraft. In this study we answer the question: can we take tree search algorithms trained through self-play from perfect information settings and adapt them to simultaneous move games without significant loss of performance? We answer this question by deriving a practical method that attempts to approximate a coarse correlated equilibrium as a subroutine within a tree search. Our algorithm works on cooperative, competitive, and mixed tasks. Our results are better than the current best MARL algorithms on a wide range of accepted baseline environments.
Authors: Terrence Neumann, Bryan Jones
Abstract: The rapid advancement of open-source foundation models has brought transparency and accessibility to this groundbreaking technology. However, this openness has also enabled the development of highly-capable, unsafe models, as exemplified by recent instances such as WormGPT and FraudGPT, which are specifically designed to facilitate criminal activity. As the capabilities of open foundation models continue to grow, potentially outpacing those of closed-source models, the risk of misuse by bad actors poses an increasingly serious threat to society. This paper addresses the critical question of how open foundation model developers should approach model safety in light of these challenges. Our analysis reveals that open-source foundation model companies often provide less restrictive acceptable use policies (AUPs) compared to their closed-source counterparts, likely due to the inherent difficulties in enforcing such policies once the models are released. To tackle this issue, we introduce PRISM, a design framework for open-source foundation model safety that emphasizes Private, Robust, Independent Safety measures, at Minimal marginal cost of compute. The PRISM framework proposes the use of modular functions that moderate prompts and outputs independently of the core language model, offering a more adaptable and resilient approach to safety compared to the brittle reinforcement learning methods currently used for value alignment. By focusing on identifying AUP violations and engaging the developer community in establishing consensus around safety design decisions, PRISM aims to create a safer open-source ecosystem that maximizes the potential of these powerful technologies while minimizing the risks to individuals and society as a whole.
Authors: Xu Cao, Bolin Lai, Wenqian Ye, Yunsheng Ma, Joerg Heintz, Jintai Chen, Jianguo Cao, James M. Rehg
Abstract: Recently, Multimodal Large Language Models (MLLMs) have shown great promise in language-guided perceptual tasks such as recognition, segmentation, and object detection. However, their effectiveness in addressing visual cognition problems that require high-level reasoning is not well-established. One such challenge is abstract visual reasoning (AVR) -- the cognitive ability to discern relationships among patterns in a set of images and extrapolate to predict subsequent patterns. This skill is crucial during the early neurodevelopmental stages of children. Inspired by the AVR tasks in Raven's Progressive Matrices (RPM) and Wechsler Intelligence Scale for Children (WISC), we propose a new dataset MaRs-VQA and a new benchmark VCog-Bench containing three datasets to evaluate the zero-shot AVR capability of MLLMs and compare their performance with existing human intelligent investigation. Our comparative experiments with different open-source and closed-source MLLMs on the VCog-Bench revealed a gap between MLLMs and human intelligence, highlighting the visual cognitive limitations of current MLLMs. We believe that the public release of VCog-Bench, consisting of MaRs-VQA, and the inference pipeline will drive progress toward the next generation of MLLMs with human-like visual cognition abilities.
Authors: Pietro Astolfi, Marlene Careil, Melissa Hall, Oscar Ma\~nas, Matthew Muckley, Jakob Verbeek, Adriana Romero Soriano, Michal Drozdzal
Abstract: Building world models that accurately and comprehensively represent the real world is the utmost aspiration for conditional image generative models as it would enable their use as world simulators. For these models to be successful world models, they should not only excel at image quality and prompt-image consistency but also ensure high representation diversity. However, current research in generative models mostly focuses on creative applications that are predominantly concerned with human preferences of image quality and aesthetics. We note that generative models have inference time mechanisms - or knobs - that allow the control of generation consistency, quality, and diversity. In this paper, we use state-of-the-art text-to-image and image-and-text-to-image models and their knobs to draw consistency-diversity-realism Pareto fronts that provide a holistic view on consistency-diversity-realism multi-objective. Our experiments suggest that realism and consistency can both be improved simultaneously; however there exists a clear tradeoff between realism/consistency and diversity. By looking at Pareto optimal points, we note that earlier models are better at representation diversity and worse in consistency/realism, and more recent models excel in consistency/realism while decreasing significantly the representation diversity. By computing Pareto fronts on a geodiverse dataset, we find that the first version of latent diffusion models tends to perform better than more recent models in all axes of evaluation, and there exist pronounced consistency-diversity-realism disparities between geographical regions. Overall, our analysis clearly shows that there is no best model and the choice of model should be determined by the downstream application. With this analysis, we invite the research community to consider Pareto fronts as an analytical tool to measure progress towards world models.
Authors: Susan Landau, James X. Dempsey, Ece Kamar, Steven M. Bellovin, Robert Pool
Abstract: In an October 2023 executive order (EO), President Biden issued a detailed but largely aspirational road map for the safe and responsible development and use of artificial intelligence (AI). The challenge for the January 24-25, 2024 workshop was to transform those aspirations regarding one specific but crucial issue -- the ability of individuals to challenge government decisions made about themselves -- into actionable guidance enabling agencies to develop, procure, and use genuinely contestable advanced automated decision-making systems. While the Administration has taken important steps since the October 2023 EO, the insights garnered from our workshop remain highly relevant, as the requirements for contestability of advanced decision-making systems are not yet fully defined or implemented. The workshop brought together technologists, members of government agencies and civil society organizations, litigators, and researchers in an intensive two-day meeting that examined the challenges that users, developers, and agencies faced in enabling contestability in light of advanced automated decision-making systems. To ensure a free and open flow of discussion, the meeting was held under a modified version of the Chatham House rule. Participants were free to use any information or details that they learned, but they may not attribute any remarks made at the meeting by the identity or the affiliation of the speaker. Thus, the workshop summary that follows anonymizes speakers and their affiliation. Where an identification of an agency, company, or organization is made, it is done from a public, identified resource and does not necessarily reflect statements made by participants at the workshop. This document is a report of that workshop, along with recommendations and explanatory material.
Authors: Emi Soroka, Rohan Sinha, Sanjay Lall
Abstract: Temporal logic rules are often used in control and robotics to provide structured, human-interpretable descriptions of high-dimensional trajectory data. These rules have numerous applications including safety validation using formal methods, constraining motion planning among autonomous agents, and classifying data. However, existing methods for learning temporal logic predicates from data provide no assurances about the correctness of the resulting predicate. We present a novel method to learn temporal logic predicates from data with finite-sample correctness guarantees. Our approach leverages expression optimization and conformal prediction to learn predicates that correctly describe future trajectories under mild assumptions with a user-defined confidence level. We provide experimental results showing the performance of our approach on a simulated trajectory dataset and perform ablation studies to understand how each component of our algorithm contributes to its performance.
Authors: Haohao Qu, Wenqi Fan, Zihuai Zhao, Qing Li
Abstract: There is a growing interest in utilizing large-scale language models (LLMs) to advance next-generation Recommender Systems (RecSys), driven by their outstanding language understanding and in-context learning capabilities. In this scenario, tokenizing (i.e., indexing) users and items becomes essential for ensuring a seamless alignment of LLMs with recommendations. While several studies have made progress in representing users and items through textual contents or latent representations, challenges remain in efficiently capturing high-order collaborative knowledge into discrete tokens that are compatible with LLMs. Additionally, the majority of existing tokenization approaches often face difficulties in generalizing effectively to new/unseen users or items that were not in the training corpus. To address these challenges, we propose a novel framework called TokenRec, which introduces not only an effective ID tokenization strategy but also an efficient retrieval paradigm for LLM-based recommendations. Specifically, our tokenization strategy, Masked Vector-Quantized (MQ) Tokenizer, involves quantizing the masked user/item representations learned from collaborative filtering into discrete tokens, thus achieving a smooth incorporation of high-order collaborative knowledge and a generalizable tokenization of users and items for LLM-based RecSys. Meanwhile, our generative retrieval paradigm is designed to efficiently recommend top-$K$ items for users to eliminate the need for the time-consuming auto-regressive decoding and beam search processes used by LLMs, thus significantly reducing inference time. Comprehensive experiments validate the effectiveness of the proposed methods, demonstrating that TokenRec outperforms competitive benchmarks, including both traditional recommender systems and emerging LLM-based recommender systems.
Authors: Zipeng Fu, Qingqing Zhao, Qi Wu, Gordon Wetzstein, Chelsea Finn
Abstract: One of the key arguments for building robots that have similar form factors to human beings is that we can leverage the massive human data for training. Yet, doing so has remained challenging in practice due to the complexities in humanoid perception and control, lingering physical gaps between humanoids and humans in morphologies and actuation, and lack of a data pipeline for humanoids to learn autonomous skills from egocentric vision. In this paper, we introduce a full-stack system for humanoids to learn motion and autonomous skills from human data. We first train a low-level policy in simulation via reinforcement learning using existing 40-hour human motion datasets. This policy transfers to the real world and allows humanoid robots to follow human body and hand motion in real time using only a RGB camera, i.e. shadowing. Through shadowing, human operators can teleoperate humanoids to collect whole-body data for learning different tasks in the real world. Using the data collected, we then perform supervised behavior cloning to train skill policies using egocentric vision, allowing humanoids to complete different tasks autonomously by imitating human skills. We demonstrate the system on our customized 33-DoF 180cm humanoid, autonomously completing tasks such as wearing a shoe to stand up and walk, unloading objects from warehouse racks, folding a sweatshirt, rearranging objects, typing, and greeting another robot with 60-100% success rates using up to 40 demonstrations. Project website: https://humanoid-ai.github.io/
Authors: Samuel S. Sohn, Danrui Li, Sen Zhang, Che-Jui Chang, Mubbasir Kapadia
Abstract: Digital storytelling, essential in entertainment, education, and marketing, faces challenges in production scalability and flexibility. The StoryAgent framework, introduced in this paper, utilizes Large Language Models and generative tools to automate and refine digital storytelling. Employing a top-down story drafting and bottom-up asset generation approach, StoryAgent tackles key issues such as manual intervention, interactive scene orchestration, and narrative consistency. This framework enables efficient production of interactive and consistent narratives across multiple modalities, democratizing content creation and enhancing engagement. Our results demonstrate the framework's capability to produce coherent digital stories without reference videos, marking a significant advancement in automated digital storytelling.
Authors: Jiahan Zhang, Qi Wei, Feng Liu, Lei Feng
Abstract: Fine-tuning vision-language models (VLMs) with abundant unlabeled data recently has attracted increasing attention. Existing methods that resort to the pseudolabeling strategy would suffer from heavily incorrect hard pseudolabels when VLMs exhibit low zero-shot performance in downstream tasks. To alleviate this issue, we propose a Candidate Pseudolabel Learning method, termed CPL, to fine-tune VLMs with suitable candidate pseudolabels of unlabeled data in downstream tasks. The core of our method lies in the generation strategy of candidate pseudolabels, which progressively generates refined candidate pseudolabels by both intra- and inter-instance label selection, based on a confidence score matrix for all unlabeled data. This strategy can result in better performance in true label inclusion and class-balanced instance selection. In this way, we can directly apply existing loss functions to learn with generated candidate psueudolabels. Extensive experiments on nine benchmark datasets with three learning paradigms demonstrate the effectiveness of our method. Our code can be found at https://github.com/vanillaer/CPL-ICML2024.
Authors: Zehua Kcriss Li, Meiying Melissa Chen, Yi Zhong, Pinxin Liu, Zhiyao Duan
Abstract: Expressive speech synthesis aims to generate speech that captures a wide range of para-linguistic features, including emotion and articulation, though current research primarily emphasizes emotional aspects over the nuanced articulatory features mastered by professional voice actors. Inspired by this, we explore expressive speech synthesis through the lens of articulatory phonetics. Specifically, we define a framework with three dimensions: Glottalization, Tenseness, and Resonance (GTR), to guide the synthesis at the voice production level. With this framework, we record a high-quality speech dataset named GTR-Voice, featuring 20 Chinese sentences articulated by a professional voice actor across 125 distinct GTR combinations. We verify the framework and GTR annotations through automatic classification and listening tests, and demonstrate precise controllability along the GTR dimensions on two fine-tuned expressive TTS models. We open-source the dataset and TTS models.
Authors: Ruize Wang, Hui Xu, Ying Cheng, Qi He, Xing Zhou, Rui Feng, Wei Xu, Lei Huang, Jie Jiang
Abstract: Advertising platforms have evolved in estimating Lifetime Value (LTV) to better align with advertisers' true performance metric. However, the sparsity of real-world LTV data presents a significant challenge to LTV predictive model(i.e., pLTV), severely limiting the their capabilities. Therefore, we propose to utilize external data, in addition to the internal data of advertising platform, to expand the size of purchase samples and enhance the LTV prediction model of the advertising platform. To tackle the issue of data distribution shift between internal and external platforms, we introduce an Adaptive Difference Siamese Network (ADSNet), which employs cross-domain transfer learning to prevent negative transfer. Specifically, ADSNet is designed to learn information that is beneficial to the target domain. We introduce a gain evaluation strategy to calculate information gain, aiding the model in learning helpful information for the target domain and providing the ability to reject noisy samples, thus avoiding negative transfer. Additionally, we also design a Domain Adaptation Module as a bridge to connect different domains, reduce the distribution distance between them, and enhance the consistency of representation space distribution. We conduct extensive offline experiments and online A/B tests on a real advertising platform. Our proposed ADSNet method outperforms other methods, improving GINI by 2$\%$. The ablation study highlights the importance of the gain evaluation strategy in negative gain sample rejection and improving model performance. Additionally, ADSNet significantly improves long-tail prediction. The online A/B tests confirm ADSNet's efficacy, increasing online LTV by 3.47$\%$ and GMV by 3.89$\%$.
Authors: Pengfei Gu, Yejia Zhang, Huimin Li, Hongxiao Wang, Yizhe Zhang, Chaoli Wang, Danny Z. Chen
Abstract: Masked Autoencoders (MAEs) have been shown to be effective in pre-training Vision Transformers (ViTs) for natural and medical image analysis problems. By reconstructing missing pixel/voxel information in visible patches, a ViT encoder can aggregate contextual information for downstream tasks. But, existing MAE pre-training methods, which were specifically developed with the ViT architecture, lack the ability to capture geometric shape and spatial information, which is critical for medical image segmentation tasks. In this paper, we propose a novel extension of known MAEs for self pre-training (i.e., models pre-trained on the same target dataset) for 3D medical image segmentation. (1) We propose a new topological loss to preserve geometric shape information by computing topological signatures of both the input and reconstructed volumes, learning geometric shape information. (2) We introduce a pre-text task that predicts the positions of the centers and eight corners of 3D crops, enabling the MAE to aggregate spatial information. (3) We extend the MAE pre-training strategy to a hybrid state-of-the-art (SOTA) medical image segmentation architecture and co-pretrain it alongside the ViT. (4) We develop a fine-tuned model for downstream segmentation tasks by complementing the pre-trained ViT encoder with our pre-trained SOTA model. Extensive experiments on five public 3D segmentation datasets show the effectiveness of our new approach.
Authors: Yaobin Ling, Xiaoqian Jiang, Yejin Kim
Abstract: In the era of big data, access to abundant data is crucial for driving research forward. However, such data is often inaccessible due to privacy concerns or high costs, particularly in healthcare domain. Generating synthetic (tabular) data can address this, but existing models typically require substantial amounts of data to train effectively, contradicting our objective to solve data scarcity. To address this challenge, we propose a novel framework to generate synthetic tabular data, powered by large language models (LLMs) that emulates the architecture of a Generative Adversarial Network (GAN). By incorporating data generation process as contextual information and utilizing LLM as the optimizer, our approach significantly enhance the quality of synthetic data generation in common scenarios with small sample sizes. Our experimental results on public and private datasets demonstrate that our model outperforms several state-of-art models regarding generating higher quality synthetic data for downstream tasks while keeping privacy of the real data.
Authors: Jifan Zhang, Lalit Jain, Yang Guo, Jiayi Chen, Kuan Lok Zhou, Siddharth Suresh, Andrew Wagenmaker, Scott Sievert, Timothy Rogers, Kevin Jamieson, Robert Mankoff, Robert Nowak
Abstract: We present a novel multimodal preference dataset for creative tasks, consisting of over 250 million human ratings on more than 2.2 million captions, collected through crowdsourcing rating data for The New Yorker's weekly cartoon caption contest over the past eight years. This unique dataset supports the development and evaluation of multimodal large language models and preference-based fine-tuning algorithms for humorous caption generation. We propose novel benchmarks for judging the quality of model-generated captions, utilizing both GPT4 and human judgments to establish ranking-based evaluation strategies. Our experimental results highlight the limitations of current fine-tuning methods, such as RLHF and DPO, when applied to creative tasks. Furthermore, we demonstrate that even state-of-the-art models like GPT4 and Claude currently underperform top human contestants in generating humorous captions. As we conclude this extensive data collection effort, we release the entire preference dataset to the research community, fostering further advancements in AI humor generation and evaluation.
Authors: Marco Bressan, Nicol\`o Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, Maximilian Thiessen
Abstract: Can a deep neural network be approximated by a small decision tree based on simple features? This question and its variants are behind the growing demand for machine learning models that are *interpretable* by humans. In this work we study such questions by introducing *interpretable approximations*, a notion that captures the idea of approximating a target concept $c$ by a small aggregation of concepts from some base class $\mathcal{H}$. In particular, we consider the approximation of a binary concept $c$ by decision trees based on a simple class $\mathcal{H}$ (e.g., of bounded VC dimension), and use the tree depth as a measure of complexity. Our primary contribution is the following remarkable trichotomy. For any given pair of $\mathcal{H}$ and $c$, exactly one of these cases holds: (i) $c$ cannot be approximated by $\mathcal{H}$ with arbitrary accuracy; (ii) $c$ can be approximated by $\mathcal{H}$ with arbitrary accuracy, but there exists no universal rate that bounds the complexity of the approximations as a function of the accuracy; or (iii) there exists a constant $\kappa$ that depends only on $\mathcal{H}$ and $c$ such that, for *any* data distribution and *any* desired accuracy level, $c$ can be approximated by $\mathcal{H}$ with a complexity not exceeding $\kappa$. This taxonomy stands in stark contrast to the landscape of supervised classification, which offers a complex array of distribution-free and universally learnable scenarios. We show that, in the case of interpretable approximations, even a slightly nontrivial a-priori guarantee on the complexity of approximations implies approximations with constant (distribution-free and accuracy-free) complexity. We extend our trichotomy to classes $\mathcal{H}$ of unbounded VC dimension and give characterizations of interpretability based on the algebra generated by $\mathcal{H}$.
Authors: Yiye Zou, Tianyu Li, Shufan Zou, Jingyu Wang, Laiping Zhang, Xiaogang Deng
Abstract: Recently, advancements in deep learning have enabled physics-informed neural networks (PINNs) to solve partial differential equations (PDEs). Numerical differentiation (ND) using the finite difference (FD) method is efficient in physics-constrained designs, even in parameterized settings, often employing body-fitted block-structured grids for complex flow cases. However, convolution operators in CNNs for finite differences are typically limited to single-block grids. To address this, we use graphs and graph networks (GNs) to learn flow representations across multi-block structured grids. We propose a graph convolution-based finite difference method (GC-FDM) to train GNs in a physics-constrained manner, enabling differentiable finite difference operations on graph unstructured outputs. Our goal is to solve parametric steady incompressible Navier-Stokes equations for flows around a backward-facing step, a circular cylinder, and double cylinders, using multi-block structured grids. Comparing our method to a CFD solver under various boundary conditions, we demonstrate improved training efficiency and accuracy, achieving a minimum relative error of $10^{-3}$ in velocity field prediction and a 20\% reduction in training cost compared to PINNs.
Authors: Pingchuan Ma, Rui Ding, Qiang Fu, Jiaru Zhang, Shuai Wang, Shi Han, Dongmei Zhang
Abstract: Differentiable causal discovery has made significant advancements in the learning of directed acyclic graphs. However, its application to real-world datasets remains restricted due to the ubiquity of latent confounders and the requirement to learn maximal ancestral graphs (MAGs). To date, existing differentiable MAG learning algorithms have been limited to small datasets and failed to scale to larger ones (e.g., with more than 50 variables). The key insight in this paper is that the causal skeleton, which is the undirected version of the causal graph, has potential for improving accuracy and reducing the search space of the optimization procedure, thereby enhancing the performance of differentiable causal discovery. Therefore, we seek to address a two-fold challenge to harness the potential of the causal skeleton for differentiable causal discovery in the presence of latent confounders: (1) scalable and accurate estimation of skeleton and (2) universal integration of skeleton estimation with differentiable causal discovery. To this end, we propose SPOT (Skeleton Posterior-guided OpTimization), a two-phase framework that harnesses skeleton posterior for differentiable causal discovery in the presence of latent confounders. On the contrary to a ``point-estimation'', SPOT seeks to estimate the posterior distribution of skeletons given the dataset. It first formulates the posterior inference as an instance of amortized inference problem and concretizes it with a supervised causal learning (SCL)-enabled solution to estimate the skeleton posterior. To incorporate the skeleton posterior with differentiable causal discovery, SPOT then features a skeleton posterior-guided stochastic optimization procedure to guide the optimization of MAGs. [abridged due to length limit]
Authors: Zhenggang Tang, Zhongzheng Ren, Xiaoming Zhao, Bowen Wen, Jonathan Tremblay, Stan Birchfield, Alexander Schwing
Abstract: We present a method for automatically modifying a NeRF representation based on a single observation of a non-rigid transformed version of the original scene. Our method defines the transformation as a 3D flow, specifically as a weighted linear blending of rigid transformations of 3D anchor points that are defined on the surface of the scene. In order to identify anchor points, we introduce a novel correspondence algorithm that first matches RGB-based pairs, then leverages multi-view information and 3D reprojection to robustly filter false positives in two steps. We also introduce a new dataset for exploring the problem of modifying a NeRF scene through a single observation. Our dataset ( https://github.com/nerfdeformer/nerfdeformer ) contains 113 synthetic scenes leveraging 47 3D assets. We show that our proposed method outperforms NeRF editing methods as well as diffusion-based methods, and we also explore different methods for filtering correspondences.
Authors: Adane Nega Tarekegn, Fazle Rabbi, Bj{\o}rnar Tessem
Abstract: The news landscape is continuously evolving, with an ever-increasing volume of information from around the world. Automated event detection within this vast data repository is essential for monitoring, identifying, and categorizing significant news occurrences across diverse platforms. This paper presents an event detection framework that leverages Large Language Models (LLMs) combined with clustering analysis to detect news events from the Global Database of Events, Language, and Tone (GDELT). The framework enhances event clustering through both pre-event detection tasks (keyword extraction and text embedding) and post-event detection tasks (event summarization and topic labeling). We also evaluate the impact of various textual embeddings on the quality of clustering outcomes, ensuring robust news categorization. Additionally, we introduce a novel Cluster Stability Assessment Index (CSAI) to assess the validity and robustness of clustering results. CSAI utilizes latent feature vectors to provide a new way of measuring clustering quality. Our experiments indicate that combining LLM embeddings with clustering algorithms yields the best results, demonstrating greater robustness in terms of CSAI scores. Moreover, post-event detection tasks generate meaningful insights, facilitating effective interpretation of event clustering results. Overall, our experimental results indicate that the proposed framework offers valuable insights and could enhance the accuracy and depth of news reporting.
Authors: Tong Wu, Zhiyong Chen, Meixia Tao, Bin Xia, Wenjun Zhang
Abstract: Degraded broadcast channels (DBC) are a typical multiuser communication scenario, Semantic communications over DBC still lack in-depth research. In this paper, we design a semantic communications approach based on multi-user semantic fusion for wireless image transmission over DBC. In the proposed method, the transmitter extracts semantic features for two users separately. It then effectively fuses these semantic features for broadcasting by leveraging semantic similarity. Unlike traditional allocation of time, power, or bandwidth, the semantic fusion scheme can dynamically control the weight of the semantic features of the two users to balance the performance between the two users. Considering the different channel state information (CSI) of both users over DBC, a DBC-Aware method is developed that embeds the CSI of both users into the joint source-channel coding encoder and fusion module to adapt to the channel. Experimental results show that the proposed system outperforms the traditional broadcasting schemes.
Authors: Yukai Xu, Jingfeng Zhang, Yujie Gu
Abstract: In the realm of healthcare where decentralized facilities are prevalent, machine learning faces two major challenges concerning the protection of data and models. The data-level challenge concerns the data privacy leakage when centralizing data with sensitive personal information. While the model-level challenge arises from the heterogeneity of local models, which need to be collaboratively trained while ensuring their confidentiality to address intellectual property concerns. To tackle these challenges, we propose a new framework termed Abstention-Aware Federated Voting (AAFV) that can collaboratively and confidentially train heterogeneous local models while simultaneously protecting the data privacy. This is achieved by integrating a novel abstention-aware voting mechanism and a differential privacy mechanism onto local models' predictions. In particular, the proposed abstention-aware voting mechanism exploits a threshold-based abstention method to select high-confidence votes from heterogeneous local models, which not only enhances the learning utility but also protects model confidentiality. Furthermore, we implement AAFV on two practical prediction tasks of diabetes and in-hospital patient mortality. The experiments demonstrate the effectiveness and confidentiality of AAFV in testing accuracy and privacy protection.
Authors: Xiao Yang, Gaolei Li, Jianhua Li
Abstract: Graph Neural Networks (GNNs) have significantly advanced various downstream graph-relevant tasks, encompassing recommender systems, molecular structure prediction, social media analysis, etc. Despite the boosts of GNN, recent research has empirically demonstrated its potential vulnerability to backdoor attacks, wherein adversaries employ triggers to poison input samples, inducing GNN to adversary-premeditated malicious outputs. This is typically due to the controlled training process, or the deployment of untrusted models, such as delegating model training to third-party service, leveraging external training sets, and employing pre-trained models from online sources. Although there's an ongoing increase in research on GNN backdoors, comprehensive investigation into this field is lacking. To bridge this gap, we propose the first survey dedicated to GNN backdoors. We begin by outlining the fundamental definition of GNN, followed by the detailed summarization and categorization of current GNN backdoor attacks and defenses based on their technical characteristics and application scenarios. Subsequently, the analysis of the applicability and use cases of GNN backdoors is undertaken. Finally, the exploration of potential research directions of GNN backdoors is presented. This survey aims to explore the principles of graph backdoors, provide insights to defenders, and promote future security research.
Authors: Alonso Silva
Abstract: Generative artificial intelligence (Generative AI), and in particular Large Language Models (LLMs) have gained significant popularity among researchers and industrial communities, paving the way for integrating LLMs in different domains, such as robotics, telecom, and healthcare. In this paper, we study the intersection of game theory and generative artificial intelligence, focusing on the capabilities of LLMs to find the Nash equilibrium in games with a mixed strategy Nash equilibrium and no pure strategy Nash equilibrium (that we denote mixed strategy Nash equilibrium games). The study reveals a significant enhancement in the performance of LLMs when they are equipped with the possibility to run code and are provided with a specific prompt to incentivize them to do so. However, our research also highlights the limitations of LLMs when the randomization strategy of the game is not easy to deduce. It is evident that while LLMs exhibit remarkable proficiency in well-known standard games, their performance dwindles when faced with slight modifications of the same games. This paper aims to contribute to the growing body of knowledge on the intersection of game theory and generative artificial intelligence while providing valuable insights into LLMs strengths and weaknesses. It also underscores the need for further research to overcome the limitations of LLMs, particularly in dealing with even slightly more complex scenarios, to harness their full potential.
Authors: Ruibo Fu, Shuchen Shi, Hongming Guo, Tao Wang, Chunyu Qiang, Zhengqi Wen, Jianhua Tao, Xin Qi, Yi Lu, Xiaopeng Wang, Zhiyong Wang, Yukun Liu, Xuefei Liu, Shuai Zhang, Guanjun Li
Abstract: Foley audio, critical for enhancing the immersive experience in multimedia content, faces significant challenges in the AI-generated content (AIGC) landscape. Despite advancements in AIGC technologies for text and image generation, the foley audio dubbing remains rudimentary due to difficulties in cross-modal scene matching and content correlation. Current text-to-audio technology, which relies on detailed and acoustically relevant textual descriptions, falls short in practical video dubbing applications. Existing datasets like AudioSet, AudioCaps, Clotho, Sound-of-Story, and WavCaps do not fully meet the requirements for real-world foley audio dubbing task. To address this, we introduce the Multi-modal Image and Narrative Text Dubbing Dataset (MINT), designed to enhance mainstream dubbing tasks such as literary story audiobooks dubbing, image/silent video dubbing. Besides, to address the limitations of existing TTA technology in understanding and planning complex prompts, a Foley Audio Content Planning, Generation, and Alignment (CPGA) framework is proposed, which includes a content planning module leveraging large language models for complex multi-modal prompts comprehension. Additionally, the training process is optimized using Proximal Policy Optimization based reinforcement learning, significantly improving the alignment and auditory realism of generated foley audio. Experimental results demonstrate that our approach significantly advances the field of foley audio dubbing, providing robust solutions for the challenges of multi-modal dubbing. Even when utilizing the relatively lightweight GPT-2 model, our framework outperforms open-source multimodal large models such as LLaVA, DeepSeek-VL, and Moondream2. The dataset is available at https://github.com/borisfrb/MINT .
Authors: Tong Zhang, Yingdong Hu, Jiacheng You, Yang Gao
Abstract: Given the high cost of collecting robotic data in the real world, sample efficiency is a consistently compelling pursuit in robotics. In this paper, we introduce SGRv2, an imitation learning framework that enhances sample efficiency through improved visual and action representations. Central to the design of SGRv2 is the incorporation of a critical inductive bias-action locality, which posits that robot's actions are predominantly influenced by the target object and its interactions with the local environment. Extensive experiments in both simulated and real-world settings demonstrate that action locality is essential for boosting sample efficiency. SGRv2 excels in RLBench tasks with keyframe control using merely 5 demonstrations and surpasses the RVT baseline in 23 of 26 tasks. Furthermore, when evaluated on ManiSkill2 and MimicGen using dense control, SGRv2's success rate is 2.54 times that of SGR. In real-world environments, with only eight demonstrations, SGRv2 can perform a variety of tasks at a markedly higher success rate compared to baseline models. Project website: http://sgrv2-robot.github.io
Authors: Zhouhong Gu, Haoning Ye, Zeyang Zhou, Hongwei Feng, Yanghua Xiao
Abstract: Given the substantial volumes of structured data held by many companies, enabling Large Language Models (LLMs) to directly understand structured text in non-structured forms could significantly enhance their capabilities across various business scenarios. To this end, we propose evaluation data generation method for assessing LLM's ability in understanding the structure-rich text, which generates structured data of controllable complexity based on manually crafted question templates and generation rules. Building on this generation method, we introduce StructBench, a benchmark comprising 6,032 questions across 8 different structured languages and 29 specific tasks. Furthermore, considering human proficiency in rule-based tasks, we also present StructBench-Hard, which includes 3,016 questions designed to further examine the gap between LLMs and human performance. Results indicate that the best-performing LLM currently achieve an accuracy of 65.0\% on StructBench-Hard, while human accuracy reaches up to 95.7\%. Moreover, while fine-tuning using StructBench can enhance existing LLMs' understanding of all structured languages, it does not necessarily improve performance across all task types. The benchmark and generation codes are open sourced in https://github.com/MikeGu721/StructBench
Authors: Anil Bhujel, Yibin Wang, Yuzhen Lu, Daniel Morris, Mukesh Dangol
Abstract: Technology-driven precision livestock farming (PLF) empowers practitioners to monitor and analyze animal growth and health conditions for improved productivity and welfare. Computer vision (CV) is indispensable in PLF by using cameras and computer algorithms to supplement or supersede manual efforts for livestock data acquisition. Data availability is crucial for developing innovative monitoring and analysis systems through artificial intelligence-based techniques. However, data curation processes are tedious, time-consuming, and resource intensive. This study presents the first systematic survey of publicly available livestock CV datasets (https://github.com/Anil-Bhujel/Public-Computer-Vision-Dataset-A-Systematic-Survey). Among 58 public datasets identified and analyzed, encompassing different species of livestock, almost half of them are for cattle, followed by swine, poultry, and other animals. Individual animal detection and color imaging are the dominant application and imaging modality for livestock. The characteristics and baseline applications of the datasets are discussed, emphasizing the implications for animal welfare advocates. Challenges and opportunities are also discussed to inspire further efforts in developing livestock CV datasets. This study highlights that the limited quantity of high-quality annotated datasets collected from diverse environments, animals, and applications, the absence of contextual metadata, are a real bottleneck in PLF.
URLs: https://github.com/Anil-Bhujel/Public-Computer-Vision-Dataset-A-Systematic-Survey).
Authors: Rui Ye, Jingyi Chai, Xiangrui Liu, Yaodong Yang, Yanfeng Wang, Siheng Chen
Abstract: Federated learning (FL) enables multiple parties to collaboratively fine-tune an large language model (LLM) without the need of direct data sharing. Ideally, by training on decentralized data that is aligned with human preferences and safety principles, federated instruction tuning can result in an LLM that could behave in a helpful and safe manner. In this paper, we for the first time reveal the vulnerability of safety alignment in FedIT by proposing a simple, stealthy, yet effective safety attack method. Specifically, the malicious clients could automatically generate attack data without involving manual efforts and attack the FedIT system by training their local LLMs on such attack data. Unfortunately, this proposed safety attack not only can compromise the safety alignment of LLM trained via FedIT, but also can not be effectively defended against by many existing FL defense methods. Targeting this, we further propose a post-hoc defense method, which could rely on a fully automated pipeline: generation of defense data and further fine-tuning of the LLM. Extensive experiments show that our safety attack method can significantly compromise the LLM's safety alignment (e.g., reduce safety rate by 70\%), which can not be effectively defended by existing defense methods (at most 4\% absolute improvement), while our safety defense method can significantly enhance the attacked LLM's safety alignment (at most 69\% absolute improvement).
Authors: Onyekachukwu R. Okonji, Kamol Yunusov, Bonnie Gordon
Abstract: Generative AI is rapidly transforming medical imaging and text analysis, offering immense potential for enhanced diagnosis and personalized care. However, this transformative technology raises crucial ethical, societal, and legal questions. This paper delves into these complexities, examining issues of accuracy, informed consent, data privacy, and algorithmic limitations in the context of generative AI's application to medical imaging and text. We explore the legal landscape surrounding liability and accountability, emphasizing the need for robust regulatory frameworks. Furthermore, we dissect the algorithmic challenges, including data biases, model limitations, and workflow integration. By critically analyzing these challenges and proposing responsible solutions, we aim to foster a roadmap for ethical and responsible implementation of generative AI in healthcare, ensuring its transformative potential serves humanity with utmost care and precision.
Authors: Aloysius Ochasi, Abdoul Jalil Djiberou Mahamadou, Russ B. Altman
Abstract: There is an ongoing debate on balancing the benefits and risks of artificial intelligence (AI) as AI is becoming critical to improving healthcare delivery and patient outcomes. Such improvements are essential in resource-constrained settings where millions lack access to adequate healthcare services, such as in Africa. AI in such a context can potentially improve the effectiveness, efficiency, and accessibility of healthcare services. Nevertheless, the development and use of AI-driven healthcare systems raise numerous ethical, legal, and socio-economic issues. Justice is a major concern in AI that has implications for amplifying social inequities. This paper discusses these implications and related justice concepts such as solidarity, Common Good, sustainability, AI bias, and fairness. For Africa to effectively benefit from AI, these principles should align with the local context while balancing the risks. Compared to mainstream ethical debates on justice, this perspective offers context-specific considerations for equitable healthcare AI development in Africa.
Authors: David Brandfonbrener, Hanlin Zhang, Andreas Kirsch, Jonathan Richard Schwarz, Sham Kakade
Abstract: Selecting high-quality data for pre-training is crucial in shaping the downstream task performance of language models. A major challenge lies in identifying this optimal subset, a problem generally considered intractable, thus necessitating scalable and effective heuristics. In this work, we propose a data selection method, CoLoR-Filter (Conditional Loss Reduction Filtering), which leverages an empirical Bayes-inspired approach to derive a simple and computationally efficient selection criterion based on the relative loss values of two auxiliary models. In addition to the modeling rationale, we evaluate CoLoR-Filter empirically on two language modeling tasks: (1) selecting data from C4 for domain adaptation to evaluation on Books and (2) selecting data from C4 for a suite of downstream multiple-choice question answering tasks. We demonstrate favorable scaling both as we subselect more aggressively and using small auxiliary models to select data for large target models. As one headline result, CoLoR-Filter data selected using a pair of 150m parameter auxiliary models can train a 1.2b parameter target model to match a 1.2b parameter model trained on 25b randomly selected tokens with 25x less data for Books and 11x less data for the downstream tasks. Code: https://github.com/davidbrandfonbrener/color-filter-olmo Filtered data: https://huggingface.co/datasets/davidbrandfonbrener/color-filtered-c4
URLs: https://github.com/davidbrandfonbrener/color-filter-olmo, https://huggingface.co/datasets/davidbrandfonbrener/color-filtered-c4
Authors: Shuang Wu, Arash A. Amini
Abstract: We consider an online decision-making problem with a reward function defined over graph-structured data. We formally formulate the problem as an instance of graph action bandit. We then propose \texttt{GNN-TS}, a Graph Neural Network (GNN) powered Thompson Sampling (TS) algorithm which employs a GNN approximator for estimating the mean reward function and the graph neural tangent features for uncertainty estimation. We prove that, under certain boundness assumptions on the reward function, GNN-TS achieves a state-of-the-art regret bound which is (1) sub-linear of order $\tilde{\mathcal{O}}((\tilde{d} T)^{1/2})$ in the number of interaction rounds, $T$, and a notion of effective dimension $\tilde{d}$, and (2) independent of the number of graph nodes. Empirical results validate that our proposed \texttt{GNN-TS} exhibits competitive performance and scales well on graph action bandit problems.
Authors: Taqwa Alhadidi, Ahmed Jaber, Shadi Jaradat, Huthaifa I Ashqar, Mohammed Elhenawy
Abstract: Object detection is a critical component of transportation systems, particularly for applications such as autonomous driving, traffic monitoring, and infrastructure maintenance. Traditional object detection methods often struggle with limited data and variability in object appearance. The Oriented Window Learning Vision Transformer (OWL-ViT) offers a novel approach by adapting window orientations to the geometry and existence of objects, making it highly suitable for detecting diverse roadway assets. This study leverages OWL-ViT within a one-shot learning framework to recognize transportation infrastructure components, such as traffic signs, poles, pavement, and cracks. This study presents a novel method for roadway asset detection using OWL-ViT. We conducted a series of experiments to evaluate the performance of the model in terms of detection consistency, semantic flexibility, visual context adaptability, resolution robustness, and impact of non-max suppression. The results demonstrate the high efficiency and reliability of the OWL-ViT across various scenarios, underscoring its potential to enhance the safety and efficiency of intelligent transportation systems.
Authors: Grzegorz Dudek
Abstract: In this study, we delve into the realm of meta-learning to combine point base forecasts for probabilistic short-term electricity demand forecasting. Our approach encompasses the utilization of quantile linear regression, quantile regression forest, and post-processing techniques involving residual simulation to generate quantile forecasts. Furthermore, we introduce both global and local variants of meta-learning. In the local-learning mode, the meta-model is trained using patterns most similar to the query pattern.Through extensive experimental studies across 35 forecasting scenarios and employing 16 base forecasting models, our findings underscored the superiority of quantile regression forest over its competitors
Authors: Wentao Yuan, Jiafei Duan, Valts Blukis, Wilbert Pumacay, Ranjay Krishna, Adithyavairavan Murali, Arsalan Mousavian, Dieter Fox
Abstract: From rearranging objects on a table to putting groceries into shelves, robots must plan precise action points to perform tasks accurately and reliably. In spite of the recent adoption of vision language models (VLMs) to control robot behavior, VLMs struggle to precisely articulate robot actions using language. We introduce an automatic synthetic data generation pipeline that instruction-tunes VLMs to robotic domains and needs. Using the pipeline, we train RoboPoint, a VLM that predicts image keypoint affordances given language instructions. Compared to alternative approaches, our method requires no real-world data collection or human demonstration, making it much more scalable to diverse environments and viewpoints. In addition, RoboPoint is a general model that enables several downstream applications such as robot navigation, manipulation, and augmented reality (AR) assistance. Our experiments demonstrate that RoboPoint outperforms state-of-the-art VLMs (GPT-4o) and visual prompting techniques (PIVOT) by 21.8% in the accuracy of predicting spatial affordance and by 30.5% in the success rate of downstream tasks. Project website: https://robo-point.github.io.
Authors: Bharat Singh, Viveka Kulharia, Luyu Yang, Avinash Ravichandran, Ambrish Tyagi, Ashish Shrivastava
Abstract: Multimodal synthetic data generation is crucial in domains such as autonomous driving, robotics, augmented/virtual reality, and retail. We propose a novel approach, GenMM, for jointly editing RGB videos and LiDAR scans by inserting temporally and geometrically consistent 3D objects. Our method uses a reference image and 3D bounding boxes to seamlessly insert and blend new objects into target videos. We inpaint the 2D Regions of Interest (consistent with 3D boxes) using a diffusion-based video inpainting model. We then compute semantic boundaries of the object and estimate it's surface depth using state-of-the-art semantic segmentation and monocular depth estimation techniques. Subsequently, we employ a geometry-based optimization algorithm to recover the 3D shape of the object's surface, ensuring it fits precisely within the 3D bounding box. Finally, LiDAR rays intersecting with the new object surface are updated to reflect consistent depths with its geometry. Our experiments demonstrate the effectiveness of GenMM in inserting various 3D objects across video and LiDAR modalities.
Authors: Wasif Khan, Seowung Leem, Kyle B. See, Joshua K. Wong, Shaoting Zhang, Ruogu Fang
Abstract: Foundation models (FMs) are large-scale deep-learning models trained on extensive datasets using self-supervised techniques. These models serve as a base for various downstream tasks, including healthcare. FMs have been adopted with great success across various domains within healthcare, including natural language processing (NLP), computer vision, graph learning, biology, and omics. Existing healthcare-based surveys have not yet included all of these domains. Therefore, this survey provides a comprehensive overview of FMs in healthcare. We focus on the history, learning strategies, flagship models, applications, and challenges of FMs. We explore how FMs such as the BERT and GPT families are reshaping various healthcare domains, including clinical large language models, medical image analysis, and omics data. Furthermore, we provide a detailed taxonomy of healthcare applications facilitated by FMs, such as clinical NLP, medical computer vision, graph learning, and other biology-related tasks. Despite the promising opportunities FMs provide, they also have several associated challenges, which are explained in detail. We also outline potential future directions to provide researchers and practitioners with insights into the potential and limitations of FMs in healthcare to advance their deployment and mitigate associated risks.
Authors: Pedro Hack
Abstract: The study of intelligent systems explains behaviour in terms of economic rationality. This results in an optimization principle involving a function or utility, which states that the system will evolve until the configuration of maximum utility is achieved. Recently, this theory has incorporated constraints, i.e., the optimum is achieved when the utility is maximized while respecting some information-processing constraints. This is reminiscent of thermodynamic systems. As such, the study of intelligent systems has benefited from the tools of thermodynamics. The first aim of this thesis is to clarify the applicability of these results in the study of intelligent systems. We can think of the local transition steps in thermodynamic or intelligent systems as being driven by uncertainty. In fact, the transitions in both systems can be described in terms of majorization. Hence, real-valued uncertainty measures like Shannon entropy are simply a proxy for their more involved behaviour. More in general, real-valued functions are fundamental to study optimization and complexity in the order-theoretic approach to several topics, including economics, thermodynamics, and quantum mechanics. The second aim of this thesis is to improve on this classification. The basic similarity between thermodynamic and intelligent systems is based on an uncertainty notion expressed by a preorder. We can also think of the transitions in the steps of a computational process as a decision-making procedure. In fact, by adding some requirements on the considered order structures, we can build an abstract model of uncertainty reduction that allows to incorporate computability, that is, to distinguish the objects that can be constructed by following a finite set of instructions from those that cannot. The third aim of this thesis is to clarify the requirements on the order structure that allow such a framework.
Authors: Pooneh Mousavi, Jarod Duret, Salah Zaiem, Luca Della Libera, Artem Ploujnikov, Cem Subakan, Mirco Ravanelli
Abstract: Discrete audio tokens have recently gained attention for their potential to bridge the gap between audio and language processing. Ideal audio tokens must preserve content, paralinguistic elements, speaker identity, and many other audio details. Current audio tokenization methods fall into two categories: Semantic tokens, acquired through quantization of Self-Supervised Learning (SSL) models, and Neural compression-based tokens (codecs). Although previous studies have benchmarked codec models to identify optimal configurations, the ideal setup for quantizing pretrained SSL models remains unclear. This paper explores the optimal configuration of semantic tokens across discriminative and generative tasks. We propose a scalable solution to train a universal vocoder across multiple SSL layers. Furthermore, an attention mechanism is employed to identify task-specific influential layers, enhancing the adaptability and performance of semantic tokens in diverse audio applications.
Authors: Nishargo Nigar
Abstract: The process of identifying human emotion and affective states from speech is known as speech emotion recognition (SER). This is based on the observation that tone and pitch in the voice frequently convey underlying emotion. Speech recognition includes the ability to recognize emotions, which is becoming increasingly popular and in high demand. With the help of appropriate factors (such modalities, emotions, intensities, repetitions, etc.) found in the data, my research seeks to use the Convolutional Neural Network (CNN) to distinguish emotions from audio recordings and label them in accordance with the range of different emotions. I have developed a machine learning model to identify emotions from supplied audio files with the aid of machine learning methods. The evaluation is mostly focused on precision, recall, and F1 score, which are common machine learning metrics. To properly set up and train the machine learning framework, the main objective is to investigate the influence and cross-relation of all input and output parameters. To improve the ability to recognize intentions, a key condition for communication, I have evaluated emotions using my specialized machine learning algorithm via voice that would address the emotional state from voice with the help of digital healthcare, bridging the gap between human and artificial intelligence (AI).
Authors: Mark Ibrahim, David Klindt, Randall Balestriero
Abstract: Deep Learning is often depicted as a trio of data-architecture-loss. Yet, recent Self Supervised Learning (SSL) solutions have introduced numerous additional design choices, e.g., a projector network, positive views, or teacher-student networks. These additions pose two challenges. First, they limit the impact of theoretical studies that often fail to incorporate all those intertwined designs. Second, they slow-down the deployment of SSL methods to new domains as numerous hyper-parameters need to be carefully tuned. In this study, we bring forward the surprising observation that--at least for pretraining datasets of up to a few hundred thousands samples--the additional designs introduced by SSL do not contribute to the quality of the learned representations. That finding not only provides legitimacy to existing theoretical studies, but also simplifies the practitioner's path to SSL deployment in numerous small and medium scale settings. Our finding answers a long-lasting question: the often-experienced sensitivity to training settings and hyper-parameters encountered in SSL come from their design, rather than the absence of supervised guidance.
Authors: Filip Trhlik, Pontus Stenetorp
Abstract: Large language models (LLMs) are increasingly being utilised across a range of tasks and domains, with a burgeoning interest in their application within the field of journalism. This trend raises concerns due to our limited understanding of LLM behaviour in this domain, especially with respect to political bias. Existing studies predominantly focus on LLMs undertaking political questionnaires, which offers only limited insights into their biases and operational nuances. To address this gap, our study establishes a new curated dataset that contains 2,100 human-written articles and utilises their descriptions to generate 56,700 synthetic articles using nine LLMs. This enables us to analyse shifts in properties between human-authored and machine-generated articles, with this study focusing on political bias, detecting it using both supervised models and LLMs. Our findings reveal significant disparities between base and instruction-tuned LLMs, with instruction-tuned models exhibiting consistent political bias. Furthermore, we are able to study how LLMs behave as classifiers, observing their display of political bias even in this role. Overall, for the first time within the journalistic domain, this study outlines a framework and provides a structured dataset for quantifiable experiments, serving as a foundation for further research into LLM political bias and its implications.
Authors: Ifigeneia Apostolopoulou, Benjamin Eysenbach, Frank Nielsen, Artur Dubrawski
Abstract: While powerful probabilistic models such as Gaussian Processes naturally have this property, deep neural networks often lack it. In this paper, we introduce Distance Aware Bottleneck (DAB), i.e., a new method for enriching deep neural networks with this property. Building on prior information bottleneck approaches, our method learns a codebook that stores a compressed representation of all inputs seen during training. The distance of a new example from this codebook can serve as an uncertainty estimate for the example. The resulting model is simple to train and provides deterministic uncertainty estimates by a single forward pass. Finally, our method achieves better out-of-distribution (OOD) detection and misclassification prediction than prior methods, including expensive ensemble methods, deep kernel Gaussian Processes, and approaches based on the standard information bottleneck.
Authors: Yurun Song, Junchen Zhao, Ian G. Harris, Sangeetha Abdu Jyothi
Abstract: This study introduces an approach to optimize Parameter Efficient Fine Tuning (PEFT) for Pretrained Language Models (PLMs) by implementing a Shared Low Rank Adaptation (ShareLoRA). By strategically deploying ShareLoRA across different layers and adapting it for the Query, Key, and Value components of self-attention layers, we achieve a substantial reduction in the number of training parameters and memory usage. Importantly, ShareLoRA not only maintains model performance but also exhibits robustness in both classification and generation tasks across a variety of models, including RoBERTa, GPT-2, LLaMA and LLaMA2. It demonstrates superior transfer learning capabilities compared to standard LoRA applications and mitigates overfitting by sharing weights across layers. Our findings affirm that ShareLoRA effectively boosts parameter efficiency while ensuring scalable and high-quality performance across different language model architectures.
Authors: Hamed Karimi, Reza Samavi
Abstract: In this paper, we propose Evidential Conformal Prediction (ECP) method for image classifiers to generate the conformal prediction sets. Our method is designed based on a non-conformity score function that has its roots in Evidential Deep Learning (EDL) as a method of quantifying model (epistemic) uncertainty in DNN classifiers. We use evidence that are derived from the logit values of target labels to compute the components of our non-conformity score function: the heuristic notion of uncertainty in CP, uncertainty surprisal, and expected utility. Our extensive experimental evaluation demonstrates that ECP outperforms three state-of-the-art methods for generating CP sets, in terms of their set sizes and adaptivity while maintaining the coverage of true labels.
Authors: Gabe Guo, Tristan Saidi, Maxwell Terban, Simon JL Billinge, Hod Lipson
Abstract: A major challenge in materials science is the determination of the structure of nanometer sized objects. Here we present a novel approach that uses a generative machine learning model based on a Diffusion model that is trained on 45,229 known structures. The model factors both the measured diffraction pattern as well as relevant statistical priors on the unit cell of atomic cluster structures. Conditioned only on the chemical formula and the information-scarce finite-size broadened powder diffraction pattern, we find that our model, PXRDnet, can successfully solve simulated nanocrystals as small as 10 angstroms across 200 materials of varying symmetry and complexity, including structures from all seven crystal systems. We show that our model can determine structural solutions with up to $81.5\%$ accuracy, as measured by structural correlation. Furthermore, PXRDnet is capable of solving structures from noisy diffraction patterns gathered in real-world experiments. We suggest that data driven approaches, bootstrapped from theoretical simulation, will ultimately provide a path towards determining the structure of previously unsolved nano-materials.
Authors: Aihua Pei (Waseda University), Zehua Yang (Waseda University), Shunan Zhu (Waseda University), Ruoxi Cheng (Southeast University), Ju Jia (Southeast University), Lina Wang (Wuhan University)
Abstract: Existing frameworks for assessing robustness of large language models (LLMs) overly depend on specific benchmarks, increasing costs and failing to evaluate performance of LLMs in professional domains due to dataset limitations. This paper proposes a framework that systematically evaluates the robustness of LLMs under adversarial attack scenarios by leveraging knowledge graphs (KGs). Our framework generates original prompts from the triplets of knowledge graphs and creates adversarial prompts by poisoning, assessing the robustness of LLMs through the results of these adversarial attacks. We systematically evaluate the effectiveness of this framework and its modules. Experiments show that adversarial robustness of the ChatGPT family ranks as GPT-4-turbo > GPT-4o > GPT-3.5-turbo, and the robustness of large language models is influenced by the professional domains in which they operate.
Authors: Marcos Piau, Roberto Lotufo, Rodrigo Nogueira
Abstract: Despite advancements in Natural Language Processing (NLP) and the growing availability of pretrained models, the English language remains the primary focus of model development. Continued pretraining on language-specific corpora provides a practical solution for adapting models to other languages. However, the impact of different pretraining settings on downstream tasks remains underexplored. This work introduces $\texttt{ptt5-v2}$, investigating the continued pretraining of T5 models for Portuguese. We first develop a baseline set of settings and pretrain models with sizes up to 3B parameters. Finetuning on three Portuguese downstream tasks (assin2 STS, assin2 RTE, and TweetSentBR) yields SOTA results on the latter two. We then explore the effects of different pretraining configurations, including quality filters, optimization strategies, and multi-epoch pretraining. Perhaps surprisingly, their impact remains subtle compared to our baseline. We release $\texttt{ptt5-v2}$ pretrained checkpoints and the finetuned MonoT5 rerankers on HuggingFace at https://huggingface.co/collections/unicamp-dl/ptt5-v2-666538a650188ba00aa8d2d0 and https://huggingface.co/collections/unicamp-dl/monoptt5-66653981877df3ea727f720d.
URLs: https://huggingface.co/collections/unicamp-dl/ptt5-v2-666538a650188ba00aa8d2d0, https://huggingface.co/collections/unicamp-dl/monoptt5-66653981877df3ea727f720d.
Authors: Oluwaseun T. Ajayi, Yu Cheng
Abstract: With the prevailing efforts to combat the coronavirus disease 2019 (COVID-19) pandemic, there are still uncertainties that are yet to be discovered about its spread, future impact, and resurgence. In this paper, we present a three-stage data-driven approach to distill the hidden information about COVID-19. The first stage employs a Bayesian network structure learning method to identify the causal relationships among COVID-19 symptoms and their intrinsic demographic variables. As a second stage, the output from the Bayesian network structure learning, serves as a useful guide to train an unsupervised machine learning (ML) algorithm that uncovers the similarities in patients' symptoms through clustering. The final stage then leverages the labels obtained from clustering to train a demographic symptom identification (DSID) model which predicts a patient's symptom class and the corresponding demographic probability distribution. We applied our method on the COVID-19 dataset obtained from the Centers for Disease Control and Prevention (CDC) in the United States. Results from the experiments show a testing accuracy of 99.99\%, as against the 41.15\% accuracy of a heuristic ML method. This strongly reveals the viability of our Bayesian network and ML approach in understanding the relationship between the virus symptoms, and providing insights on patients' stratification towards reducing the severity of the virus.
Authors: Yoonna Jang, Suhyune Son, Jeongwoo Lee, Junyoung Son, Yuna Hur, Jungwoo Lim, Hyeonseok Moon, Kisu Yang, Heuiseok Lim
Abstract: Despite the striking advances in recent language generation performance, model-generated responses have suffered from the chronic problem of hallucinations that are either untrue or unfaithful to a given source. Especially in the task of knowledge grounded conversation, the models are required to generate informative responses, but hallucinated utterances lead to miscommunication. In particular, entity-level hallucination that causes critical misinformation and undesirable conversation is one of the major concerns. To address this issue, we propose a post-hoc refinement method called REM. It aims to enhance the quality and faithfulness of hallucinated utterances by refining them based on the source knowledge. If the generated utterance has a low source-faithfulness score with the given knowledge, REM mines the key entities in the knowledge and implicitly uses them for refining the utterances. We verify that our method reduces entity hallucination in the utterance. Also, we show the adaptability and efficacy of REM with extensive experiments and generative results. Our code is available at https://github.com/YOONNAJANG/REM.
Authors: Meiyun Wang, Kiyoshi Izumi, Hiroki Sakaji
Abstract: Recently, Large Language Models (LLMs) have attracted significant attention for their exceptional performance across a broad range of tasks, particularly in text analysis. However, the finance sector presents a distinct challenge due to its dependence on time-series data for complex forecasting tasks. In this study, we introduce a novel framework called LLMFactor, which employs Sequential Knowledge-Guided Prompting (SKGP) to identify factors that influence stock movements using LLMs. Unlike previous methods that relied on keyphrases or sentiment analysis, this approach focuses on extracting factors more directly related to stock market dynamics, providing clear explanations for complex temporal changes. Our framework directs the LLMs to create background knowledge through a fill-in-the-blank strategy and then discerns potential factors affecting stock prices from related news. Guided by background knowledge and identified factors, we leverage historical stock prices in textual format to predict stock movement. An extensive evaluation of the LLMFactor framework across four benchmark datasets from both the U.S. and Chinese stock markets demonstrates its superiority over existing state-of-the-art methods and its effectiveness in financial time-series forecasting.
Authors: Jeongheon Oh, Kibok Lee
Abstract: Supervised contrastive representation learning has been shown to be effective in various transfer learning scenarios. However, while asymmetric non-contrastive learning (ANCL) often outperforms its contrastive learning counterpart in self-supervised representation learning, the extension of ANCL to supervised scenarios is less explored. To bridge the gap, we study ANCL for supervised representation learning, coined SupSiam and SupBYOL, leveraging labels in ANCL to achieve better representations. The proposed supervised ANCL framework improves representation learning while avoiding collapse. Our analysis reveals that providing supervision to ANCL reduces intra-class variance, and the contribution of supervision should be adjusted to achieve the best performance. Experiments demonstrate the superiority of supervised ANCL across various datasets and tasks. The code is available at: https://github.com/JH-Oh-23/Sup-ANCL.
Authors: Longhao Chen, Yina Zhao, Qiangjun Xie, Qinghua Sheng
Abstract: This article optimizes the inference performance of the Qwen-1.8B model by performing Int8 quantization, vectorizing some operators in llama.cpp, and modifying the compilation script to improve the compiler optimization level. On the Yitian 710 experimental platform, the prefill performance is increased by 1.6 times, the decoding performance is increased by 24 times, the memory usage is reduced to 1/5 of the original, and the accuracy loss is almost negligible.
Authors: Dongping Chen, Yue Huang, Siyuan Wu, Jingyu Tang, Liuyi Chen, Yilin Bai, Zhigang He, Chenlong Wang, Huichi Zhou, Yiqiang Li, Tianshuo Zhou, Yue Yu, Chujie Gao, Qihui Zhang, Yi Gui, Zhen Li, Yao Wan, Pan Zhou, Jianfeng Gao, Lichao Sun
Abstract: Recently, Multimodal Large Language Models (MLLMs) have been used as agents to control keyboard and mouse inputs by directly perceiving the Graphical User Interface (GUI) and generating corresponding code. However, current agents primarily exhibit excellent understanding capabilities in static environments and are predominantly applied in relatively simple domains, such as Web or mobile interfaces. We argue that a robust GUI agent should be capable of perceiving temporal information on the GUI, including dynamic Web content and multi-step tasks. Additionally, it should possess a comprehensive understanding of various GUI scenarios, including desktop software and multi-window interactions. To this end, this paper introduces a new dataset, termed GUI-World, which features meticulously crafted Human-MLLM annotations, extensively covering six GUI scenarios and eight types of GUI-oriented questions in three formats. We evaluate the capabilities of current state-of-the-art MLLMs, including ImageLLMs and VideoLLMs, in understanding various types of GUI content, especially dynamic and sequential content. Our findings reveal that ImageLLMs struggle with dynamic GUI content without manually annotated keyframes or operation history. On the other hand, VideoLLMs fall short in all GUI-oriented tasks given the sparse GUI video dataset. Based on GUI-World, we take the initial step of leveraging a fine-tuned VideoLLM as a GUI agent, demonstrating an improved understanding of various GUI tasks. However, due to the limitations in the performance of base LLMs, we conclude that using VideoLLMs as GUI agents remains a significant challenge. We believe our work provides valuable insights for future research in dynamic GUI content understanding. The code and dataset are publicly available at our project homepage: https://gui-world.github.io/.
Authors: Weiheng Tang, Jingyi Li, Lin Chen, Xu Chen
Abstract: Edge computing has recently emerged as a promising paradigm to boost the performance of distributed learning by leveraging the distributed resources at edge nodes. Architecturally, the introduction of edge nodes adds an additional intermediate layer between the master and workers in the original distributed learning systems, potentially leading to more severe straggler effect. Recently, coding theory-based approaches have been proposed for stragglers mitigation in distributed learning, but the majority focus on the conventional workers-master architecture. In this paper, along a different line, we investigate the problem of mitigating the straggler effect in hierarchical distributed learning systems with an additional layer composed of edge nodes. Technically, we first derive the fundamental trade-off between the computational loads of workers and the stragglers tolerance. Then, we propose a hierarchical gradient coding framework, which provides better stragglers mitigation, to achieve the derived computational trade-off. To further improve the performance of our framework in heterogeneous scenarios, we formulate an optimization problem with the objective of minimizing the expected execution time for each iteration in the learning process. We develop an efficient algorithm to mathematically solve the problem by outputting the optimum strategy. Extensive simulation results demonstrate the superiority of our schemes compared with conventional solutions.
Authors: Joykirat Singh, Akshay Nambi, Vibhav Vineet
Abstract: Large Language Models (LLMs) have been applied to Math Word Problems (MWPs) with transformative impacts, revolutionizing how these complex problems are approached and solved in various domains including educational settings. However, the evaluation of these models often prioritizes final accuracy, overlooking the crucial aspect of reasoning capabilities. This work addresses this gap by focusing on the ability of LLMs to detect and correct reasoning mistakes. We introduce a novel dataset MWP-MISTAKE, incorporating MWPs with both correct and incorrect reasoning steps generated through rule-based methods and smaller language models. Our comprehensive benchmarking reveals significant insights into the strengths and weaknesses of state-of-the-art models, such as GPT-4o, GPT-4, GPT-3.5Turbo, and others. We highlight GPT-$o's superior performance in mistake detection and rectification and the persistent challenges faced by smaller models. Additionally, we identify issues related to data contamination and memorization, impacting the reliability of LLMs in real-world applications. Our findings emphasize the importance of rigorous evaluation of reasoning processes and propose future directions to enhance the generalization and robustness of LLMs in mathematical problem-solving.
Authors: Haitao Lin, Guojiang Zhao, Odin Zhang, Yufei Huang, Lirong Wu, Zicheng Liu, Siyuan Li, Cheng Tan, Zhifeng Gao, Stan Z. Li
Abstract: Structure-based drug design (SBDD) aims to generate potential drugs that can bind to a target protein and is greatly expedited by the aid of AI techniques in generative models. However, a lack of systematic understanding persists due to the diverse settings, complex implementation, difficult reproducibility, and task singularity. Firstly, the absence of standardization can lead to unfair comparisons and inconclusive insights. To address this dilemma, we propose CBGBench, a comprehensive benchmark for SBDD, that unifies the task as a generative heterogeneous graph completion, analogous to fill-in-the-blank of the 3D complex binding graph. By categorizing existing methods based on their attributes, CBGBench facilitates a modular and extensible framework that implements various cutting-edge methods. Secondly, a single task on \textit{de novo} molecule generation can hardly reflect their capabilities. To broaden the scope, we have adapted these models to a range of tasks essential in drug design, which are considered sub-tasks within the graph fill-in-the-blank tasks. These tasks include the generative designation of \textit{de novo} molecules, linkers, fragments, scaffolds, and sidechains, all conditioned on the structures of protein pockets. Our evaluations are conducted with fairness, encompassing comprehensive perspectives on interaction, chemical properties, geometry authenticity, and substructure validity. We further provide the pre-trained versions of the state-of-the-art models and deep insights with analysis from empirical studies. The codebase for CBGBench is publicly accessible at \url{https://github.com/Edapinenut/CBGBench}.
Authors: Zhuoxu Duan, Zhengye Yang, Samuel Westby, Christoph Riedl, Brooke Foucault Welles, Richard J. Radke
Abstract: Large language models like GPT have proven widely successful on natural language understanding tasks based on written text documents. In this paper, we investigate an LLM's performance on recordings of a group oral communication task in which utterances are often truncated or not well-formed. We propose a new group task experiment involving a puzzle with several milestones that can be achieved in any order. We investigate methods for processing transcripts to detect if, when, and by whom a milestone has been completed. We demonstrate that iteratively prompting GPT with transcription chunks outperforms semantic similarity search methods using text embeddings, and further discuss the quality and randomness of GPT responses under different context window sizes.
Authors: Yue Zhuo, Zhiqiang Ge
Abstract: Feature attribution explains Artificial Intelligence (AI) at the instance level by providing importance scores of input features' contributions to model prediction. Integrated Gradients (IG) is a prominent path attribution method for deep neural networks, involving the integration of gradients along a path from the explained input (explicand) to a counterfactual instance (baseline). Current IG variants primarily focus on the gradient of explicand's output. However, our research indicates that the gradient of the counterfactual output significantly affects feature attribution as well. To achieve this, we propose Iterative Gradient path Integrated Gradients (IG2), considering both gradients. IG2 incorporates the counterfactual gradient iteratively into the integration path, generating a novel path (GradPath) and a novel baseline (GradCF). These two novel IG components effectively address the issues of attribution noise and arbitrary baseline choice in earlier IG methods. IG2, as a path method, satisfies many desirable axioms, which are theoretically justified in the paper. Experimental results on XAI benchmark, ImageNet, MNIST, TREC questions answering, wafer-map failure patterns, and CelebA face attributes validate that IG2 delivers superior feature attributions compared to the state-of-the-art techniques. The code is released at: https://github.com/JoeZhuo-ZY/IG2.
Authors: Song Zhang, Qingzhong Wang, Junyi Liu, Haoyi Xiong
Abstract: In the fast-growing field of Remote Sensing (RS) image analysis, the gap between massive unlabeled datasets and the ability to fully utilize these datasets for advanced RS analytics presents a significant challenge. To fill the gap, our work introduces an innovative auto-labeling framework named ALPS (Automatic Labeling for Pre-training in Segmentation), leveraging the Segment Anything Model (SAM) to predict precise pseudo-labels for RS images without necessitating prior annotations or additional prompts. The proposed pipeline significantly reduces the labor and resource demands traditionally associated with annotating RS datasets. By constructing two comprehensive pseudo-labeled RS datasets via ALPS for pre-training purposes, our approach enhances the performance of downstream tasks across various benchmarks, including iSAID and ISPRS Potsdam. Experiments demonstrate the effectiveness of our framework, showcasing its ability to generalize well across multiple tasks even under the scarcity of extensively annotated datasets, offering a scalable solution to automatic segmentation and annotation challenges in the field. In addition, the proposed a pipeline is flexible and can be applied to medical image segmentation, remarkably boosting the performance. Note that ALPS utilizes pre-trained SAM to semi-automatically annotate RS images without additional manual annotations. Though every component in the pipeline has bee well explored, integrating clustering algorithms with SAM and novel pseudo-label alignment significantly enhances RS segmentation, as an off-the-shelf tool for pre-training data preparation. Our source code is available at: https://github.com/StriveZs/ALPS.
Authors: Guoxin Chen, Minpeng Liao, Chengxi Li, Kai Fan
Abstract: Direct Preference Optimization (DPO) using an implicit reward model has proven to be an effective alternative to reinforcement learning from human feedback (RLHF) for fine-tuning preference aligned large language models (LLMs). However, the overall preference annotations of responses do not fully capture the fine-grained quality of model outputs in complex multi-step reasoning tasks, such as mathematical reasoning. To address this limitation, we introduce a novel algorithm called Step-level Value Preference Optimization (SVPO). Our approach employs Monte Carlo Tree Search (MCTS) to automatically annotate step-level preferences for multi-step reasoning. Furthermore, from the perspective of learning-to-rank, we train an explicit value model to replicate the behavior of the implicit reward model, complementing standard preference optimization. This value model enables the LLM to generate higher reward responses with minimal cost during inference. Experimental results demonstrate that our method achieves state-of-the-art performance on both in-domain and out-of-domain mathematical reasoning benchmarks.
Authors: Chung-Wen Wu, Berlin Chen
Abstract: Automatic Speech Assessment (ASA) has seen notable advancements with the utilization of self-supervised features (SSL) in recent research. However, a key challenge in ASA lies in the imbalanced distribution of data, particularly evident in English test datasets. To address this challenge, we approach ASA as an ordinal classification task, introducing Weighted Vectors Ranking Similarity (W-RankSim) as a novel regularization technique. W-RankSim encourages closer proximity of weighted vectors in the output layer for similar classes, implying that feature vectors with similar labels would be gradually nudged closer to each other as they converge towards corresponding weighted vectors. Extensive experimental evaluations confirm the effectiveness of our approach in improving ordinal classification performance for ASA. Furthermore, we propose a hybrid model that combines SSL and handcrafted features, showcasing how the inclusion of handcrafted features enhances performance in an ASA system.
Authors: Darshana Saravanan, Darshan Singh, Varun Gupta, Zeeshan Khan, Vineet Gandhi, Makarand Tapaswi
Abstract: Compositionality is a fundamental aspect of vision-language understanding and is especially required for videos since they contain multiple entities (e.g. persons, actions, and scenes) interacting dynamically over time. Existing benchmarks focus primarily on perception capabilities. However, they do not study binding, the ability of a model to associate entities through appropriate relationships. To this end, we propose VELOCITI, a new benchmark building on complex movie clips and dense semantic role label annotations to test perception and binding in video language models (contrastive and Video-LLMs). Our perception-based tests require discriminating video-caption pairs that share similar entities, and the binding tests require models to associate the correct entity to a given situation while ignoring the different yet plausible entities that also appear in the same video. While current state-of-the-art models perform moderately well on perception tests, accuracy is near random when both entities are present in the same video, indicating that they fail at binding tests. Even the powerful Gemini 1.5 Flash has a substantial gap (16-28%) with respect to human accuracy in such binding tests.
Authors: Zhuoran Jin, Pengfei Cao, Chenhao Wang, Zhitao He, Hongbang Yuan, Jiachun Li, Yubo Chen, Kang Liu, Jun Zhao
Abstract: Large language models (LLMs) inevitably memorize sensitive, copyrighted, and harmful knowledge from the training corpus; therefore, it is crucial to erase this knowledge from the models. Machine unlearning is a promising solution for efficiently removing specific knowledge by post hoc modifying models. In this paper, we propose a Real-World Knowledge Unlearning benchmark (RWKU) for LLM unlearning. RWKU is designed based on the following three key factors: (1) For the task setting, we consider a more practical and challenging unlearning setting, where neither the forget corpus nor the retain corpus is accessible. (2) For the knowledge source, we choose 200 real-world famous people as the unlearning targets and show that such popular knowledge is widely present in various LLMs. (3) For the evaluation framework, we design the forget set and the retain set to evaluate the model's capabilities across various real-world applications. Regarding the forget set, we provide four four membership inference attack (MIA) methods and nine kinds of adversarial attack probes to rigorously test unlearning efficacy. Regarding the retain set, we assess locality and utility in terms of neighbor perturbation, general ability, reasoning ability, truthfulness, factuality, and fluency. We conduct extensive experiments across two unlearning scenarios, two models and six baseline methods and obtain some meaningful findings. We release our benchmark and code publicly at http://rwku-bench.github.io for future work.
Authors: Sumit Kumar Jha, Purnendu Mishra, Shubham Mathur, Gursewak Singh, Rajiv Kumar, Kiran Aatre, Suraj Rengarajan
Abstract: Immunohistochemistry (IHC) analysis is a well-accepted and widely used method for molecular subtyping, a procedure for prognosis and targeted therapy of breast carcinoma, the most common type of tumor affecting women. There are four molecular biomarkers namely progesterone receptor (PR), estrogen receptor (ER), antigen Ki67, and human epidermal growth factor receptor 2 (HER2) whose assessment is needed under IHC procedure to decide prognosis as well as predictors of response to therapy. However, IHC scoring is based on subjective microscopic examination of tumor morphology and suffers from poor reproducibility, high subjectivity, and often incorrect scoring in low-score cases. In this paper, we present, a deep learning-based semi-supervised trained, fully automatic, decision support system (DSS) for IHC scoring of invasive ductal carcinoma. Our system automatically detects the tumor region removing artifacts and scores based on Allred standard. The system is developed using 3 million pathologist-annotated image patches from 300 slides, fifty thousand in-house cell annotations, and forty thousand pixels marking of HER2 membrane. We have conducted multicentric trials at four centers with three different types of digital scanners in terms of percentage agreement with doctors. And achieved agreements of 95, 92, 88 and 82 percent for Ki67, HER2, ER, and PR stain categories, respectively. In addition to overall accuracy, we found that there is 5 percent of cases where pathologist have changed their score in favor of algorithm score while reviewing with detailed algorithmic analysis. Our approach could improve the accuracy of IHC scoring and subsequent therapy decisions, particularly where specialist expertise is unavailable. Our system is highly modular. The proposed algorithm modules can be used to develop DSS for other cancer types.
Authors: Bhrij Patel, Vishnu Sashank Dorbala, Amrit Singh Bedi
Abstract: Embodied Question Answering (EQA) is an important problem, which involves an agent exploring the environment to answer user queries. In the existing literature, EQA has exclusively been studied in single-agent scenarios, where exploration can be time-consuming and costly. In this work, we consider EQA in a multi-agent framework involving multiple large language models (LLM) based agents independently answering queries about a household environment. To generate one answer for each query, we use the individual responses to train a Central Answer Model (CAM) that aggregates responses for a robust answer. Using CAM, we observe a $50\%$ higher EQA accuracy when compared against aggregation methods for ensemble LLM, such as voting schemes and debates. CAM does not require any form of agent communication, alleviating it from the associated costs. We ablate CAM with various nonlinear (neural network, random forest, decision tree, XGBoost) and linear (logistic regression classifier, SVM) algorithms. Finally, we present a feature importance analysis for CAM via permutation feature importance (PFI), quantifying CAMs reliance on each independent agent and query context.
Authors: Jae Yong Lee, Yeoneung Kim
Abstract: The framework of deep operator network (DeepONet) has been widely exploited thanks to its capability of solving high dimensional partial differential equations. In this paper, we incorporate DeepONet with a recently developed policy iteration scheme to numerically solve optimal control problems and the corresponding Hamilton--Jacobi--Bellman (HJB) equations. A notable feature of our approach is that once the neural network is trained, the solution to the optimal control problem and HJB equations with different terminal functions can be inferred quickly thanks to the unique feature of operator learning. Furthermore, a quantitative analysis of the accuracy of the algorithm is carried out via comparison principles of viscosity solutions. The effectiveness of the method is verified with various examples, including 10-dimensional linear quadratic regulator problems (LQRs).
Authors: Yevgeni Berkovitch, Oren Glickman, Amit Somech, Tomer Wolfson
Abstract: We explore generating factual and accurate tables from the parametric knowledge of large language models (LLMs). While LLMs have demonstrated impressive capabilities in recreating knowledge bases and generating free-form text, we focus on generating structured tabular data, which is crucial in domains like finance and healthcare. We examine the table generation abilities of four state-of-the-art LLMs: GPT-3.5, GPT-4, Llama2-13B, and Llama2-70B, using three prompting methods for table generation: (a) full-table, (b) row-by-row; (c) cell-by-cell. For evaluation, we introduce a novel benchmark, WikiTabGen which contains 100 curated Wikipedia tables. Tables are further processed to ensure their factual correctness and manually annotated with short natural language descriptions. Our findings reveal that table generation remains a challenge, with GPT-4 reaching the highest accuracy at 19.6%. Our detailed analysis sheds light on how various table properties, such as size, table popularity, and numerical content, influence generation performance. This work highlights the unique challenges in LLM-based table generation and provides a solid evaluation framework for future research. Our code, prompts and data are all publicly available: https://github.com/analysis-bots/WikiTabGen
Authors: Xiao Jingyu, Xu Zhiyao, Zou Qingsong, Li Qing, Zhao Dan, Fang Dong, Li Ruoyu, Tang Wenxin, Li Kang, Zuo Xudong, Hu Penghui, Jiang Yong, Weng Zixuan, Lyv. R Michael
Abstract: Smart homes, powered by the Internet of Things, offer great convenience but also pose security concerns due to abnormal behaviors, such as improper operations of users and potential attacks from malicious attackers. Several behavior modeling methods have been proposed to identify abnormal behaviors and mitigate potential risks. However, their performance often falls short because they do not effectively learn less frequent behaviors, consider temporal context, or account for the impact of noise in human behaviors. In this paper, we propose SmartGuard, an autoencoder-based unsupervised user behavior anomaly detection framework. First, we design a Loss-guided Dynamic Mask Strategy (LDMS) to encourage the model to learn less frequent behaviors, which are often overlooked during learning. Second, we propose a Three-level Time-aware Position Embedding (TTPE) to incorporate temporal information into positional embedding to detect temporal context anomaly. Third, we propose a Noise-aware Weighted Reconstruction Loss (NWRL) that assigns different weights for routine behaviors and noise behaviors to mitigate the interference of noise behaviors during inference. Comprehensive experiments on three datasets with ten types of anomaly behaviors demonstrates that SmartGuard consistently outperforms state-of-the-art baselines and also offers highly interpretable results.
Authors: Wenhan Yao, Jiangkun Yang, Yongqiang He, Jia Liu, Weiping Wen
Abstract: Speech recognition is an essential start ring of human-computer interaction, and recently, deep learning models have achieved excellent success in this task. However, when the model training and private data provider are always separated, some security threats that make deep neural networks (DNNs) abnormal deserve to be researched. In recent years, the typical backdoor attacks have been researched in speech recognition systems. The existing backdoor methods are based on data poisoning. The attacker adds some incorporated changes to benign speech spectrograms or changes the speech components, such as pitch and timbre. As a result, the poisoned data can be detected by human hearing or automatic deep algorithms. To improve the stealthiness of data poisoning, we propose a non-neural and fast algorithm called Random Spectrogram Rhythm Transformation (RSRT) in this paper. The algorithm combines four steps to generate stealthy poisoned utterances. From the perspective of rhythm component transformation, our proposed trigger stretches or squeezes the mel spectrograms and recovers them back to signals. The operation keeps timbre and content unchanged for good stealthiness. Our experiments are conducted on two kinds of speech recognition tasks, including testing the stealthiness of poisoned samples by speaker verification and automatic speech recognition. The results show that our method has excellent effectiveness and stealthiness. The rhythm trigger needs a low poisoning rate and gets a very high attack success rate.
Authors: Heidi Carolina Tamm, Anastasija Nikiforova
Abstract: In the contemporary data-driven landscape, ensuring data quality (DQ) is crucial for deriving actionable insights from vast data repositories. The objective of this study is to explore the potential for automating data quality management within data warehouses as data repository commonly used by large organizations. By conducting a systematic review of existing DQ tools available in the market and academic literature, the study assesses their capability to automatically detect and enforce data quality rules. The review encompassed 151 tools from various sources, revealing that most current tools focus on data cleansing and fixing in domain-specific databases rather than data warehouses. Only a limited number of tools, specifically ten, demonstrated the capability to detect DQ rules, not to mention implementing this in data warehouses. The findings underscore a significant gap in the market and academic research regarding AI-augmented DQ rule detection in data warehouses. This paper advocates for further development in this area to enhance the efficiency of DQ management processes, reduce human workload, and lower costs. The study highlights the necessity of advanced tools for automated DQ rule detection, paving the way for improved practices in data quality management tailored to data warehouse environments. The study can guide organizations in selecting data quality tool that would meet their requirements most.
Authors: Shuwen Zheng, Zhou Fang, Liang Zhao
Abstract: Existing deep learning approaches for travel mode choice modeling fail to inform modelers about their prediction uncertainty. Even when facing scenarios that are out of the distribution of training data, which implies high prediction uncertainty, these approaches still provide deterministic answers, potentially leading to misguidance. To address this limitation, this study introduces the concept of uncertainty from the field of explainable artificial intelligence into travel mode choice modeling. We propose a Bayesian neural network-based travel mode prediction model (BTMP) that quantifies the uncertainty of travel mode predictions, enabling the model itself to "know" and "tell" what it doesn't know. With BTMP, we further propose an uncertainty-guided active survey framework, which dynamically formulates survey questions representing travel mode choice scenarios with high prediction uncertainty. Through iterative collection of responses to these dynamically tailored survey questions, BTMP is iteratively trained to achieve the desired accuracy faster with fewer questions, thereby reducing survey costs. Experimental validation using synthetic datasets confirms the effectiveness of BTMP in quantifying prediction uncertainty. Furthermore, experiments, utilizing both synthetic and real-world data, demonstrate that the BTMP model, trained with the uncertainty-guided active survey framework, requires 20% to 50% fewer survey responses to match the performance of the model trained on randomly collected survey data. Overall, the proposed BTMP model and active survey framework innovatively incorporate uncertainty quantification into travel mode choice modeling, providing model users with essential insights into prediction reliability while optimizing data collection for deep learning model training in a cost-efficient manner.
Authors: Shuyang Lin, Tong Jia, Hao Wang, Bowen Ma, Mingyuan Li, Dongyue Chen
Abstract: X-ray prohibited item detection is an essential component of security check and categories of prohibited item are continuously increasing in accordance with the latest laws. Previous works all focus on close-set scenarios, which can only recognize known categories used for training and often require time-consuming as well as labor-intensive annotations when learning novel categories, resulting in limited real-world applications. Although the success of vision-language models (e.g. CLIP) provides a new perspectives for open-set X-ray prohibited item detection, directly applying CLIP to X-ray domain leads to a sharp performance drop due to domain shift between X-ray data and general data used for pre-training CLIP. To address aforementioned challenges, in this paper, we introduce distillation-based open-vocabulary object detection (OVOD) task into X-ray security inspection domain by extending CLIP to learn visual representations in our specific X-ray domain, aiming to detect novel prohibited item categories beyond base categories on which the detector is trained. Specifically, we propose X-ray feature adapter and apply it to CLIP within OVOD framework to develop OVXD model. X-ray feature adapter containing three adapter submodules of bottleneck architecture, which is simple but can efficiently integrate new knowledge of X-ray domain with original knowledge, further bridge domain gap and promote alignment between X-ray images and textual concepts. Extensive experiments conducted on PIXray and PIDray datasets demonstrate that proposed method performs favorably against other baseline OVOD methods in detecting novel categories in X-ray scenario. It outperforms previous best result by 15.2 AP50 and 1.5 AP50 on PIXray and PIDray with achieving 21.0 AP50 and 27.8 AP50 respectively.
Authors: Samar Khanna, Medhanie Irgau, David B. Lobell, Stefano Ermon
Abstract: Parameter-efficient fine-tuning (PEFT) techniques such as low-rank adaptation (LoRA) can effectively adapt large pre-trained foundation models to downstream tasks using only a small fraction (0.1%-10%) of the original trainable weights. An under-explored question of PEFT is in extending the pre-training phase without supervised labels; that is, can we adapt a pre-trained foundation model to a new domain via efficient self-supervised pre-training on this new domain? In this work, we introduce ExPLoRA, a highly effective technique to improve transfer learning of pre-trained vision transformers (ViTs) under domain shifts. Initializing a ViT with pre-trained weights on large, natural-image datasets such as from DinoV2 or MAE, ExPLoRA continues the unsupervised pre-training objective on a new domain. In this extended pre-training phase, ExPLoRA only unfreezes 1-2 pre-trained ViT blocks and all normalization layers, and then tunes all other layers with LoRA. Finally, we fine-tune the resulting model only with LoRA on this new domain for supervised learning. Our experiments demonstrate state-of-the-art results on satellite imagery, even outperforming fully pre-training and fine-tuning ViTs. Using the DinoV2 training objective, we demonstrate up to 7% improvement in linear probing top-1 accuracy on downstream tasks while using <10% of the number of parameters that are used in prior fully-tuned state-of-the art approaches. Our ablation studies confirm the efficacy of our approach over other baselines, including PEFT and simply unfreezing more transformer blocks.
Authors: T. Y. S. S Santosh, Kevin D. Ashley, Katie Atkinson, Matthias Grabmair
Abstract: Modeling legal reasoning and argumentation justifying decisions in cases has always been central to AI & Law, yet contemporary developments in legal NLP have increasingly focused on statistically classifying legal conclusions from text. While conceptually simpler, these approaches often fall short in providing usable justifications connecting to appropriate legal concepts. This paper reviews both traditional symbolic works in AI & Law and recent advances in legal NLP, and distills possibilities of integrating expert-informed knowledge to strike a balance between scalability and explanation in symbolic vs. data-driven approaches. We identify open challenges and discuss the potential of modern NLP models and methods that integrate
Authors: Rui Zheng, Hongyi Guo, Zhihan Liu, Xiaoying Zhang, Yuanshun Yao, Xiaojun Xu, Zhaoran Wang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Hang Li, Yang Liu
Abstract: The standard Reinforcement Learning from Human Feedback (RLHF) framework primarily focuses on optimizing the performance of large language models using pre-collected prompts. However, collecting prompts that provide comprehensive coverage is both tedious and challenging, and often fails to include scenarios that LLMs need to improve on the most. In this paper, we investigate alignment through the lens of two-agent games, involving iterative interactions between an adversarial and a defensive agent. The adversarial agent's task at each step is to generate prompts that expose the weakness of the defensive agent. In return, the defensive agent seeks to improve its responses to these newly identified prompts it struggled with, based on feedback from the reward model. We theoretically demonstrate that this iterative reinforcement learning optimization converges to a Nash Equilibrium for the game induced by the agents. Experimental results in safety scenarios demonstrate that learning in such a competitive environment not only fully trains agents but also leads to policies with enhanced generalization capabilities for both adversarial and defensive agents.
Authors: Mojtaba Mostafavi Ghahfarokhi, Alireza Asadi, Arash Asgari, Bardia Mohammadi, Masih Beigi Rizi, Abbas Heydarnoori
Abstract: Computational notebooks have become the primary coding environment for data scientists. However, research on their code quality is still emerging, and the code shared is often of poor quality. Given the importance of maintenance and reusability, understanding the metrics that affect notebook code comprehensibility is crucial. Code understandability, a qualitative variable, is closely tied to user opinions. Traditional approaches to measuring it either use limited questionnaires to review a few code pieces or rely on metadata such as likes and votes in software repositories. Our approach enhances the measurement of Jupyter notebook understandability by leveraging user comments related to code understandability. As a case study, we used 542,051 Kaggle Jupyter notebooks from our previous research, named DistilKaggle. We employed a fine-tuned DistilBERT transformer to identify user comments associated with code understandability. We established a criterion called User Opinion Code Understandability (UOCU), which considers the number of relevant comments, upvotes on those comments, total notebook views, and total notebook upvotes. UOCU proved to be more effective than previous methods. Furthermore, we trained machine learning models to predict notebook code understandability based solely on their metrics. We collected 34 metrics for 132,723 final notebooks as features in our dataset, using UOCU as the label. Our predictive model, using the Random Forest classifier, achieved 89% accuracy in predicting the understandability levels of computational notebooks.
Authors: Liman Wang, Hanyang Zhong
Abstract: This paper investigates the nuanced role of biases in the decision-making processes of large language models (LLMs). While conventional research typically aims to eliminate all biases, our study reveals that not all biases are detrimental. By examining rational deviations, involving heuristic shortcuts that enhance decision-making efficiency, we highlight their potential benefits when properly balanced. We introduce the concepts of heuristic moderation and an abstention option, allowing LLMs to abstain from answering when uncertain, thereby reducing error rates and improving decision accuracy. Using our newly developed BRD (Balance Rational Deviations) dataset, our findings demonstrate that appropriately scaled bias inspection enhances model performance and aligns LLM decision-making more closely with human reasoning. This balance improves the reliability and trustworthiness of LLMs and suggests new strategies for future enhancements. Our work offers a fresh perspective on leveraging biases constructively to enhance the practical applications of LLMs, from conversational agents to decision support systems and beyond.
Authors: Eduardo Davalos, Yike Zhang, Ashwin T. S., Joyce H. Fonteles, Umesh Timalsina, Guatam Biswas
Abstract: This study presents a novel framework for 3D gaze tracking tailored for mixed-reality settings, aimed at enhancing joint attention and collaborative efforts in team-based scenarios. Conventional gaze tracking, often limited by monocular cameras and traditional eye-tracking apparatus, struggles with simultaneous data synchronization and analysis from multiple participants in group contexts. Our proposed framework leverages state-of-the-art computer vision and machine learning techniques to overcome these obstacles, enabling precise 3D gaze estimation without dependence on specialized hardware or complex data fusion. Utilizing facial recognition and deep learning, the framework achieves real-time, tracking of gaze patterns across several individuals, addressing common depth estimation errors, and ensuring spatial and identity consistency within the dataset. Empirical results demonstrate the accuracy and reliability of our method in group environments. This provides mechanisms for significant advances in behavior and interaction analysis in educational and professional training applications in dynamic and unstructured environments.
Authors: Yuhang He, Shitong Xu, Jia-Xing Zhong, Sangyun Shin, Niki Trigoni, Andrew Markham
Abstract: We present SPEAR, a continuous receiver-to-receiver acoustic neural warping field for spatial acoustic effects prediction in an acoustic 3D space with a single stationary audio source. Unlike traditional source-to-receiver modelling methods that require prior space acoustic properties knowledge to rigorously model audio propagation from source to receiver, we propose to predict by warping the spatial acoustic effects from one reference receiver position to another target receiver position, so that the warped audio essentially accommodates all spatial acoustic effects belonging to the target position. SPEAR can be trained in a data much more readily accessible manner, in which we simply ask two robots to independently record spatial audio at different positions. We further theoretically prove the universal existence of the warping field if and only if one audio source presents. Three physical principles are incorporated to guide SPEAR network design, leading to the learned warping field physically meaningful. We demonstrate SPEAR superiority on both synthetic, photo-realistic and real-world dataset, showing the huge potential of SPEAR to various down-stream robotic tasks.
Authors: Prisha Samadarshi, Mariam Mustafa, Anushka Kulkarni, Raven Rothkopf, Tuhin Chakrabarty, Smaranda Muresan
Abstract: The New York Times Connections game has emerged as a popular and challenging pursuit for word puzzle enthusiasts. We collect 200 Connections games to evaluate the performance of state-of-the-art large language models (LLMs) against expert and novice human players. Our results show that even the best-performing LLM, GPT-4o, which has otherwise shown impressive reasoning abilities on a wide variety of benchmarks, can only fully solve 8% of the games. Compared to GPT-4o, novice and expert players perform better, with expert human players significantly outperforming GPT-4o. To deepen our understanding we create a taxonomy of the knowledge types required to successfully categorize words in the Connections game, revealing that LLMs struggle with associative, encyclopedic, and linguistic knowledge. Our findings establish the New York Times Connections game as a challenging benchmark for evaluating abstract reasoning capabilities in humans and AI systems.
Authors: Luca Moschella
Abstract: As NNs permeate various scientific and industrial domains, understanding the universality and reusability of their representations becomes crucial. At their core, these networks create intermediate neural representations, indicated as latent spaces, of the input data and subsequently leverage them to perform specific downstream tasks. This dissertation focuses on the universality and reusability of neural representations. Do the latent representations crafted by a NN remain exclusive to a particular trained instance, or can they generalize across models, adapting to factors such as randomness during training, model architecture, or even data domain? This adaptive quality introduces the notion of Latent Communication -- a phenomenon that describes when representations can be unified or reused across neural spaces. A salient observation from our research is the emergence of similarities in latent representations, even when these originate from distinct or seemingly unrelated NNs. By exploiting a partial correspondence between the two data distributions that establishes a semantic link, we found that these representations can either be projected into a universal representation, coined as Relative Representation, or be directly translated from one space to another. Latent Communication allows for a bridge between independently trained NN, irrespective of their training regimen, architecture, or the data modality they were trained on -- as long as the data semantic content stays the same (e.g., images and their captions). This holds true for both generation, classification and retrieval downstream tasks; in supervised, weakly supervised, and unsupervised settings; and spans various data modalities including images, text, audio, and graphs -- showcasing the universality of the Latent Communication phenomenon. [...]
Authors: Mohammadreza Kavianpour, Parisa Kavianpour, Amin Ramezani
Abstract: One of the most significant obstacles in bearing fault diagnosis is a lack of labeled data for various fault types. Also, sensor-acquired data frequently lack labels and have a large amount of missing data. This paper tackles these issues by presenting the PTPAI method, which uses a physics-informed deep learning-based technique to generate synthetic labeled data. Labeled synthetic data makes up the source domain, whereas unlabeled data with missing data is present in the target domain. Consequently, imbalanced class problems and partial-set fault diagnosis hurdles emerge. To address these challenges, the RF-Mixup approach is used to handle imbalanced classes. As domain adaptation strategies, the MK-MMSD and CDAN are employed to mitigate the disparity in distribution between synthetic and actual data. Furthermore, the partial-set challenge is tackled by applying weighting methods at the class and instance levels. Experimental outcomes on the CWRU and JNU datasets indicate that the proposed approach effectively addresses these problems.
Authors: Pengfei Gu, Zihan Zhao, Hongxiao Wang, Yaopeng Peng, Yizhe Zhang, Nishchal Sapkota, Chaoli Wang, Danny Z. Chen
Abstract: The Segment Anything Model (SAM) exhibits impressive capabilities in zero-shot segmentation for natural images. Recently, SAM has gained a great deal of attention for its applications in medical image segmentation. However, to our best knowledge, no studies have shown how to harness the power of SAM for medical image classification. To fill this gap and make SAM a true ``foundation model'' for medical image analysis, it is highly desirable to customize SAM specifically for medical image classification. In this paper, we introduce SAMAug-C, an innovative augmentation method based on SAM for augmenting classification datasets by generating variants of the original images. The augmented datasets can be used to train a deep learning classification model, thereby boosting the classification performance. Furthermore, we propose a novel framework that simultaneously processes raw and SAMAug-C augmented image input, capitalizing on the complementary information that is offered by both. Experiments on three public datasets validate the effectiveness of our new approach.
Authors: Yupeng Xie, Yuyu Luo, Guoliang Li, Nan Tang
Abstract: The growing importance of data visualization in business intelligence and data science emphasizes the need for tools that can efficiently generate meaningful visualizations from large datasets. Existing tools fall into two main categories: human-powered tools (e.g., Tableau and PowerBI), which require intensive expert involvement, and AI-powered automated tools (e.g., Draco and Table2Charts), which often fall short of guessing specific user needs. In this paper, we aim to achieve the best of both worlds. Our key idea is to initially auto-generate a set of high-quality visualizations to minimize manual effort, then refine this process iteratively with user feedback to more closely align with their needs. To this end, we present HAIChart, a reinforcement learning-based framework designed to iteratively recommend good visualizations for a given dataset by incorporating user feedback. Specifically, we propose a Monte Carlo Graph Search-based visualization generation algorithm paired with a composite reward function to efficiently explore the visualization space and automatically generate good visualizations. We devise a visualization hints mechanism to actively incorporate user feedback, thus progressively refining the visualization generation module. We further prove that the top-k visualization hints selection problem is NP-hard and design an efficient algorithm. We conduct both quantitative evaluations and user studies, showing that HAIChart significantly outperforms state-of-the-art human-powered tools (21% better at Recall and 1.8 times faster) and AI-powered automatic tools (25.1% and 14.9% better in terms of Hit@3 and R10@30, respectively).
Authors: Behrad Moniri, Hamed Hassani, Edgar Dobriban
Abstract: Large Language Models (LLMs) are rapidly evolving and impacting various fields, necessitating the development of effective methods to evaluate and compare their performance. Most current approaches for performance evaluation are either based on fixed, domain-specific questions that lack the flexibility required in many real-world applications where tasks are not always from a single domain, or rely on human input, making them unscalable. We propose an automated benchmarking framework based on debates between LLMs, judged by another LLM. This method assesses not only domain knowledge, but also skills such as problem definition and inconsistency recognition. We evaluate the performance of various state-of-the-art LLMs using the debate framework and achieve rankings that align closely with popular rankings based on human input, eliminating the need for costly human crowdsourcing.
Authors: Chandran Nandkumar, Luka Peternel
Abstract: This paper presents the design and evaluation of a novel multi-level LLM interface for supermarket robots to assist customers. The proposed interface allows customers to convey their needs through both generic and specific queries. While state-of-the-art systems like OpenAI's GPTs are highly adaptable and easy to build and deploy, they still face challenges such as increased response times and limitations in strategic control of the underlying model for tailored use-case and cost optimization. Driven by the goal of developing faster and more efficient conversational agents, this paper advocates for using multiple smaller, specialized LLMs fine-tuned to handle different user queries based on their specificity and user intent. We compare this approach to a specialized GPT model powered by GPT-4 Turbo, using the Artificial Social Agent Questionnaire (ASAQ) and qualitative participant feedback in a counterbalanced within-subjects experiment. Our findings show that our multi-LLM chatbot architecture outperformed the benchmarked GPT model across all 13 measured criteria, with statistically significant improvements in four key areas: performance, user satisfaction, user-agent partnership, and self-image enhancement. The paper also presents a method for supermarket robot navigation by mapping the final chatbot response to correct shelf numbers, enabling the robot to sequentially navigate towards the respective products, after which lower-level robot perception, control, and planning can be used for automated object retrieval. We hope this work encourages more efforts into using multiple, specialized smaller models instead of relying on a single powerful, but more expensive and slower model.
Authors: Bowen Jiang, Yangxinyu Xie, Zhuoqun Hao, Xiaomeng Wang, Tanwi Mallick, Weijie J. Su, Camillo J. Taylor, Dan Roth
Abstract: This study introduces a hypothesis-testing framework to assess whether large language models (LLMs) possess genuine reasoning abilities or primarily depend on token bias. We go beyond evaluating LLMs on accuracy; rather, we aim to investigate their token bias in solving logical reasoning tasks. Specifically, we develop carefully controlled synthetic datasets, featuring conjunction fallacy and syllogistic problems. Our framework outlines a list of hypotheses where token biases are readily identifiable, with all null hypotheses assuming genuine reasoning capabilities of LLMs. The findings in this study suggest, with statistical guarantee, that most LLMs still struggle with logical reasoning. While they may perform well on classic problems, their success largely depends on recognizing superficial patterns with strong token bias, thereby raising concerns about their actual reasoning and generalization abilities.
Authors: Yujie Lu, Dongfu Jiang, Wenhu Chen, William Yang Wang, Yejin Choi, Bill Yuchen Lin
Abstract: Recent breakthroughs in vision-language models (VLMs) emphasize the necessity of benchmarking human preferences in real-world multimodal interactions. To address this gap, we launched WildVision-Arena (WV-Arena), an online platform that collects human preferences to evaluate VLMs. We curated WV-Bench by selecting 500 high-quality samples from 8,000 user submissions in WV-Arena. WV-Bench uses GPT-4 as the judge to compare each VLM with Claude-3-Sonnet, achieving a Spearman correlation of 0.94 with the WV-Arena Elo. This significantly outperforms other benchmarks like MMVet, MMMU, and MMStar. Our comprehensive analysis of 20K real-world interactions reveals important insights into the failure cases of top-performing VLMs. For example, we find that although GPT-4V surpasses many other models like Reka-Flash, Opus, and Yi-VL-Plus in simple visual recognition and reasoning tasks, it still faces challenges with subtle contextual cues, spatial reasoning, visual imagination, and expert domain knowledge. Additionally, current VLMs exhibit issues with hallucinations and safety when intentionally provoked. We are releasing our chat and feedback data to further advance research in the field of VLMs.
Authors: Yanming Liu, Xinyue Peng, Jiannan Cao, Yuwei Zhang, Chen Ma, Songhang Deng, Mengchen Fu, Xuhong Zhang, Sheng Cheng, Xun Wang, Jianwei Yin, Tianyu Du
Abstract: Large language models have consistently demonstrated remarkable performance across a wide spectrum of applications. Nonetheless, the deployment of these models can inadvertently expose user privacy to potential risks. The substantial memory demands of these models during training represent a significant resource consumption challenge. The sheer size of these models imposes a considerable burden on memory resources, which is a matter of significant concern in practice. In this paper, we present an innovative training framework MemDPT that not only reduces the memory cost of large language models but also places a strong emphasis on safeguarding user data privacy. MemDPT provides edge network and reverse network designs to accommodate various differential privacy memory-efficient fine-tuning schemes. Our approach not only achieves $2 \sim 3 \times$ memory optimization but also provides robust privacy protection, ensuring that user data remains secure and confidential. Extensive experiments have demonstrated that MemDPT can effectively provide differential privacy efficient fine-tuning across various task scenarios.
Authors: Juseon-Do, Jingun Kwon, Hidetaka Kamigaito, Manabu Okumura
Abstract: Extractive summarization can produce faithful summaries but often requires additional constraints such as a desired summary length. Traditional sentence compression models do not typically consider the constraints because of their restricted model abilities, which require model modifications for coping with them. To bridge this gap, we propose Instruction-based Compression (InstructCMP), an approach to the sentence compression task that can consider the length constraint through instructions by leveraging the zero-shot task-solving abilities of Large Language Models (LLMs). For this purpose, we created new evaluation datasets by transforming traditional sentence compression datasets into an instruction format. By using the datasets, we first reveal that the current LLMs still face challenges in accurately controlling the length for a compressed text. To address this issue, we propose an approach named "length priming," that incorporates additional length information into the instructions without external resources. While the length priming effectively works in a zero-shot setting, a training dataset with the instructions would further improve the ability of length control. Thus, we additionally created a training dataset in an instruction format to fine-tune the model on it. Experimental results and analysis show that applying the length priming significantly improves performances of InstructCMP in both zero-shot and fine-tuning settings without the need of any model modifications.
Authors: Shahriar Golchin, Nikhil Garuda, Christopher Impey, Matthew Wenger
Abstract: Massive open online courses (MOOCs) offer free education globally to anyone with a computer and internet access. Despite this democratization of learning, the massive enrollment in these courses makes it impractical for one instructor to assess every student's writing assignment. As a result, peer grading, often guided by a straightforward rubric, is the method of choice. While convenient, peer grading often falls short in terms of reliability and validity. In this study, we explore the feasibility of using large language models (LLMs) to replace peer grading in MOOCs. Specifically, we use two LLMs, GPT-4 and GPT-3.5, across three MOOCs: Introductory Astronomy, Astrobiology, and the History and Philosophy of Astronomy. To instruct LLMs, we use three different prompts based on the zero-shot chain-of-thought (ZCoT) prompting technique: (1) ZCoT with instructor-provided correct answers, (2) ZCoT with both instructor-provided correct answers and rubrics, and (3) ZCoT with instructor-provided correct answers and LLM-generated rubrics. Tested on 18 settings, our results show that ZCoT, when augmented with instructor-provided correct answers and rubrics, produces grades that are more aligned with those assigned by instructors compared to peer grading. Finally, our findings indicate a promising potential for automated grading systems in MOOCs, especially in subjects with well-defined rubrics, to improve the learning experience for millions of online learners worldwide.
Authors: Armando Zhu, Jiabei Liu, Keqin Li, Shuying Dai, Bo Hong, Peng Zhao, Changsong Wei
Abstract: Out-of-distribution (OOD) detection is crucial for deploying robust machine learning models, especially in areas where security is critical. However, traditional OOD detection methods often fail to capture complex data distributions from large scale date. In this paper, we present a novel approach for OOD detection that leverages the generative ability of diffusion models and the powerful feature extraction capabilities of CLIP. By using these features as conditional inputs to a diffusion model, we can reconstruct the images after encoding them with CLIP. The difference between the original and reconstructed images is used as a signal for OOD identification. The practicality and scalability of our method is increased by the fact that it does not require class-specific labeled ID data, as is the case with many other methods. Extensive experiments on several benchmark datasets demonstrates the robustness and effectiveness of our method, which have significantly improved the detection accuracy.
Authors: Harsh Nishant Lalai, Aashish Anantha Ramakrishnan, Raj Sanjay Shah, Dongwon Lee
Abstract: With the rapid growth of Large Language Models (LLMs), safeguarding textual content against unauthorized use is crucial. Text watermarking offers a vital solution, protecting both - LLM-generated and plain text sources. This paper presents a unified overview of different perspectives behind designing watermarking techniques, through a comprehensive survey of the research literature. Our work has two key advantages, (1) we analyze research based on the specific intentions behind different watermarking techniques, evaluation datasets used, watermarking addition, and removal methods to construct a cohesive taxonomy. (2) We highlight the gaps and open challenges in text watermarking to promote research in protecting text authorship. This extensive coverage and detailed analysis sets our work apart, offering valuable insights into the evolving landscape of text watermarking in language models.
Authors: Amit Das, Zheng Zhang, Fatemeh Jamshidi, Vinija Jain, Aman Chadha, Nilanjana Raychawdhary, Mary Sandage, Lauramarie Pope, Gerry Dozier, Cheryl Seals
Abstract: Data annotation, the practice of assigning descriptive labels to raw data, is pivotal in optimizing the performance of machine learning models. However, it is a resource-intensive process susceptible to biases introduced by annotators. The emergence of sophisticated Large Language Models (LLMs), like ChatGPT presents a unique opportunity to modernize and streamline this complex procedure. While existing research extensively evaluates the efficacy of LLMs, as annotators, this paper delves into the biases present in LLMs, specifically GPT 3.5 and GPT 4o when annotating hate speech data. Our research contributes to understanding biases in four key categories: gender, race, religion, and disability. Specifically targeting highly vulnerable groups within these categories, we analyze annotator biases. Furthermore, we conduct a comprehensive examination of potential factors contributing to these biases by scrutinizing the annotated data. We introduce our custom hate speech detection dataset, HateSpeechCorpus, to conduct this research. Additionally, we perform the same experiments on the ETHOS (Mollas et al., 2022) dataset also for comparative analysis. This paper serves as a crucial resource, guiding researchers and practitioners in harnessing the potential of LLMs for dataannotation, thereby fostering advancements in this critical field. The HateSpeechCorpus dataset is available here: https://github.com/AmitDasRup123/HateSpeechCorpus
Authors: Eden Saig, Ohad Einav, Inbal Talgam-Cohen
Abstract: While the success of large language models (LLMs) increases demand for machine-generated text, current pay-per-token pricing schemes create a misalignment of incentives known in economics as moral hazard: Text-generating agents have strong incentive to cut costs by preferring a cheaper model over the cutting-edge one, and this can be done "behind the scenes" since the agent performs inference internally. In this work, we approach this issue from an economic perspective, by proposing a pay-for-performance, contract-based framework for incentivizing quality. We study a principal-agent game where the agent generates text using costly inference, and the contract determines the principal's payment for the text according to an automated quality evaluation. Since standard contract theory is inapplicable when internal inference costs are unknown, we introduce cost-robust contracts. As our main theoretical contribution, we characterize optimal cost-robust contracts through a direct correspondence to optimal composite hypothesis tests from statistics, generalizing a result of Saig et al. (NeurIPS'23). We evaluate our framework empirically by deriving contracts for a range of objectives and LLM evaluation benchmarks, and find that cost-robust contracts sacrifice only a marginal increase in objective value compared to their cost-aware counterparts.
Authors: Yushi Sun, Hao Xin, Kai Sun, Yifan Ethan Xu, Xiao Yang, Xin Luna Dong, Nan Tang, Lei Chen
Abstract: Large language models (LLMs) demonstrate an impressive ability to internalize knowledge and answer natural language questions. Although previous studies validate that LLMs perform well on general knowledge while presenting poor performance on long-tail nuanced knowledge, the community is still doubtful about whether the traditional knowledge graphs should be replaced by LLMs. In this paper, we ask if the schema of knowledge graph (i.e., taxonomy) is made obsolete by LLMs. Intuitively, LLMs should perform well on common taxonomies and at taxonomy levels that are common to people. Unfortunately, there lacks a comprehensive benchmark that evaluates the LLMs over a wide range of taxonomies from common to specialized domains and at levels from root to leaf so that we can draw a confident conclusion. To narrow the research gap, we constructed a novel taxonomy hierarchical structure discovery benchmark named TaxoGlimpse to evaluate the performance of LLMs over taxonomies. TaxoGlimpse covers ten representative taxonomies from common to specialized domains with in-depth experiments of different levels of entities in this taxonomy from root to leaf. Our comprehensive experiments of eighteen state-of-the-art LLMs under three prompting settings validate that LLMs can still not well capture the knowledge of specialized taxonomies and leaf-level entities.
Authors: Weizhe Chen, Sven Koenig, Bistra Dilkina
Abstract: In this past year, large language models (LLMs) have had remarkable success in domains outside the traditional natural language processing, and people are starting to explore the usage of LLMs in more general and close to application domains like code generation, travel planning, and robot controls. Connecting these LLMs with great capacity and external tools, people are building the so-called LLM agents, which are supposed to help people do all kinds of work in everyday life. In all these domains, the prompt to the LLMs has been shown to make a big difference in what the LLM would generate and thus affect the performance of the LLM agents. Therefore, automatic prompt engineering has become an important question for many researchers and users of LLMs. In this paper, we propose a novel method, \textsc{RePrompt}, which does "gradient descent" to optimize the step-by-step instructions in the prompt of the LLM agents based on the chat history obtained from interactions with LLM agents. By optimizing the prompt, the LLM will learn how to plan in specific domains. We have used experiments in PDDL generation and travel planning to show that our method could generally improve the performance for different reasoning tasks when using the updated prompt as the initial prompt.
Authors: Kellie Yu Hui Sim, Kohleen Tijing Fortuno, Kenny Tsu Wei Choo
Abstract: Providing timely support and intervention is crucial in mental health settings. As the need to engage youth comfortable with texting increases, mental health providers are exploring and adopting text-based media such as chatbots, community-based forums, online therapies with licensed professionals, and helplines operated by trained responders. To support these text-based media for mental health--particularly for crisis care--we are developing a system to perform passive emotion-sensing using a combination of keystroke dynamics and sentiment analysis. Our early studies of this system posit that the analysis of short text messages and keyboard typing patterns can provide emotion information that may be used to support both clients and responders. We use our preliminary findings to discuss the way forward for applying AI to support mental health providers in providing better care.
Authors: Chunming He, Yuqi Shen, Chengyu Fang, Fengyang Xiao, Longxiang Tang, Yulun Zhang, Wangmeng Zuo, Zhenhua Guo, Xiu Li
Abstract: Deep generative models have garnered significant attention in low-level vision tasks due to their generative capabilities. Among them, diffusion model-based solutions, characterized by a forward diffusion process and a reverse denoising process, have emerged as widely acclaimed for their ability to produce samples of superior quality and diversity. This ensures the generation of visually compelling results with intricate texture information. Despite their remarkable success, a noticeable gap exists in a comprehensive survey that amalgamates these pioneering diffusion model-based works and organizes the corresponding threads. This paper proposes the comprehensive review of diffusion model-based techniques. We present three generic diffusion modeling frameworks and explore their correlations with other deep generative models, establishing the theoretical foundation. Following this, we introduce a multi-perspective categorization of diffusion models, considering both the underlying framework and the target task. Additionally, we summarize extended diffusion models applied in other tasks, including medical, remote sensing, and video scenarios. Moreover, we provide an overview of commonly used benchmarks and evaluation metrics. We conduct a thorough evaluation, encompassing both performance and efficiency, of diffusion model-based techniques in three prominent tasks. Finally, we elucidate the limitations of current diffusion models and propose seven intriguing directions for future research. This comprehensive examination aims to facilitate a profound understanding of the landscape surrounding denoising diffusion models in the context of low-level vision tasks. A curated list of diffusion model-based techniques in over 20 low-level vision tasks can be found at https://github.com/ChunmingHe/awesome-diffusion-models-in-low-level-vision.
URLs: https://github.com/ChunmingHe/awesome-diffusion-models-in-low-level-vision.
Authors: Xueying Du, Geng Zheng, Kaixin Wang, Jiayi Feng, Wentai Deng, Mingwei Liu, Xin Peng, Tao Ma, Yiling Lou
Abstract: Vulnerability detection is essential for software quality assurance. In recent years, deep learning models (especially large language models) have shown promise in vulnerability detection. In this work, we propose a novel LLM-based vulnerability detection technique Vul-RAG, which leverages knowledge-level retrieval-augmented generation (RAG) framework to detect vulnerability for the given code in three phases. First, Vul-RAG constructs a vulnerability knowledge base by extracting multi-dimension knowledge via LLMs from existing CVE instances; second, for a given code snippet, Vul-RAG} retrieves the relevant vulnerability knowledge from the constructed knowledge base based on functional semantics; third, Vul-RAG leverages LLMs to check the vulnerability of the given code snippet by reasoning the presence of vulnerability causes and fixing solutions of the retrieved vulnerability knowledge. Our evaluation of Vul-RAG on our constructed benchmark PairVul shows that Vul-RAG substantially outperforms all baselines by 12.96\%/110\% relative improvement in accuracy/pairwise-accuracy. In addition, our user study shows that the vulnerability knowledge generated by Vul-RAG can serve as high-quality explanations which can improve the manual detection accuracy from 0.60 to 0.77.
Authors: Tian Liu, Huixin Zhang, Shubham Parashar, Shu Kong
Abstract: Few-shot recognition aims to train a classification model with only a few labeled examples of pre-defined concepts, where annotation can be costly in a downstream task. In another related research area, zero-shot recognition, which assumes no access to any downstream-task data, has been greatly advanced by using pretrained Vision-Language Models (VLMs). In this area, retrieval-augmented learning (RAL) effectively boosts zero-shot accuracy by retrieving and learning from external data relevant to downstream concepts. Motivated by these advancements, our work explores RAL for few-shot recognition. While seemingly straightforward despite being under-explored in the literature (till now!), we present novel challenges and opportunities for applying RAL for few-shot recognition. First, perhaps surprisingly, simply finetuning the VLM on a large amount of retrieved data barely surpasses state-of-the-art zero-shot methods due to the imbalanced distribution of retrieved data and its domain gaps compared to few-shot annotated data. Second, finetuning a VLM on few-shot examples alone significantly outperforms prior methods, and finetuning on the mix of retrieved and few-shot data yields even better results. Third, to mitigate the imbalanced distribution and domain gap issue, we propose Stage-Wise Augmented fineTuning (SWAT) method, which involves end-to-end finetuning on mixed data for the first stage and retraining the classifier solely on the few-shot data in the second stage. Extensive experiments show that SWAT achieves the best performance on standard benchmark datasets, resoundingly outperforming prior works by ~10% in accuracy. Code is available at https://github.com/tian1327/SWAT.
Authors: Guohao Sun, Haoyi Zhang
Abstract: Sequential recommendation (SR) tasks enhance recommendation accuracy by capturing the connection between users' past interactions and their changing preferences. Conventional models often focus solely on capturing sequential patterns within the training data, neglecting the broader context and semantic information embedded in item titles from external sources. This limits their predictive power and adaptability. Recently, large language models (LLMs) have shown promise in SR tasks due to their advanced understanding capabilities and strong generalization abilities. Researchers have attempted to enhance LLMs' recommendation performance by incorporating information from SR models. However, previous approaches have encountered problems such as 1) only influencing LLMs at the result level;2) increased complexity of LLMs recommendation methods leading to reduced interpretability; 3) incomplete understanding and utilization of SR models information by LLMs. To address these problems, we proposes a novel framework, DELRec, which aims to extract knowledge from SR models and enable LLMs to easily comprehend and utilize this supplementary information for more effective sequential recommendations. DELRec consists of two main stages: 1) SR Models Pattern Distilling, focusing on extracting behavioral patterns exhibited by SR models using soft prompts through two well-designed strategies; 2) LLMs-based Sequential Recommendation, aiming to fine-tune LLMs to effectively use the distilled auxiliary information to perform SR tasks. Extensive experimental results conducted on three real datasets validate the effectiveness of the DELRec framework.
Authors: Weimin Xiong, Yifan Song, Xiutian Zhao, Wenhao Wu, Xun Wang, Ke Wang, Cheng Li, Wei Peng, Sujian Li
Abstract: Large language model agents have exhibited exceptional performance across a range of complex interactive tasks. Recent approaches have utilized tuning with expert trajectories to enhance agent performance, yet they primarily concentrate on outcome rewards, which may lead to errors or suboptimal actions due to the absence of process supervision signals. In this paper, we introduce the Iterative step-level Process Refinement (IPR) framework, which provides detailed step-by-step guidance to enhance agent training. Specifically, we adopt the Monte Carlo method to estimate step-level rewards. During each iteration, the agent explores along the expert trajectory and generates new actions. These actions are then evaluated against the corresponding step of expert trajectory using step-level rewards. Such comparison helps identify discrepancies, yielding contrastive action pairs that serve as training data for the agent. Our experiments on three complex agent tasks demonstrate that our framework outperforms a variety of strong baselines. Moreover, our analytical findings highlight the effectiveness of IPR in augmenting action efficiency and its applicability to diverse models.
Authors: Yilun Du, Jiayuan Mao, Joshua B. Tenenbaum
Abstract: We introduce iterative reasoning through energy diffusion (IRED), a novel framework for learning to reason for a variety of tasks by formulating reasoning and decision-making problems with energy-based optimization. IRED learns energy functions to represent the constraints between input conditions and desired outputs. After training, IRED adapts the number of optimization steps during inference based on problem difficulty, enabling it to solve problems outside its training distribution -- such as more complex Sudoku puzzles, matrix completion with large value magnitudes, and pathfinding in larger graphs. Key to our method's success is two novel techniques: learning a sequence of annealed energy landscapes for easier inference and a combination of score function and energy landscape supervision for faster and more stable training. Our experiments show that IRED outperforms existing methods in continuous-space reasoning, discrete-space reasoning, and planning tasks, particularly in more challenging scenarios. Code and visualizations at https://energy-based-model.github.io/ired/
Authors: Rong Bao, Rui Zheng, Shihan Dou, Xiao Wang, Enyu Zhou, Bo Wang, Qi Zhang, Liang Ding, Dacheng Tao
Abstract: In aligning large language models (LLMs), utilizing feedback from existing advanced AI rather than humans is an important method to scale supervisory signals. However, it is highly challenging for AI to understand human intentions and societal values, and provide accurate preference feedback based on these. Current AI feedback methods rely on powerful LLMs, carefully designed specific principles to describe human intentions, and are easily influenced by position bias. To address these issues, we propose a self-reference-based AI feedback framework that enables a 13B Llama2-Chat to provide high-quality feedback under simple and general principles such as ``best for humanity``. Specifically, we allow the AI to first respond to the user's instructions, then generate criticism of other answers based on its own response as a reference, and finally determine which answer better fits human preferences according to the criticism. Additionally, we use a self-consistency method to further reduce the impact of position bias, and employ semantic perplexity to calculate the preference strength differences between different answers. Experimental results show that our method enables 13B and 70B Llama2-Chat annotators to provide high-quality preference feedback, and the policy models trained based on these preference data achieve significant advantages in benchmark datasets through reinforcement learning.
Authors: Scott Barnett, Zac Brannelly, Stefanus Kurniawan, Sheng Wong
Abstract: Large Language Models (LLMs) have the unique capability to understand and generate human-like text from input queries. When fine-tuned, these models show enhanced performance on domain-specific queries. OpenAI highlights the process of fine-tuning, stating: "To fine-tune a model, you are required to provide at least 10 examples. We typically see clear improvements from fine-tuning on 50 to 100 training examples, but the right number varies greatly based on the exact use case." This study extends this concept to the integration of LLMs within Retrieval-Augmented Generation (RAG) pipelines, which aim to improve accuracy and relevance by leveraging external corpus data for information retrieval. However, RAG's promise of delivering optimal responses often falls short in complex query scenarios. This study aims to specifically examine the effects of fine-tuning LLMs on their ability to extract and integrate contextual data to enhance the performance of RAG systems across multiple domains. We evaluate the impact of fine-tuning on the LLMs' capacity for data extraction and contextual understanding by comparing the accuracy and completeness of fine-tuned models against baseline performances across datasets from multiple domains. Our findings indicate that fine-tuning resulted in a decline in performance compared to the baseline models, contrary to the improvements observed in standalone LLM applications as suggested by OpenAI. This study highlights the need for vigorous investigation and validation of fine-tuned models for domain-specific tasks.
Authors: Miguel Ortega-Mart\'in, \'Oscar Garc\'ia-Sierra, Alfonso Ardoiz, Juan Carlos Armenteros, Ignacio Garrido, Jorge \'Alvarez, Camilo Torr\'on, I\~nigo Galdeano, Ignacio Arranz, Oleg Vorontsov, Adri\'an Alonso
Abstract: We present the "Spanish Built Factual Freectianary 2.0" (Spanish-BFF-2) as the second iteration of an AI-generated Spanish dictionary. Previously, we developed the inaugural version of this unique free dictionary employing GPT-3. In this study, we aim to improve the dictionary by using GPT-4-turbo instead. Furthermore, we explore improvements made to the initial version and compare the performance of both models.
Authors: Silvery D. Fu, Xuewei Chen
Abstract: Schema evolution is critical in managing database systems to ensure compatibility across different data versions. A schema registry typically addresses the challenges of schema evolution in real-time data streaming by managing, validating, and ensuring schema compatibility. However, current schema registries struggle with complex syntactic alterations like field renaming or type changes, which often require significant manual intervention and can disrupt service. To enhance the flexibility of schema evolution, we propose the use of generalized schema evolution (GSE) facilitated by a compound AI system. This system employs Large Language Models (LLMs) to interpret the semantics of schema changes, supporting a broader range of syntactic modifications without interrupting data streams. Our approach includes developing a task-specific language, Schema Transformation Language (STL), to generate schema mappings as an intermediate representation (IR), simplifying the integration of schema changes across different data processing platforms. Initial results indicate that this approach can improve schema mapping accuracy and efficiency, demonstrating the potential of GSE in practical applications.
Authors: Hengyi Wang, Haizhou Shi, Shiwei Tan, Weiyi Qin, Wenyuan Wang, Tunyu Zhang, Akshay Nambi, Tanuja Ganu, Hao Wang
Abstract: Multimodal Large Language Models (MLLMs) have shown significant promise in various applications, leading to broad interest from researchers and practitioners alike. However, a comprehensive evaluation of their long-context capabilities remains underexplored. To address these gaps, we introduce the MultiModal Needle-in-a-haystack (MMNeedle) benchmark, specifically designed to assess the long-context capabilities of MLLMs. Besides multi-image input, we employ image stitching to further increase the input context length, and develop a protocol to automatically generate labels for sub-image level retrieval. Essentially, MMNeedle evaluates MLLMs by stress-testing their capability to locate a target sub-image (needle) within a set of images (haystack) based on textual instructions and descriptions of image contents. This setup necessitates an advanced understanding of extensive visual contexts and effective information retrieval within long-context image inputs. With this benchmark, we evaluate state-of-the-art MLLMs, encompassing both API-based and open-source models. The findings reveal that GPT-4o consistently surpasses other models in long-context scenarios, but suffers from hallucination problems in negative samples, i.e., when needles are not in the haystacks. Our comprehensive long-context evaluation of MLLMs also sheds lights on the considerable performance gap between API-based and open-source models. All the code, data, and instructions required to reproduce the main results are available at https://github.com/Wang-ML-Lab/multimodal-needle-in-a-haystack.
URLs: https://github.com/Wang-ML-Lab/multimodal-needle-in-a-haystack.
Authors: Ruaridh Mon-Williams, Gen Li, Ran Long, Wenqian Du, Chris Lucas
Abstract: Completing complex tasks in unpredictable settings like home kitchens challenges robotic systems. These challenges include interpreting high-level human commands, such as "make me a hot beverage" and performing actions like pouring a precise amount of water into a moving mug. To address these challenges, we present a novel framework that combines Large Language Models (LLMs), a curated Knowledge Base, and Integrated Force and Visual Feedback (IFVF). Our approach interprets abstract instructions, performs long-horizon tasks, and handles various uncertainties. It utilises GPT-4 to analyse the user's query and surroundings, then generates code that accesses a curated database of functions during execution. It translates abstract instructions into actionable steps. Each step involves generating custom code by employing retrieval-augmented generalisation to pull IFVF-relevant examples from the Knowledge Base. IFVF allows the robot to respond to noise and disturbances during execution. We use coffee making and plate decoration to demonstrate our approach, including components ranging from pouring to drawer opening, each benefiting from distinct feedback types and methods. This novel advancement marks significant progress toward a scalable, efficient robotic framework for completing complex tasks in uncertain environments. Our findings are illustrated in an accompanying video and supported by an open-source GitHub repository (released upon paper acceptance).
Authors: Siu Lung Ng, Hirad Baradaran Rezaei, Fethi Rabhi
Abstract: This paper presents the SLEGO (Software-Lego) system, a collaborative analytics platform that bridges the gap between experienced developers and novice users using a cloud-based platform with modular, reusable microservices. These microservices enable developers to share their analytical tools and workflows, while a simple graphical user interface (GUI) allows novice users to build comprehensive analytics pipelines without programming skills. Supported by a knowledge base and a Large Language Model (LLM) powered recommendation system, SLEGO enhances the selection and integration of microservices, increasing the efficiency of analytics pipeline construction. Case studies in finance and machine learning illustrate how SLEGO promotes the sharing and assembly of modular microservices, significantly improving resource reusability and team collaboration. The results highlight SLEGO's role in democratizing data analytics by integrating modular design, knowledge bases, and recommendation systems, fostering a more inclusive and efficient analytical environment.
Authors: Siyan Zhao, Tung Nguyen, Aditya Grover
Abstract: In-context learning is a key paradigm in large language models (LLMs) that enables them to generalize to new tasks and domains by simply prompting these models with a few exemplars without explicit parameter updates. Many attempts have been made to understand in-context learning in LLMs as a function of model scale, pretraining data, and other factors. In this work, we propose a new mechanism to probe and understand in-context learning from the lens of decision boundaries for in-context binary classification. Decision boundaries are straightforward to visualize and provide important information about the qualitative behavior of the inductive biases of standard classifiers. To our surprise, we find that the decision boundaries learned by current LLMs in simple binary classification tasks are often irregular and non-smooth, regardless of linear separability in the underlying task. This paper investigates the factors influencing these decision boundaries and explores methods to enhance their generalizability. We assess various approaches, including training-free and fine-tuning methods for LLMs, the impact of model architecture, and the effectiveness of active prompting techniques for smoothing decision boundaries in a data-efficient manner. Our findings provide a deeper understanding of in-context learning dynamics and offer practical improvements for enhancing robustness and generalizability of in-context learning.
Authors: Qiao Sun, Liujia Yang, Minghao Ma, Nanyang Ye, Qinying Gu
Abstract: Aspect Sentiment Triplet Extraction (ASTE) aims to co-extract the sentiment triplets in a given corpus. Existing approaches within the pretraining-finetuning paradigm tend to either meticulously craft complex tagging schemes and classification heads, or incorporate external semantic augmentation to enhance performance. In this study, we, for the first time, re-evaluate the redundancy in tagging schemes and the internal enhancement in pretrained representations. We propose a method to improve and utilize pretrained representations by integrating a minimalist tagging scheme and a novel token-level contrastive learning strategy. The proposed approach demonstrates comparable or superior performance compared to state-of-the-art techniques while featuring a more compact design and reduced computational overhead. Additionally, we are the first to formally evaluate GPT-4's performance in few-shot learning and Chain-of-Thought scenarios for this task. The results demonstrate that the pretraining-finetuning paradigm remains highly effective even in the era of large language models.
Authors: Aldan Creo, Shushanta Pudasaini
Abstract: The generation of text that is increasingly human-like has been enabled by the advent of large language models (LLMs). As the detection of AI-generated content holds significant importance in the fight against issues such as misinformation and academic cheating, numerous studies have been conducted to develop reliable LLM detectors. While promising results have been demonstrated by such detectors on test data, recent research has revealed that they can be circumvented by employing different techniques. In this article, homoglyph-based ($a \rightarrow {\alpha}$) attacks that can be used to circumvent existing LLM detectors are presented. The efficacy of the attacks is illustrated by analizing how homoglyphs shift the tokenization of the text, and thus its token loglikelihoods. A comprehensive evaluation is conducted to assess the effectiveness of homoglyphs on state-of-the-art LLM detectors, including Binoculars, DetectGPT, OpenAI's detector, and watermarking techniques, on five different datasets. A significant reduction in the efficiency of all the studied configurations of detectors and datasets, down to an accuracy of 0.5 (random guessing), is demonstrated by the proposed approach. The results show that homoglyph-based attacks can effectively evade existing LLM detectors, and the implications of these findings are discussed along with possible defenses against such attacks.
Authors: Michelle Li, Michael Dennis
Abstract: Cooperative Multi-Agent Reinforcement Learning (MARL) algorithms, trained only to optimize task reward, can lead to a concentration of power where the failure or adversarial intent of a single agent could decimate the reward of every agent in the system. In the context of teams of people, it is often useful to explicitly consider how power is distributed to ensure no person becomes a single point of failure. Here, we argue that explicitly regularizing the concentration of power in cooperative RL systems can result in systems which are more robust to single agent failure, adversarial attacks, and incentive changes of co-players. To this end, we define a practical pairwise measure of power that captures the ability of any co-player to influence the ego agent's reward, and then propose a power-regularized objective which balances task reward and power concentration. Given this new objective, we show that there always exists an equilibrium where every agent is playing a power-regularized best-response balancing power and task reward. Moreover, we present two algorithms for training agents towards this power-regularized objective: Sample Based Power Regularization (SBPR), which injects adversarial data during training; and Power Regularization via Intrinsic Motivation (PRIM), which adds an intrinsic motivation to regulate power to the training objective. Our experiments demonstrate that both algorithms successfully balance task reward and power, leading to lower power behavior than the baseline of task-only reward and avoid catastrophic events in case an agent in the system goes off-policy.
Authors: Bangzheng Li, Ben Zhou, Xingyu Fu, Fei Wang, Dan Roth, Muhao Chen
Abstract: Language models have shown impressive in-context-learning capabilities, which allow them to benefit from input prompts and perform better on downstream end tasks. Existing works investigate the mechanisms behind this observation, and propose label-agnostic prompt metrics that can better estimate end-task performances. One popular approach is using perplexity as a way to measure models' familiarity with the prompt. While showing consistent improvements on in-domain tasks, we found that familiarity metrics such as perplexity cannot accurately estimate performance in complicated situations such as task or domain transferring scenarios. In this work, we propose a revised measure called FamiCom, providing a more comprehensive measure for task-agnostic performance estimation. Specifically, FamiCom combines familiarity with \textit{complexity} -- the inherent difficulty of end tasks, which is an important factor missing from current metrics. Experiments show that FamiCom strongly correlates with end-task performances, producing a 0.85 Spearman's correlation, versus 0.43 of familiarity-only ones'. We further apply FamiCom to automatic prompt and demonstration selection, and outperform existing methods and baselines by more than 7.0% in accuracy.
Authors: Jinhyeok Choi, Heehyeon Kim, Minhyeong An, Joyce Jiyoung Whang
Abstract: Spatio-temporal graph (STG) forecasting is a critical task with extensive applications in the real world, including traffic and weather forecasting. Although several recent methods have been proposed to model complex dynamics in STGs, addressing long-range spatio-temporal dependencies remains a significant challenge, leading to limited performance gains. Inspired by a recently proposed state space model named Mamba, which has shown remarkable capability of capturing long-range dependency, we propose a new STG forecasting framework named SpoT-Mamba. SpoT-Mamba generates node embeddings by scanning various node-specific walk sequences. Based on the node embeddings, it conducts temporal scans to capture long-range spatio-temporal dependencies. Experimental results on the real-world traffic forecasting dataset demonstrate the effectiveness of SpoT-Mamba.
Authors: Do Hyun Lee, Yoonah Song, Hong Kook Kim
Abstract: We present a prompt-engineering-based text-augmentation approach applied to a language-queried audio source separation (LASS) task. To enhance the performance of LASS, the proposed approach utilizes large language models (LLMs) to generate multiple captions corresponding to each sentence of the training dataset. To this end, we first perform experiments to identify the most effective prompts for caption augmentation with a smaller number of captions. A LASS model trained with these augmented captions demonstrates improved performance on the DCASE 2024 Task 9 validation set compared to that trained without augmentation. This study highlights the effectiveness of LLM-based caption augmentation in advancing language-queried audio source separation.
Authors: Silvery D. Fu, David Wang, Wen Zhang, Kathleen Ge
Abstract: Entity matching (EM), the task of identifying whether two descriptions refer to the same entity, is essential in data management. Traditional methods have evolved from rule-based to AI-driven approaches, yet current techniques using large language models (LLMs) often fall short due to their reliance on static knowledge and rigid, predefined prompts. In this paper, we introduce Libem, a compound AI system designed to address these limitations by incorporating a flexible, tool-oriented approach. Libem supports entity matching through dynamic tool use, self-refinement, and optimization, allowing it to adapt and refine its process based on the dataset and performance metrics. Unlike traditional solo-AI EM systems, which often suffer from a lack of modularity that hinders iterative design improvements and system optimization, Libem offers a composable and reusable toolchain. This approach aims to contribute to ongoing discussions and developments in AI-driven data management.
Authors: Niu Guanchen
Abstract: Talking head generation based on the neural radiation fields model has shown promising visual effects. However, the slow rendering speed of NeRF seriously limits its application, due to the burdensome calculation process over hundreds of sampled points to synthesize one pixel. In this work, a novel Neural Light Dynamic Fields model is proposed aiming to achieve generating high quality 3D talking face with significant speedup. The NLDF represents light fields based on light segments, and a deep network is used to learn the entire light beam's information at once. In learning the knowledge distillation is applied and the NeRF based synthesized result is used to guide the correct coloration of light segments in NLDF. Furthermore, a novel active pool training strategy is proposed to focus on high frequency movements, particularly on the speaker mouth and eyebrows. The propose method effectively represents the facial light dynamics in 3D talking video generation, and it achieves approximately 30 times faster speed compared to state of the art NeRF based method, with comparable generation visual quality.
Authors: Sungwon Park, Sungwon Han, Meeyoung Cha
Abstract: The spread of fake news negatively impacts individuals and is regarded as a significant social challenge that needs to be addressed. A number of algorithmic and insightful features have been identified for detecting fake news. However, with the recent LLMs and their advanced generation capabilities, many of the detectable features (e.g., style-conversion attacks) can be altered, making it more challenging to distinguish from real news. This study proposes adversarial style augmentation, AdStyle, to train a fake news detector that remains robust against various style-conversion attacks. Our model's key mechanism is the careful use of LLMs to automatically generate a diverse yet coherent range of style-conversion attack prompts. This improves the generation of prompts that are particularly difficult for the detector to handle. Experiments show that our augmentation strategy improves robustness and detection performance when tested on fake news benchmark datasets.
Authors: Wanli Yang, Fei Sun, Jiajun Tan, Xinyu Ma, Du Su, Dawei Yin, Huawei Shen
Abstract: Despite significant progress in model editing methods, their application in real-world scenarios remains challenging as they often cause large language models (LLMs) to collapse. Among them, ROME is particularly concerning, as it could disrupt LLMs with only a single edit. In this paper, we study the root causes of such collapse. Through extensive analysis, we identify two primary factors that contribute to the collapse: i) inconsistent handling of prefixed and unprefixed keys in the parameter update equation may result in very small denominators, causing excessively large parameter updates; ii) the subject of collapse cases is usually the first token, whose unprefixed key distribution significantly differs from the prefixed key distribution in autoregressive transformers, causing the aforementioned issue to materialize. To validate our analysis, we propose a simple yet effective approach: uniformly using prefixed keys during editing phase and adding prefixes during the testing phase. The experimental results show that the proposed solution can prevent model collapse while maintaining the effectiveness of the edits.
Authors: Yanxin Xi, Yu Liu, Zhicheng Liu, Sasu Tarkoma, Pan Hui, Yong Li
Abstract: The Sustainable Development Goals (SDGs) aim to resolve societal challenges, such as eradicating poverty and improving the lives of vulnerable populations in impoverished areas. Those areas rely on road infrastructure construction to promote accessibility and economic development. Although publicly available data like OpenStreetMap is available to monitor road status, data completeness in impoverished areas is limited. Meanwhile, the development of deep learning techniques and satellite imagery shows excellent potential for earth monitoring. To tackle the challenge of road network assessment in impoverished areas, we develop a systematic road extraction framework combining an encoder-decoder architecture and morphological operations on satellite imagery, offering an integrated workflow for interdisciplinary researchers. Extensive experiments of road network extraction on real-world data in impoverished regions achieve a 42.7% enhancement in the F1-score over the baseline methods and reconstruct about 80% of the actual roads. We also propose a comprehensive road network dataset covering approximately 794,178 km2 area and 17.048 million people in 382 impoverished counties in China. The generated dataset is further utilized to conduct socioeconomic analysis in impoverished counties, showing that road network construction positively impacts regional economic development. The technical appendix, code, and generated dataset can be found at https://github.com/tsinghua-fib-lab/Road_network_extraction_impoverished_counties.
URLs: https://github.com/tsinghua-fib-lab/Road_network_extraction_impoverished_counties.
Authors: Hengran Zhang, Keping Bi, Jiafeng Guo, Xueqi Cheng
Abstract: Utility and topical relevance are critical measures in information retrieval (IR), reflecting system and user perspectives, respectively. While topical relevance has long been emphasized, utility is a higher standard of relevance and is more useful for facilitating downstream tasks, e.g., in Retrieval-Augmented Generation (RAG). When we incorporate utility judgments into RAG, we realize that the topical relevance, utility, and answering in RAG are closely related to the three types of relevance that Schutz discussed from a philosophical perspective. They are topical relevance, interpretational relevance, and motivational relevance, respectively. Inspired by the dynamic iterations of the three types of relevance, we propose an Iterative utiliTy judgmEnt fraMework (ITEM) to promote each step of the cycle of RAG. We conducted extensive experiments on multi-grade passage retrieval and factoid question-answering datasets (i.e., TREC DL, WebAP, and NQ). Experimental results demonstrate significant improvements in utility judgments, ranking of topical relevance, and answer generation upon representative baselines, including multiple single-shot utility judging approaches. Our code and benchmark can be found at https://anonymous.4open.science/r/ITEM-B486/.
Authors: Yunxin Li, Xinyu Chen, Baotian Hu, Longyue Wang, Haoyuan Shi, Min Zhang
Abstract: Despite significant breakthroughs in video analysis driven by the rapid development of large multimodal models (LMMs), there remains a lack of a versatile evaluation benchmark to comprehensively assess these models' performance in video understanding and reasoning. To address this, we present VideoVista, a video QA benchmark that integrates challenges across diverse content categories, durations, and abilities. Specifically, VideoVista comprises 25,000 questions derived from 3,400 videos spanning 14 categories (e.g., Howto, Film, and Entertainment) with durations ranging from a few seconds to over 10 minutes. Besides, it encompasses 19 types of understanding tasks (e.g., anomaly detection, interaction understanding) and 8 reasoning tasks (e.g., logical reasoning, causal reasoning). To achieve this, we present an automatic data construction framework, leveraging powerful GPT-4o alongside advanced analysis tools (e.g., video splitting, object segmenting, and tracking). We also utilize this framework to construct training data to enhance the capabilities of video-related LMMs (Video-LMMs). Through a comprehensive and quantitative evaluation of cutting-edge models, we reveal that: 1) Video-LMMs face difficulties in fine-grained video tasks involving temporal location, object tracking, and anomaly detection; 2) Video-LMMs present inferior logical and relation reasoning abilities; 3) Open-source Video-LMMs' performance is significantly lower than GPT-4o and Gemini-1.5, lagging by 20 points. This highlights the crucial role VideoVista will play in advancing LMMs that can accurately understand videos and perform precise reasoning.
Authors: Philipp Schwarz, Oliver Schacht, Sven Klaassen, Daniel Gr\"unbaum, Sebastian Imhof, Martin Spindler
Abstract: In this paper, we present a data-driven model for estimating optimal rework policies in manufacturing systems. We consider a single production stage within a multistage, lot-based system that allows for optional rework steps. While the rework decision depends on an intermediate state of the lot and system, the final product inspection, and thus the assessment of the actual yield, is delayed until production is complete. Repair steps are applied uniformly to the lot, potentially improving some of the individual items while degrading others. The challenge is thus to balance potential yield improvement with the rework costs incurred. Given the inherently causal nature of this decision problem, we propose a causal model to estimate yield improvement. We apply methods from causal machine learning, in particular double/debiased machine learning (DML) techniques, to estimate conditional treatment effects from data and derive policies for rework decisions. We validate our decision model using real-world data from opto-electronic semiconductor manufacturing, achieving a yield improvement of 2 - 3% during the color-conversion process of white light-emitting diodes (LEDs).
Authors: Pietari Kaskela, Philipp Fischer, Timo Roman
Abstract: Given the lidar measurements from an autonomous vehicle, we can project the points and generate a sparse depth image. Depth completion aims at increasing the resolution of such a depth image by infilling and interpolating the sparse depth values. Like most existing approaches, we make use of camera images as guidance in very sparse or occluded regions. In addition, we propose a temporal algorithm that utilizes information from previous timesteps using recurrence. In this work, we show how a state-of-the-art method PENet can be modified to benefit from recurrency. Our algorithm achieves state-of-the-art results on the KITTI depth completion dataset while adding only less than one percent of additional overhead in terms of both neural network parameters and floating point operations. The accuracy is especially improved for faraway objects and regions containing a low amount of lidar depth samples. Even in regions without any ground truth (like sky and rooftops) we observe large improvements which are not captured by the existing evaluation metrics.
Authors: Ilja Siro\v{s}, Dave Singel\'ee, Bart Preneel
Abstract: This paper aims to evaluate GitHub Copilot's generated code quality based on the LeetCode problem set using a custom automated framework. We evaluate the results of Copilot for 4 programming languages: Java, C++, Python3 and Rust. We aim to evaluate Copilot's reliability in the code generation stage, the correctness of the generated code and its dependency on the programming language, problem's difficulty level and problem's topic. In addition to that, we evaluate code's time and memory efficiency and compare it to the average human results. In total, we generate solutions for 1760 problems for each programming language and evaluate all the Copilot's suggestions for each problem, resulting in over 50000 submissions to LeetCode spread over a 2-month period. We found that Copilot successfully solved most of the problems. However, Copilot was rather more successful in generating code in Java and C++ than in Python3 and Rust. Moreover, in case of Python3 Copilot proved to be rather unreliable in the code generation phase. We also discovered that Copilot's top-ranked suggestions are not always the best. In addition, we analysed how the topic of the problem impacts the correctness rate. Finally, based on statistics information from LeetCode, we can conclude that Copilot generates more efficient code than an average human.
Authors: Han Liu, Yupeng Zhang, Bingning Wang, Weipeng Chen, Xiaolin Hu
Abstract: Deep Neural Networks (DNNs) excel in various domains but face challenges in providing accurate uncertainty estimates, which are crucial for high-stakes applications. Large Language Models (LLMs) have recently emerged as powerful tools, demonstrating exceptional performance in language tasks. However, traditional calibration metrics such as Expected Calibration Error (ECE) and classwise-ECE (cw-ECE) are inadequate for LLMs due to their vast vocabularies, data complexity, and distributional focus. To address this, we propose a novel calibration concept called full calibration and introduce its corresponding metric, Full-ECE. Full-ECE evaluates the entire predicted probability distribution, offering a more accurate and robust measure of calibration for LLMs.
Authors: Zilun Zhang, Yutao Sun, Tiancheng Zhao, Leigang Sha, Ruochen Xu, Kyusong Lee, Jianwei Yin
Abstract: Humans can retain old knowledge while learning new information, but Large Language Models (LLMs) often suffer from catastrophic forgetting when post-pretrained or supervised fine-tuned (SFT) on domain-specific data. Moreover, for Multimodal Large Language Models (MLLMs) which are composed of the LLM base and visual projector (e.g. LLaVA), a significant decline in performance on language benchmarks was observed compared to their single-modality counterparts. To address these challenges, we introduce a novel model-agnostic self-decompression method, Tree Generation (TG), that decompresses knowledge within LLMs into the training corpus. This paper focuses on TG-SFT, which can synthetically generate SFT data for the instruction tuning steps. By incorporating the dumped corpus during SFT for MLLMs, we significantly reduce the forgetting problem.
Authors: Zhonghao Li, Xuming Hu, Aiwei Liu, Kening Zheng, Sirui Huang, Hui Xiong
Abstract: Large Language Models (LLMs) are limited by their parametric knowledge, leading to hallucinations in knowledge-extensive tasks. To address this, Retrieval-Augmented Generation (RAG) incorporates external document chunks to expand LLM knowledge. Furthermore, compressing information from document chunks through extraction or summarization can improve LLM performance. Nonetheless, LLMs still struggle to notice and utilize scattered key information, a problem known as the "lost-in-the-middle" syndrome. Therefore, we typically need to restructure the content for LLM to recognize the key information. We propose $\textit{Refiner}$, an end-to-end extract-and-restructure paradigm that operates in the post-retrieval process of RAG. $\textit{Refiner}$ leverages a single decoder-only LLM to adaptively extract query-relevant contents verbatim along with the necessary context, and section them based on their interconnectedness, thereby highlights information distinction, and aligns downstream LLMs with the original context effectively. Experiments show that a trained $\textit{Refiner}$ (with 7B parameters) exhibits significant gain to downstream LLM in improving answer accuracy, and outperforms other state-of-the-art advanced RAG and concurrent compressing approaches in various single-hop and multi-hop QA tasks. Notably, $\textit{Refiner}$ achieves a 80.5% tokens reduction and a 1.6-7.0% improvement margin in multi-hop tasks compared to the next best solution. $\textit{Refiner}$ is a plug-and-play solution that can be seamlessly integrated with RAG systems, facilitating its application across diverse open-source frameworks.
Authors: Han Zhou, Xingchen Wan, Yinhong Liu, Nigel Collier, Ivan Vuli\'c, Anna Korhonen
Abstract: Large language models (LLMs) have shown promising abilities as cost-effective and reference-free evaluators for assessing language generation quality. In particular, pairwise LLM evaluators, which compare two generated texts and determine the preferred one, have been employed in a wide range of applications. However, LLMs exhibit preference biases and worrying sensitivity to prompt designs. In this work, we first reveal that the predictive preference of LLMs can be highly brittle and skewed, even with semantically equivalent instructions. We find that fairer predictive preferences from LLMs consistently lead to judgments that are better aligned with humans. Motivated by this phenomenon, we propose an automatic Zero-shot Evaluation-oriented Prompt Optimization framework, ZEPO, which aims to produce fairer preference decisions and improve the alignment of LLM evaluators with human judgments. To this end, we propose a zero-shot learning objective based on the preference decision fairness. ZEPO demonstrates substantial performance improvements over state-of-the-art LLM evaluators, without requiring labeled data, on representative meta-evaluation benchmarks. Our findings underscore the critical correlation between preference fairness and human alignment, positioning ZEPO as an efficient prompt optimizer for bridging the gap between LLM evaluators and human judgments.
Authors: Siyu Yuan, Cheng Jiayang, Lin Qiu, Deqing Yang
Abstract: Analogical reasoning plays a critical role in human cognition, enabling us to understand new concepts by associating them with familiar ones. Previous research in the AI community has mainly focused on identifying and generating analogies and then examining their quality under human evaluation, which overlooks the practical application of these analogies in real-world settings. Inspired by the human education process, in this paper, we propose to investigate how analogies created by teacher language models (LMs) can assist student LMs in understanding scientific concepts, thereby aligning more closely with practical scenarios. Our results suggest that free-form analogies can indeed aid LMs in understanding concepts. Additionally, analogies generated by student LMs can improve their own performance on scientific question answering, demonstrating their capability to use analogies for self-learning new knowledge. Resources are available at https://github.com/siyuyuan/SCUA.
Authors: Daojun Liang, Haixia Zhang, Dongfeng Yuan
Abstract: Traditional regression and prediction tasks often only provide deterministic point estimates. To estimate the uncertainty or distribution information of the response variable, methods such as Bayesian inference, model ensembling, or MC Dropout are typically used. These methods either assume that the posterior distribution of samples follows a Gaussian process or require thousands of forward passes for sample generation. We propose a novel approach called DistPred for regression and forecasting tasks, which overcomes the limitations of existing methods while remaining simple and powerful. Specifically, we transform proper scoring rules that measure the discrepancy between the predicted distribution and the target distribution into a differentiable discrete form and use it as a loss function to train the model end-to-end. This allows the model to sample numerous samples in a single forward pass to estimate the potential distribution of the response variable. We have compared our method with several existing approaches on multiple datasets and achieved state-of-the-art performance. Additionally, our method significantly improves computational efficiency. For example, compared to state-of-the-art models, DistPred has a 90x faster inference speed. Experimental results can be reproduced through https://github.com/Anoise/DistPred.
Authors: Neelabh Sinha, Vinija Jain, Aman Chadha
Abstract: The rapid rise of Language Models (LMs) has expanded their use in several applications. Yet, due to constraints of model size, associated cost, or proprietary restrictions, utilizing state-of-the-art (SOTA) LLMs is not always feasible. With open, smaller LMs emerging, more applications can leverage their capabilities, but selecting the right LM can be challenging. This work conducts an in-depth experimental analysis of the semantic correctness of outputs of 10 smaller, open LMs across three aspects: task types, application domains and reasoning types, using diverse prompt styles. We demonstrate that most effective models and prompt styles vary depending on the specific requirements. Our analysis provides a comparative assessment of LMs and prompt styles using a proposed three-tier schema of aspects for their strategic selection based on use-case and other constraints. We also show that if utilized appropriately, these LMs can compete with, and sometimes outperform, SOTA LLMs like DeepSeek-v2, GPT-3.5-Turbo, and GPT-4o.
Authors: CodeGemma Team
Abstract: This paper introduces CodeGemma, a collection of specialized open code models built on top of Gemma, capable of a variety of code and natural language generation tasks. We release three model variants. CodeGemma 7B pretrained (PT) and instruction-tuned (IT) variants have remarkably resilient natural language understanding, excel in mathematical reasoning, and match code capabilities of other open models. CodeGemma 2B is a state-of-the-art code completion model designed for fast code infilling and open-ended generation in latency-sensitive settings.
Authors: Lingyun Zhang, Bin jin, Gaojian Ge, Lunhui Liu, Xuewen Shen, Mingyong Wu, Houqian Zhang, Yongneng Jiang, Shiqi Chen, Shi Pu
Abstract: Human priors play a crucial role in efficiently utilizing data in deep learning. However, with the development of large language models (LLMs), there is an increasing emphasis on scaling both model size and data volume, which often diminishes the importance of human priors in data construction. Influenced by these trends, existing Small Language Models (SLMs) mainly rely on web-scraped large-scale training data, neglecting the proper incorporation of human priors. This oversight limits the training efficiency of language models in resource-constrained settings. In this paper, we propose a principle to leverage human priors for data construction. This principle emphasizes achieving high-performance SLMs by training on a concise dataset that accommodates both semantic diversity and data quality consistency, while avoiding benchmark data leakage. Following this principle, we train an SLM named HARE-1.1B. Extensive experiments on large-scale benchmark datasets demonstrate that HARE-1.1B performs favorably against state-of-the-art SLMs, validating the effectiveness of the proposed principle. Additionally, this provides new insights into efficient language model training in resource-constrained environments from the view of human priors.
Authors: Yong Kiam Tan, Jiong Yang, Mate Soos, Magnus O. Myreen, Kuldeep S. Meel
Abstract: Approximate model counting is the task of approximating the number of solutions to an input Boolean formula. The state-of-the-art approximate model counter for formulas in conjunctive normal form (CNF), ApproxMC, provides a scalable means of obtaining model counts with probably approximately correct (PAC)-style guarantees. Nevertheless, the validity of ApproxMC's approximation relies on a careful theoretical analysis of its randomized algorithm and the correctness of its highly optimized implementation, especially the latter's stateful interactions with an incremental CNF satisfiability solver capable of natively handling parity (XOR) constraints. We present the first certification framework for approximate model counting with formally verified guarantees on the quality of its output approximation. Our approach combines: (i) a static, once-off, formal proof of the algorithm's PAC guarantee in the Isabelle/HOL proof assistant; and (ii) dynamic, per-run, verification of ApproxMC's calls to an external CNF-XOR solver using proof certificates. We detail our general approach to establish a rigorous connection between these two parts of the verification, including our blueprint for turning the formalized, randomized algorithm into a verified proof checker, and our design of proof certificates for both ApproxMC and its internal CNF-XOR solving steps. Experimentally, we show that certificate generation adds little overhead to an approximate counter implementation, and that our certificate checker is able to fully certify $84.7\%$ of instances with generated certificates when given the same time and memory limits as the counter.
Authors: Evan M. Williams, Peter Carragher, Kathleen M. Carley
Abstract: In an attempt to mimic the complex paths through which unreliable content spreads between search engines and social media, we explore the impact of incorporating both webgraph and large-scale social media contexts into website credibility classification and discovery systems. We further explore the usage of what we define as \textit{dredge words} on social media -- terms or phrases for which unreliable domains rank highly. Through comprehensive graph neural network ablations, we demonstrate that curriculum-based heterogeneous graph models that leverage context from both webgraphs and social media data outperform homogeneous and single-mode approaches. We further demonstrate that the incorporation of dredge words into our model strongly associates unreliable websites with social media and online commerce platforms. Finally, we show our heterogeneous model greatly outperforms competing systems in the top-k identification of unlabeled unreliable websites. We demonstrate the strong unreliability signals present in the diverse paths that users follow to uncover unreliable content, and we release a novel dataset of dredge words.
Authors: Keon Lee, Dong Won Kim, Jaehyeon Kim, Jaewoong Cho
Abstract: Large-scale diffusion models have shown outstanding generative abilities across multiple modalities including images, videos, and audio. However, text-to-speech (TTS) systems typically involve domain-specific modeling factors (e.g., phonemes and phoneme-level durations) to ensure precise temporal alignments between text and speech, which hinders the efficiency and scalability of diffusion models for TTS. In this work, we present an efficient and scalable Diffusion Transformer (DiT) that utilizes off-the-shelf pre-trained text and speech encoders. Our approach addresses the challenge of text-speech alignment via cross-attention mechanisms with the prediction of the total length of speech representations. To achieve this, we enhance the DiT architecture to suit TTS and improve the alignment by incorporating semantic guidance into the latent space of speech. We scale the training dataset and the model size to 82K hours and 790M parameters, respectively. Our extensive experiments demonstrate that the large-scale diffusion model for TTS without domain-specific modeling not only simplifies the training pipeline but also yields superior or comparable zero-shot performance to state-of-the-art TTS models in terms of naturalness, intelligibility, and speaker similarity. Our speech samples are available at https://ditto-tts.github.io.
Authors: Shilong Li, Ge Bai, Zhang Zhang, Ying Liu, Chenji Lu, Daichi Guo, Ruifang Liu, Yong Sun
Abstract: Predicting unseen relations that cannot be observed during the training phase is a challenging task in relation extraction. Previous works have made progress by matching the semantics between input instances and label descriptions. However, fine-grained matching often requires laborious manual annotation, and rich interactions between instances and label descriptions come with significant computational overhead. In this work, we propose an efficient multi-grained matching approach that uses virtual entity matching to reduce manual annotation cost, and fuses coarse-grained recall and fine-grained classification for rich interactions with guaranteed inference speed. Experimental results show that our approach outperforms the previous State Of The Art (SOTA) methods, and achieves a balance between inference efficiency and prediction accuracy in zero-shot relation extraction tasks. Our code is available at https://github.com/longls777/EMMA.
Authors: Alessio Devoto, Yu Zhao, Simone Scardapane, Pasquale Minervini
Abstract: The deployment of large language models (LLMs) is often hindered by the extensive memory requirements of the Key-Value (KV) cache, especially as context lengths increase. Existing approaches to reduce the KV cache size involve either fine-tuning the model to learn a compression strategy or leveraging attention scores to reduce the sequence length. We analyse the attention distributions in decoder-only Transformers-based models and observe that attention allocation patterns stay consistent across most layers. Surprisingly, we find a clear correlation between the $L_2$ and the attention scores over cached KV pairs, where a low $L_2$ of a key embedding usually leads to a high attention score during decoding. This finding indicates that the influence of a KV pair is potentially determined by the key embedding itself before being queried. Based on this observation, we compress the KV cache based on the $L_2$ of key embeddings. Our experimental results show that this simple strategy can reduce the KV cache size by 50% on language modelling and needle-in-a-haystack tasks and 90% on passkey retrieval tasks without losing accuracy.
Authors: Wenkai Yang, Shiqi Shen, Guangyao Shen, Zhi Gong, Yankai Lin
Abstract: Superalignment, where humans are weak supervisors of superhuman models, has become an important and widely discussed issue in the current era of rapid development of Large Language Models (LLMs). The recent work preliminarily studies this problem by using weak models to supervise strong models. It discovers that weakly supervised strong students can consistently outperform weak teachers towards the alignment target, leading to a weak-to-strong generalization phenomenon. However, we are concerned that behind such a promising phenomenon, whether there exists an issue of weak-to-strong deception, where strong models may deceive weak models by exhibiting well-aligned in areas known to weak models but producing misaligned behaviors in cases weak models do not know. We then take an initial step towards exploring this security issue in a specific but realistic multi-objective alignment case, where there may be some alignment targets conflicting with each other (e.g., helpfulness v.s. harmlessness). Such a conflict is likely to cause strong models to deceive weak models in one alignment dimension to gain high reward in other alignment dimension. Our experiments on both the reward modeling task and the preference optimization scenario indicate: (1) the weak-to-strong deception exists; (2) the deception phenomenon may intensify as the capability gap between weak and strong models increases. We also discuss potential solutions and find bootstrapping with an intermediate model can mitigate the deception to some extent. Our work highlights the urgent need to pay more attention to the true reliability of superalignment.
Authors: Zhipeng Qian, Pei Zhang, Baosong Yang, Kai Fan, Yiwei Ma, Derek F. Wong, Xiaoshuai Sun, Rongrong Ji
Abstract: This paper introduces AnyTrans, an all-encompassing framework for the task-Translate AnyText in the Image (TATI), which includes multilingual text translation and text fusion within images. Our framework leverages the strengths of large-scale models, such as Large Language Models (LLMs) and text-guided diffusion models, to incorporate contextual cues from both textual and visual elements during translation. The few-shot learning capability of LLMs allows for the translation of fragmented texts by considering the overall context. Meanwhile, the advanced inpainting and editing abilities of diffusion models make it possible to fuse translated text seamlessly into the original image while preserving its style and realism. Additionally, our framework can be constructed entirely using open-source models and requires no training, making it highly accessible and easily expandable. To encourage advancement in the TATI task, we have meticulously compiled a test dataset called MTIT6, which consists of multilingual text image translation data from six language pairs.
Authors: Peter Samoaa, Mehrdad Farahani, Antonio Longa, Philipp Leitner, Morteza Haghir Chehreghani
Abstract: The landscape of deep learning has vastly expanded the frontiers of source code analysis, particularly through the utilization of structural representations such as Abstract Syntax Trees (ASTs). While these methodologies have demonstrated effectiveness in classification tasks, their efficacy in regression applications, such as execution time prediction from source code, remains underexplored. This paper endeavours to decode the behaviour of tree-based neural network models in the context of such regression challenges. We extend the application of established models--tree-based Convolutional Neural Networks (CNNs), Code2Vec, and Transformer-based methods--to predict the execution time of source code by parsing it to an AST. Our comparative analysis reveals that while these models are benchmarks in code representation, they exhibit limitations when tasked with regression. To address these deficiencies, we propose a novel dual-transformer approach that operates on both source code tokens and AST representations, employing cross-attention mechanisms to enhance interpretability between the two domains. Furthermore, we explore the adaptation of Graph Neural Networks (GNNs) to this tree-based problem, theorizing the inherent compatibility due to the graphical nature of ASTs. Empirical evaluations on real-world datasets showcase that our dual-transformer model outperforms all other tree-based neural networks and the GNN-based models. Moreover, our proposed dual transformer demonstrates remarkable adaptability and robust performance across diverse datasets.
Authors: Binnur G\"orer, Fatma Ba\c{s}ak Aydemir
Abstract: Elicitation interviews are the most common requirements elicitation technique, and proficiency in conducting these interviews is crucial for requirements elicitation. Traditional training methods, typically limited to textbook learning, may not sufficiently address the practical complexities of interviewing techniques. Practical training with various interview scenarios is important for understanding how to apply theoretical knowledge in real-world contexts. However, there is a shortage of educational interview material, as creating interview scripts requires both technical expertise and creativity. To address this issue, we develop a specialized GPT agent for auto-generating interview scripts. The GPT agent is equipped with a dedicated knowledge base tailored to the guidelines and best practices of requirements elicitation interview procedures. We employ a prompt chaining approach to mitigate the output length constraint of GPT to be able to generate thorough and detailed interview scripts. This involves dividing the interview into sections and crafting distinct prompts for each, allowing for the generation of complete content for each section. The generated scripts are assessed through standard natural language generation evaluation metrics and an expert judgment study, confirming their applicability in requirements engineering training.
Authors: Enrico Russo, Maurizio Palesi, Davide Patti, Giuseppe Ascia, Vincenzo Catania
Abstract: Modular, distributed and multi-core architectures are currently considered a promising approach for scalability of quantum computing systems. The integration of multiple Quantum Processing Units necessitates classical and quantum-coherent communication, introducing challenges related to noise and quantum decoherence in quantum state transfers between cores. Optimizing communication becomes imperative, and the compilation and mapping of quantum circuits onto physical qubits must minimize state transfers while adhering to architectural constraints. The compilation process, inherently an NP-hard problem, demands extensive search times even with a small number of qubits to be solved to optimality. To address this challenge efficiently, we advocate for the utilization of heuristic mappers that can rapidly generate solutions. In this work, we propose a novel approach employing Deep Reinforcement Learning (DRL) methods to learn these heuristics for a specific multi-core architecture. Our DRL agent incorporates a Transformer encoder and Graph Neural Networks. It encodes quantum circuits using self-attention mechanisms and produce outputs through an attention-based pointer mechanism that directly signifies the probability of matching logical qubits with physical cores. This enables the selection of optimal cores for logical qubits efficiently. Experimental evaluations show that the proposed method can outperform baseline approaches in terms of reducing inter-core communications and minimizing online time-to-solution. This research contributes to the advancement of scalable quantum computing systems by introducing a novel learning-based heuristic approach for efficient quantum circuit compilation and mapping.
Authors: Zepeng Ding, Ruiyang Ke, Wenhao Huang, Guochao Jiang, Yanda Li, Deqing Yang, Yanghua Xiao, Jiaqing Liang
Abstract: Existing research on large language models (LLMs) shows that they can solve information extraction tasks through multi-step planning. However, their extraction behavior on complex sentences and tasks is unstable, emerging issues such as false positives and missing elements. We observe that decomposing complex extraction tasks and extracting them step by step can effectively improve LLMs' performance, and the extraction orders of entities significantly affect the final results of LLMs. This paper proposes a two-stage multi-step method for LLM-based information extraction and adopts the RL framework to execute the multi-step planning. We regard sequential extraction as a Markov decision process, build an LLM-based extraction environment, design a decision module to adaptively provide the optimal order for sequential entity extraction on different sentences, and utilize the DDQN algorithm to train the decision model. We also design the rewards and evaluation metrics suitable for the extraction results of LLMs. We conduct extensive experiments on multiple public datasets to demonstrate the effectiveness of our method in improving the information extraction capabilities of LLMs.
Authors: Jinyuan Fang, Zaiqiao Meng, Craig Macdonald
Abstract: Retrieval-augmented generation (RAG) offers an effective approach for addressing question answering (QA) tasks. However, the imperfections of the retrievers in RAG models often result in the retrieval of irrelevant information, which could introduce noises and degrade the performance, especially when handling multi-hop questions that require multiple steps of reasoning. To enhance the multi-hop reasoning ability of RAG models, we propose TRACE. TRACE constructs knowledge-grounded reasoning chains, which are a series of logically connected knowledge triples, to identify and integrate supporting evidence from the retrieved documents for answering questions. Specifically, TRACE employs a KG Generator to create a knowledge graph (KG) from the retrieved documents, and then uses an Autoregressive Reasoning Chain Constructor to build reasoning chains. Experimental results on three multi-hop QA datasets show that TRACE achieves an average performance improvement of up to 14.03% compared to using all the retrieved documents. Moreover, the results indicate that using reasoning chains as context, rather than the entire documents, is often sufficient to correctly answer questions.
Authors: Justin Deschenaux, Caglar Gulcehre
Abstract: The modern autoregressive Large Language Models (LLMs) have achieved outstanding performance on NLP benchmarks, and they are deployed in the real world. However, they still suffer from limitations of the autoregressive training paradigm. For example, autoregressive token generation is notably slow and can be prone to \textit{exposure bias}. The diffusion-based language models were proposed as an alternative to autoregressive generation to address some of these limitations. We evaluate the recently proposed Score Entropy Discrete Diffusion (SEDD) approach and show it is a promising alternative to autoregressive generation but it has some short-comings too. We empirically demonstrate the advantages and challenges of SEDD, and observe that SEDD generally matches autoregressive models in perplexity and on benchmarks such as HellaSwag, Arc or WinoGrande. Additionally, we show that in terms of inference latency, SEDD can be up to 4.5$\times$ more efficient than GPT-2. While SEDD allows conditioning on tokens at abitrary positions, SEDD appears slightly weaker than GPT-2 for conditional generation given short prompts. Finally, we reproduced the main results from the original SEDD paper.
Authors: Heyan Huang, Yinghao Li, Huashan Sun, Yu Bai, Yang Gao
Abstract: Recent studies have demonstrated that In-Context Learning (ICL), through the use of specific demonstrations, can align Large Language Models (LLMs) with human preferences known as In-Context Alignment (ICA), indicating that models can comprehend human instructions without requiring parameter adjustments. However, the exploration of the mechanism and applicability of ICA remains limited. In this paper, we begin by dividing the context text used in ICA into three categories: format, system prompt, and example. Through ablation experiments, we investigate the effectiveness of each part in enabling ICA to function effectively. We then examine how variants in these parts impact the model's alignment performance. Our findings indicate that the example part is crucial for enhancing the model's alignment capabilities, with changes in examples significantly affecting alignment performance. We also conduct a comprehensive evaluation of ICA's zero-shot capabilities in various alignment tasks. The results indicate that compared to parameter fine-tuning methods, ICA demonstrates superior performance in knowledge-based tasks and tool-use tasks. However, it still exhibits certain limitations in areas such as multi-turn dialogues and instruction following.
Authors: Atsuki Yamaguchi, Aline Villavicencio, Nikolaos Aletras
Abstract: Large language models (LLMs) have shown remarkable capabilities in many languages beyond English. Yet, LLMs require more inference steps when generating non-English text due to their reliance on English-centric tokenizers, vocabulary, and pre-training data, resulting in higher usage costs to non-English speakers. Vocabulary expansion with target language tokens is a widely used cross-lingual vocabulary adaptation approach to remedy this issue. Despite its effectiveness in inference speedup, the majority of previous work has focused on high-resource settings assuming access to a substantial amount of target language data to effectively initialize the embeddings of the new tokens and adapt the LLM to the target language. However, vocabulary expansion for LLMs in low-resource settings (i.e. languages and compute) has yet to be explored. In this paper, we investigate sample-efficient adaptation strategies from different angles, including target vocabulary size and initialization methods, and the amount of target data available for adaptation. Extensive experiments across typologically diverse languages, tasks and models show that simpler heuristic-based embedding initialization is more efficient and robust to changes in target vocabulary size and adaptation data in low-resource settings, outperforming a popular random initialization and a more sophisticated state-of-the-art approach that relies on external data and model.
Authors: Vaneet Aggarwal, Washim Uddin Mondal, Qinbo Bai
Abstract: Reinforcement Learning (RL) serves as a versatile framework for sequential decision-making, finding applications across diverse domains such as robotics, autonomous driving, recommendation systems, supply chain optimization, biology, mechanics, and finance. The primary objective in these applications is to maximize the average reward. Real-world scenarios often necessitate adherence to specific constraints during the learning process. This monograph focuses on the exploration of various model-based and model-free approaches for Constrained RL within the context of average reward Markov Decision Processes (MDPs). The investigation commences with an examination of model-based strategies, delving into two foundational methods - optimism in the face of uncertainty and posterior sampling. Subsequently, the discussion transitions to parametrized model-free approaches, where the primal-dual policy gradient-based algorithm is explored as a solution for constrained MDPs. The monograph provides regret guarantees and analyzes constraint violation for each of the discussed setups. For the above exploration, we assume the underlying MDP to be ergodic. Further, this monograph extends its discussion to encompass results tailored for weakly communicating MDPs, thereby broadening the scope of its findings and their relevance to a wider range of practical scenarios.
Authors: Iaroslav Okunevich, Alexandre Lombard, Tomas Krajnik, Yassine Ruichek, Zhi Yan
Abstract: Robot social navigation needs to adapt to different human factors and environmental contexts. However, since these factors and contexts are difficult to predict and cannot be exhaustively enumerated, traditional learning-based methods have difficulty in ensuring the social attributes of robots in long-term and cross-environment deployments. This letter introduces an online context learning method that aims to empower robots to adapt to new social environments online. The proposed method adopts a two-layer structure. The bottom layer is built using a deep reinforcement learning-based method to ensure the output of basic robot navigation commands. The upper layer is implemented using an online robot learning-based method to socialize the control commands suggested by the bottom layer. Experiments using a community-wide simulator show that our method outperforms the state-of-the-art ones. Experimental results in the most challenging scenarios show that our method improves the performance of the state-of-the-art by 8%. The source code of the proposed method, the data used, and the tools for the per-training step will be publicly available at https://github.com/Nedzhaken/SOCSARL-OL.
Authors: Jiangmeng Li, Bin Qin, Qirui Ji, Yi Li, Wenwen Qiang, Jianwen Cao, Fanjiang Xu
Abstract: Leveraging the development of structural causal model (SCM), researchers can establish graphical models for exploring the causal mechanisms behind machine learning techniques. As the complexity of machine learning applications rises, single-world interventionism causal analysis encounters theoretical adaptation limitations. Accordingly, cross-world counterfactual approach extends our understanding of causality beyond observed data, enabling hypothetical reasoning about alternative scenarios. However, the joint involvement of cross-world variables, encompassing counterfactual variables and real-world variables, challenges the construction of the graphical model. Twin network is a subtle attempt, establishing a symbiotic relationship, to bridge the gap between graphical modeling and the introduction of counterfactuals albeit with room for improvement in generalization. In this regard, we demonstrate the theoretical breakdowns of twin networks in certain cross-world counterfactual scenarios. To this end, we propose a novel teleporter theory to establish a general and simple graphical representation of counterfactuals, which provides criteria for determining teleporter variables to connect multiple worlds. In theoretical application, we determine that introducing the proposed teleporter theory can directly obtain the conditional independence between counterfactual variables and real-world variables from the cross-world SCM without requiring complex algebraic derivations. Accordingly, we can further identify counterfactual causal effects through cross-world symbolic derivation. We demonstrate the generality of the teleporter theory to the practical application. Adhering to the proposed theory, we build a plug-and-play module, and the effectiveness of which are substantiated by experiments on benchmarks.
Authors: Yong-Min Shin, Won-Yong Shin
Abstract: As one of popular quantitative metrics to assess the quality of explanation of graph neural networks (GNNs), fidelity measures the output difference after removing unimportant parts of the input graph. Fidelity has been widely used due to its straightforward interpretation that the underlying model should produce similar predictions when features deemed unimportant from the explanation are removed. This raises a natural question: "Does fidelity induce a global (soft) mask for graph pruning?" To solve this, we aim to explore the potential of the fidelity measure to be used for graph pruning, eventually enhancing the GNN models for better efficiency. To this end, we propose Fidelity$^-$-inspired Pruning (FiP), an effective framework to construct global edge masks from local explanations. Our empirical observations using 7 edge attribution methods demonstrate that, surprisingly, general eXplainable AI methods outperform methods tailored to GNNs in terms of graph pruning performance.
Authors: Bin Qin, Jiangmeng Li, Yi Li, Xuesong Wu, Yupeng Wang, Wenwen Qiang, Jianwen Cao
Abstract: Without loss of generality, existing machine learning techniques may learn spurious correlation dependent on the domain, which exacerbates the generalization of models in out-of-distribution (OOD) scenarios. To address this issue, recent works build a structural causal model (SCM) to describe the causality within data generation process, thereby motivating methods to avoid the learning of spurious correlation by models. However, from the machine learning viewpoint, such a theoretical analysis omits the nuanced difference between the data generation process and representation learning process, resulting in that the causal analysis based on the former cannot well adapt to the latter. To this end, we explore to build a SCM for representation learning process and further conduct a thorough analysis of the mechanisms underlying spurious correlation. We underscore that adjusting erroneous covariates introduces bias, thus necessitating the correct selection of spurious correlation mechanisms based on practical application scenarios. In this regard, we substantiate the correctness of the proposed SCM and further propose to control confounding bias in OOD generalization by introducing a propensity score weighted estimator, which can be integrated into any existing OOD method as a plug-and-play module. The empirical results comprehensively demonstrate the effectiveness of our method on synthetic and large-scale real OOD datasets.
Authors: Tobias Lorenz, Marta Kwiatkowska, Mario Fritz
Abstract: Modern machine learning models are sensitive to the manipulation of both the training data (poisoning attacks) and inference data (adversarial examples). Recognizing this issue, the community has developed many empirical defenses against both attacks and, more recently, provable certification methods against inference-time attacks. However, such guarantees are still largely lacking for training-time attacks. In this work, we present FullCert, the first end-to-end certifier with sound, deterministic bounds, which proves robustness against both training-time and inference-time attacks. We first bound all possible perturbations an adversary can make to the training data under the considered threat model. Using these constraints, we bound the perturbations' influence on the model's parameters. Finally, we bound the impact of these parameter changes on the model's prediction, resulting in joint robustness guarantees against poisoning and adversarial examples. To facilitate this novel certification paradigm, we combine our theoretical work with a new open-source library BoundFlow, which enables model training on bounded datasets. We experimentally demonstrate FullCert's feasibility on two different datasets.
Authors: Artur Jurgas, Marek Wodzinski, Marina D'Amato, Jeroen van der Laak, Manfredo Atzori, Henning M\"uller
Abstract: The problem of artifacts in whole slide image acquisition, prevalent in both clinical workflows and research-oriented settings, necessitates human intervention and re-scanning. Overcoming this challenge requires developing quality control algorithms, that are hindered by the limited availability of relevant annotated data in histopathology. The manual annotation of ground-truth for artifact detection methods is expensive and time-consuming. This work addresses the issue by proposing a method dedicated to augmenting whole slide images with artifacts. The tool seamlessly generates and blends artifacts from an external library to a given histopathology dataset. The augmented datasets are then utilized to train artifact classification methods. The evaluation shows their usefulness in classification of the artifacts, where they show an improvement from 0.10 to 0.01 AUROC depending on the artifact type. The framework, model, weights, and ground-truth annotations are freely released to facilitate open science and reproducible research.
Authors: Anshuman Suri, Xiao Zhang, David Evans
Abstract: Membership inference attacks aim to infer whether an individual record was used to train a model, serving as a key tool for disclosure auditing. While such evaluations are useful to demonstrate risk, they are computationally expensive and often make strong assumptions about potential adversaries' access to models and training environments, and thus do not provide very tight bounds on leakage from potential attacks. We show how prior claims around black-box access being sufficient for optimal membership inference do not hold for most useful settings such as stochastic gradient descent, and that optimal membership inference indeed requires white-box access. We validate our findings with a new white-box inference attack IHA (Inverse Hessian Attack) that explicitly uses model parameters by taking advantage of computing inverse-Hessian vector products. Our results show that both audits and adversaries may be able to benefit from access to model parameters, and we advocate for further research into white-box methods for membership privacy auditing.
Authors: Rick Wilming, Artur Dox, Hjalmar Schulz, Marta Oliveira, Benedict Clark, Stefan Haufe
Abstract: Large pre-trained language models have become popular for many applications and form an important backbone of many downstream tasks in natural language processing (NLP). Applying 'explainable artificial intelligence' (XAI) techniques to enrich such models' outputs is considered crucial for assuring their quality and shedding light on their inner workings. However, large language models are trained on a plethora of data containing a variety of biases, such as gender biases, affecting model weights and, potentially, behavior. Currently, it is unclear to what extent such biases also impact model explanations in possibly unfavorable ways. We create a gender-controlled text dataset, GECO, in which otherwise identical sentences appear in male and female forms. This gives rise to ground-truth 'world explanations' for gender classification tasks, enabling the objective evaluation of the correctness of XAI methods. We also provide GECOBench, a rigorous quantitative evaluation framework benchmarking popular XAI methods, applying them to pre-trained language models fine-tuned to different degrees. This allows us to investigate how pre-training induces undesirable bias in model explanations and to what extent fine-tuning can mitigate such explanation bias. We show a clear dependency between explanation performance and the number of fine-tuned layers, where XAI methods are observed to particularly benefit from fine-tuning or complete retraining of embedding layers. Remarkably, this relationship holds for models achieving similar classification performance on the same task. With that, we highlight the utility of the proposed gender-controlled dataset and novel benchmarking approach for research and development of novel XAI methods. All code including dataset generation, model training, evaluation and visualization is available at: https://github.com/braindatalab/gecobench
Authors: Chuyan Xiong, Chengyu Shen, Xiaoqi Li, Kaichen Zhou, Jiaming Liu, Ruiping Wang, Hao Dong
Abstract: The ability to reflect on and correct failures is crucial for robotic systems to interact stably with real-life objects.Observing the generalization and reasoning capabilities of Multimodal Large Language Models (MLLMs), previous approaches have aimed to utilize these models to enhance robotic systems accordingly.However, these methods typically focus on high-level planning corrections using an additional MLLM, with limited utilization of failed samples to correct low-level contact poses. To address this gap, we propose an Autonomous Interactive Correction (AIC) MLLM, which makes use of previous low-level interaction experiences to correct SE(3) pose predictions. Specifically, AIC MLLM is initially fine-tuned to acquire both pose prediction and feedback prompt comprehension abilities.We carefully design two types of prompt instructions through interactions with objects: 1) visual masks to highlight unmovable parts for position correction, and 2)textual descriptions to indicate potential directions for rotation correction.During inference, a Feedback Information Extraction module is introduced to recognize the failure cause, allowing AIC MLLM to adaptively correct the pose prediction using the corresponding prompts.To further enhance manipulation stability, we devise a Test Time Adaptation strategy that enables AIC MLLM to better adapt to the current scene configuration.Finally, extensive experiments are conducted in both simulated and real-world environments to evaluate the proposed method. The results demonstrate that our AIC MLLM can efficiently correct failure samples by leveraging interaction experience prompts.Real-world demonstration can be found at https://sites.google.com/view/aic-mllm
Authors: Lukas Vierling, Jie Fu, Kai Chen
Abstract: Recent progress in Large Language Models (LLMs) and language agents has demonstrated significant promise for various future applications across multiple disciplines. While traditional approaches to language agents often rely on fixed, handcrafted designs, our research aims to develop both learnable and dynamic agents. Our method uses an existing framework that abstracts language agents as graphs. Within this graph framework, we aim to learn a model that can generate edges for every given input to the language agent. This allows us to generate edges that represent the flow of communication within the graph based on the given input, thereby adjusting the internal communication of a language agent. We learn to generate these edges using a pretrained LLM that is fine-tuned with reinforcement learning. This LLM can be fine-tuned on several datasets simultaneously, and we hypothesize that the model learns to adapt to these different domains during training, achieving good overall performance when encountering data from different domains during deployment. We demonstrate that our approach surpasses the previous static approach by nearly 6% accuracy on a combined dataset of MMLU and CMMLU, and by more than 10% when trained with a sparsity-inducing loss. It also performs superior in additional experiments conducted with the MMLU and Mini Crossword Puzzles datasets. The code is available at https://github.com/lukasVierling/DynamicGPTSwarm.
Authors: Duan Wang, Dandan Zhu, Meixiang Zhao, Zhigang Jia
Abstract: Color image inpainting is a challenging task in imaging science. The existing method is based on real operation, and the red, green and blue channels of the color image are processed separately, ignoring the correlation between each channel. In order to make full use of the correlation between each channel, this paper proposes a Quaternion Generative Adversarial Neural Network (QGAN) model and related theory, and applies it to solve the problem of color image inpainting with large area missing. Firstly, the definition of quaternion deconvolution is given and the quaternion batch normalization is proposed. Secondly, the above two innovative modules are applied to generate adversarial networks to improve stability. Finally, QGAN is applied to color image inpainting and compared with other state-of-the-art algorithms. The experimental results show that QGAN has superiority in color image inpainting with large area missing.
Authors: Jing Gong, Yanghui Wu, Linxi Liang, Zibin Zheng, Yanlin Wang
Abstract: Semantic code search, retrieving code that matches a given natural language query, is an important task to improve productivity in software engineering. Existing code search datasets are problematic: either using unrealistic queries, or with mismatched codes, and typically using one-to-one query-code pairing, which fails to reflect the reality that a query might have multiple valid code matches. This paper introduces CoSQA+, pairing high-quality queries (reused from CoSQA) with multiple suitable codes. We collect code candidates from diverse sources and form candidate pairs by pairing queries with these codes. Utilizing the power of large language models (LLMs), we automate pair annotation, filtering, and code generation for queries without suitable matches. Through extensive experiments, CoSQA+ has demonstrated superior quality over CoSQA. Models trained on CoSQA+ exhibit improved performance. Furthermore, we propose a new metric Mean Multi-choice Reciprocal Rank (MMRR), to assess one-to-N code search performance. We provide the code and data at https://github.com/DeepSoftwareAnalytics/CoSQA_Plus.
Authors: Egor Bogomolov, Aleksandra Eliseeva, Timur Galimzyanov, Evgeniy Glukhov, Anton Shapkin, Maria Tigina, Yaroslav Golubev, Alexander Kovrigin, Arie van Deursen, Maliheh Izadi, Timofey Bryksin
Abstract: Nowadays, the fields of code and natural language processing are evolving rapidly. In particular, models become better at processing long context windows - supported context sizes have increased by orders of magnitude over the last few years. However, there is a shortage of benchmarks for code processing that go beyond a single file of context, while the most popular ones are limited to a single method. With this work, we aim to close this gap by introducing Long Code Arena, a suite of six benchmarks for code processing tasks that require project-wide context. These tasks cover different aspects of code processing: library-based code generation, CI builds repair, project-level code completion, commit message generation, bug localization, and module summarization. For each task, we provide a manually verified dataset for testing, an evaluation suite, and open-source baseline solutions based on popular LLMs to showcase the usage of the dataset and to simplify adoption by other researchers. We publish the benchmark page on HuggingFace Spaces with the leaderboard, links to HuggingFace Hub for all the datasets, and link to the GitHub repository with baselines: https://huggingface.co/spaces/JetBrains-Research/long-code-arena.
URLs: https://huggingface.co/spaces/JetBrains-Research/long-code-arena.
Authors: Yihuai Hong, Lei Yu, Shauli Ravfogel, Haiqin Yang, Mor Geva
Abstract: The task of "unlearning" certain concepts in large language models (LLMs) has attracted immense attention recently, due to its importance for mitigating undesirable model behaviours, such as the generation of harmful, private, or incorrect information. Current protocols to evaluate unlearning methods largely rely on behavioral tests, without monitoring the presence of unlearned knowledge within the model's parameters. This residual knowledge can be adversarially exploited to recover the erased information post-unlearning. We argue that unlearning should also be evaluated internally, by considering changes in the parametric knowledge traces of the unlearned concepts. To this end, we propose a general methodology for eliciting directions in the parameter space (termed "concept vectors") that encode concrete concepts, and construct ConceptVectors, a benchmark dataset containing hundreds of common concepts and their parametric knowledge traces within two open-source LLMs. Evaluation on ConceptVectors shows that existing unlearning methods minimally impact concept vectors, while directly ablating these vectors demonstrably removes the associated knowledge from the LLMs and significantly reduces their susceptibility to adversarial manipulation. Our results highlight limitations in behavioral-based unlearning evaluations and call for future work to include parametric-based evaluations. To support this, we release our code and benchmark at https://github.com/yihuaihong/ConceptVectors.
Authors: Boxuan Lyu, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura
Abstract: Maximum a posteriori decoding, a commonly used method for neural machine translation (NMT), aims to maximize the estimated posterior probability. However, high estimated probability does not always lead to high translation quality. Minimum Bayes Risk (MBR) decoding offers an alternative by seeking hypotheses with the highest expected utility. In this work, we show that Quality Estimation (QE) reranking, which uses a QE model as a reranker, can be viewed as a variant of MBR. Inspired by this, we propose source-based MBR (sMBR) decoding, a novel approach that utilizes synthetic sources generated by backward translation as ``support hypotheses'' and a reference-free quality estimation metric as the utility function, marking the first work to solely use sources in MBR decoding. Experiments show that sMBR significantly outperforms QE reranking and is competitive with standard MBR decoding. Furthermore, sMBR calls the utility function fewer times compared to MBR. Our findings suggest that sMBR is a promising approach for high-quality NMT decoding.
Authors: Kyle Moore, Jesse Roberts, Thao Pham, Oseremhen Ewaleifoh, Doug Fisher
Abstract: Cloze testing is a common method for measuring the behavior of large language models on a number of benchmark tasks. Using the MMLU dataset, we show that the base-rate probability (BRP) differences across answer tokens are significant and affect task performance ie. guess A if uncertain. We find that counterfactual prompting does sufficiently mitigate the BRP effect. The BRP effect is found to have a similar effect to test taking strategies employed by humans leading to the conflation of task performance and test-taking ability. We propose the Nvr-X-MMLU task, a variation of MMLU, which helps to disambiguate test-taking ability from task performance and reports the latter.
Authors: Noah Golowich, Ankur Moitra
Abstract: One of the most natural approaches to reinforcement learning (RL) with function approximation is value iteration, which inductively generates approximations to the optimal value function by solving a sequence of regression problems. To ensure the success of value iteration, it is typically assumed that Bellman completeness holds, which ensures that these regression problems are well-specified. We study the problem of learning an optimal policy under Bellman completeness in the online model of RL with linear function approximation. In the linear setting, while statistically efficient algorithms are known under Bellman completeness (e.g., Jiang et al. (2017); Zanette et al. (2020)), these algorithms all rely on the principle of global optimism which requires solving a nonconvex optimization problem. In particular, it has remained open as to whether computationally efficient algorithms exist. In this paper we give the first polynomial-time algorithm for RL under linear Bellman completeness when the number of actions is any constant.
Authors: Tamara R. Lenhard, Andreas Weinmann, Stefan J\"ager, Tobias Koch
Abstract: Predominant methods for image-based drone detection frequently rely on employing generic object detection algorithms like YOLOv5. While proficient in identifying drones against homogeneous backgrounds, these algorithms often struggle in complex, highly textured environments. In such scenarios, drones seamlessly integrate into the background, creating camouflage effects that adversely affect the detection quality. To address this issue, we introduce a novel deep learning architecture called YOLO-FEDER FusionNet. Unlike conventional approaches, YOLO-FEDER FusionNet combines generic object detection methods with the specialized strength of camouflage object detection techniques to enhance drone detection capabilities. Comprehensive evaluations of YOLO-FEDER FusionNet show the efficiency of the proposed model and demonstrate substantial improvements in both reducing missed detections and false alarms.
Authors: Amith Ananthram, Elias Stengel-Eskin, Carl Vondrick, Mohit Bansal, Kathleen McKeown
Abstract: Vision-language models (VLMs) can respond to queries about images in many languages. However, beyond language, culture affects how we see things. For example, individuals from Western cultures focus more on the central figure in an image while individuals from Eastern cultures attend more to scene context. In this work, we present a novel investigation that demonstrates and localizes VLMs' Western bias in image understanding. We evaluate large VLMs across subjective and objective visual tasks with culturally diverse images and annotations. We find that VLMs perform better on the Western subset than the Eastern subset of each task. Controlled experimentation tracing the source of this bias highlights the importance of a diverse language mix in text-only pre-training for building equitable VLMs, even when inference is performed in English. Moreover, while prompting in the language of a target culture can lead to reductions in bias, it is not a substitute for building AI more representative of the world's languages.
Authors: Constantinos Daskalakis, Noah Golowich
Abstract: The empirical risk minimization (ERM) principle has been highly impactful in machine learning, leading both to near-optimal theoretical guarantees for ERM-based learning algorithms as well as driving many of the recent empirical successes in deep learning. In this paper, we investigate the question of whether the ability to perform ERM, which computes a hypothesis minimizing empirical risk on a given dataset, is necessary for efficient learning: in particular, is there a weaker oracle than ERM which can nevertheless enable learnability? We answer this question affirmatively, showing that in the realizable setting of PAC learning for binary classification, a concept class can be learned using an oracle which only returns a single bit indicating whether a given dataset is realizable by some concept in the class. The sample complexity and oracle complexity of our algorithm depend polynomially on the VC dimension of the hypothesis class, thus showing that there is only a polynomial price to pay for use of our weaker oracle. Our results extend to the agnostic learning setting with a slight strengthening of the oracle, as well as to the partial concept, multiclass and real-valued learning settings. In the setting of partial concept classes, prior to our work no oracle-efficient algorithms were known, even with a standard ERM oracle. Thus, our results address a question of Alon et al. (2021) who asked whether there are algorithmic principles which enable efficient learnability in this setting.
Authors: Thorsten Pr\"ohl, Erik Putzier, R\"udiger Zarnekow
Abstract: This article gives an overview of the field of LLM text recognition. Different approaches and implemented detectors for the recognition of LLM-generated text are presented. In addition to discussing the implementations, the article focuses on benchmarking the detectors. Although there are numerous software products for the recognition of LLM-generated text, with a focus on ChatGPT-like LLMs, the quality of the recognition (recognition rate) is not clear. Furthermore, while it can be seen that scientific contributions presenting their novel approaches strive for some kind of comparison with other approaches, the construction and independence of the evaluation dataset is often not comprehensible. As a result, discrepancies in the performance evaluation of LLM detectors are often visible due to the different benchmarking datasets. This article describes the creation of an evaluation dataset and uses this dataset to investigate the different detectors. The selected detectors are benchmarked against each other.
Authors: Yibin Wang, Haizhou Shi, Ligong Han, Dimitris Metaxas, Hao Wang
Abstract: Large Language Models (LLMs) often suffer from overconfidence during inference, particularly when adapted to downstream domain-specific tasks with limited data. Previous work addresses this issue by employing approximate Bayesian estimation after the LLMs are trained, enabling them to quantify uncertainty. However, such post-training approaches' performance is severely limited by the parameters learned during training. In this paper, we go beyond post-training Bayesianization and propose Bayesian Low-Rank Adaptation by Backpropagation (BLoB), an algorithm that continuously and jointly adjusts both the mean and covariance of LLM parameters throughout the whole fine-tuning process. Our empirical results verify the effectiveness of BLoB in terms of generalization and uncertainty estimation, when evaluated on both in-distribution and out-of-distribution data.
Authors: Shangqing Tu, Yuanchun Wang, Jifan Yu, Yuyang Xie, Yaran Shi, Xiaozhi Wang, Jing Zhang, Lei Hou, Juanzi Li
Abstract: Large language models have achieved remarkable success on general NLP tasks, but they may fall short for domain-specific problems. Recently, various Retrieval-Augmented Large Language Models (RALLMs) are proposed to address this shortcoming. However, existing evaluation tools only provide a few baselines and evaluate them on various domains without mining the depth of domain knowledge. In this paper, we address the challenges of evaluating RALLMs by introducing the R-Eval toolkit, a Python toolkit designed to streamline the evaluation of different RAG workflows in conjunction with LLMs. Our toolkit, which supports popular built-in RAG workflows and allows for the incorporation of customized testing data on the specific domain, is designed to be user-friendly, modular, and extensible. We conduct an evaluation of 21 RALLMs across three task levels and two representative domains, revealing significant variations in the effectiveness of RALLMs across different tasks and domains. Our analysis emphasizes the importance of considering both task and domain requirements when choosing a RAG workflow and LLM combination. We are committed to continuously maintaining our platform at https://github.com/THU-KEG/R-Eval to facilitate both the industry and the researchers.
Authors: Shangqing Tu, Zhuoran Pan, Wenxuan Wang, Zhexin Zhang, Yuliang Sun, Jifan Yu, Hongning Wang, Lei Hou, Juanzi Li
Abstract: Large language models (LLMs) have been increasingly applied to various domains, which triggers increasing concerns about LLMs' safety on specialized domains, e.g. medicine. However, testing the domain-specific safety of LLMs is challenging due to the lack of domain knowledge-driven attacks in existing benchmarks. To bridge this gap, we propose a new task, knowledge-to-jailbreak, which aims to generate jailbreaks from domain knowledge to evaluate the safety of LLMs when applied to those domains. We collect a large-scale dataset with 12,974 knowledge-jailbreak pairs and fine-tune a large language model as jailbreak-generator, to produce domain knowledge-specific jailbreaks. Experiments on 13 domains and 8 target LLMs demonstrate the effectiveness of jailbreak-generator in generating jailbreaks that are both relevant to the given knowledge and harmful to the target LLMs. We also apply our method to an out-of-domain knowledge base, showing that jailbreak-generator can generate jailbreaks that are comparable in harmfulness to those crafted by human experts. Data and code: https://github.com/THU-KEG/Knowledge-to-Jailbreak/.
Authors: Noah Golowich, Ankur Moitra
Abstract: In this paper, we study the offline RL problem with linear function approximation. Our main structural assumption is that the MDP has low inherent Bellman error, which stipulates that linear value functions have linear Bellman backups with respect to the greedy policy. This assumption is natural in that it is essentially the minimal assumption required for value iteration to succeed. We give a computationally efficient algorithm which succeeds under a single-policy coverage condition on the dataset, namely which outputs a policy whose value is at least that of any policy which is well-covered by the dataset. Even in the setting when the inherent Bellman error is 0 (termed linear Bellman completeness), our algorithm yields the first known guarantee under single-policy coverage. In the setting of positive inherent Bellman error ${\varepsilon_{\mathrm{BE}}} > 0$, we show that the suboptimality error of our algorithm scales with $\sqrt{\varepsilon_{\mathrm{BE}}}$. Furthermore, we prove that the scaling of the suboptimality with $\sqrt{\varepsilon_{\mathrm{BE}}}$ cannot be improved for any algorithm. Our lower bound stands in contrast to many other settings in reinforcement learning with misspecification, where one can typically obtain performance that degrades linearly with the misspecification error.
Authors: Krista Opsahl-Ong, Michael J Ryan, Josh Purtell, David Broman, Christopher Potts, Matei Zaharia, Omar Khattab
Abstract: Language Model Programs, i.e. sophisticated pipelines of modular language model (LM) calls, are increasingly advancing NLP tasks, but they require crafting prompts that are jointly effective for all modules. We study prompt optimization for LM programs, i.e. how to update these prompts to maximize a downstream metric without access to module-level labels or gradients. To make this tractable, we factorize our problem into optimizing the free-form instructions and few-shot demonstrations of every module and introduce several strategies to craft task-grounded instructions and navigate credit assignment across modules. Our strategies include (i) program- and data-aware techniques for proposing effective instructions, (ii) a stochastic mini-batch evaluation function for learning a surrogate model of our objective, and (iii) a meta-optimization procedure in which we refine how LMs construct proposals over time. Using these insights we develop MIPRO, a novel optimizer that outperforms baselines on five of six diverse LM programs using a best-in-class open-source model (Llama-3-8B), by as high as 12.9% accuracy. We will release our new optimizers and benchmark in DSPy at https://github.com/stanfordnlp/dspy
Authors: Nvidia, :, Bo Adler, Niket Agarwal, Ashwath Aithal, Dong H. Anh, Pallab Bhattacharya, Annika Brundyn, Jared Casper, Bryan Catanzaro, Sharon Clay, Jonathan Cohen, Sirshak Das, Ayush Dattagupta, Olivier Delalleau, Leon Derczynski, Yi Dong, Daniel Egert, Ellie Evans, Aleksander Ficek, Denys Fridman, Shaona Ghosh, Boris Ginsburg, Igor Gitman, Tomasz Grzegorzek, Robert Hero, Jining Huang, Vibhu Jawa, Joseph Jennings, Aastha Jhunjhunwala, John Kamalu, Sadaf Khan, Oleksii Kuchaiev, Patrick LeGresley, Hui Li, Jiwei Liu, Zihan Liu, Eileen Long, Ameya Sunil Mahabaleshwarkar, Somshubra Majumdar, James Maki, Miguel Martinez, Maer Rodrigues de Melo, Ivan Moshkov, Deepak Narayanan, Sean Narenthiran, Jesus Navarro, Phong Nguyen, Osvald Nitski, Vahid Noroozi, Guruprasad Nutheti, Christopher Parisien, Jupinder Parmar, Mostofa Patwary, Krzysztof Pawelec, Wei Ping, Shrimai Prabhumoye, Rajarshi Roy, Trisha Saar, Vasanth Rao Naik Sabavat, Sanjeev Satheesh, Jane Polak Scowcroft, Jason Sewall, Pavel Shamis, Gerald Shen, Mohammad Shoeybi, Dave Sizer, Misha Smelyanskiy, Felipe Soares, Makesh Narsimhan Sreedhar, Dan Su, Sandeep Subramanian, Shengyang Sun, Shubham Toshniwal, Hao Wang, Zhilin Wang, Jiaxuan You, Jiaqi Zeng, Jimmy Zhang, Jing Zhang, Vivienne Zhang, Yian Zhang, Chen Zhu
Abstract: We release the Nemotron-4 340B model family, including Nemotron-4-340B-Base, Nemotron-4-340B-Instruct, and Nemotron-4-340B-Reward. Our models are open access under the NVIDIA Open Model License Agreement, a permissive model license that allows distribution, modification, and use of the models and its outputs. These models perform competitively to open access models on a wide range of evaluation benchmarks, and were sized to fit on a single DGX H100 with 8 GPUs when deployed in FP8 precision. We believe that the community can benefit from these models in various research studies and commercial applications, especially for generating synthetic data to train smaller language models. Notably, over 98% of data used in our model alignment process is synthetically generated, showcasing the effectiveness of these models in generating synthetic data. To further support open research and facilitate model development, we are also open-sourcing the synthetic data generation pipeline used in our model alignment process.
Authors: Andy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka, Nina Rimsky, Wes Gurnee, Neel Nanda
Abstract: Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this refusal behavior is widespread across chat models, its underlying mechanisms remain poorly understood. In this work, we show that refusal is mediated by a one-dimensional subspace, across 13 popular open-source chat models up to 72B parameters in size. Specifically, for each model, we find a single direction such that erasing this direction from the model's residual stream activations prevents it from refusing harmful instructions, while adding this direction elicits refusal on even harmless instructions. Leveraging this insight, we propose a novel white-box jailbreak method that surgically disables refusal with minimal effect on other capabilities. Finally, we mechanistically analyze how adversarial suffixes suppress propagation of the refusal-mediating direction. Our findings underscore the brittleness of current safety fine-tuning methods. More broadly, our work showcases how an understanding of model internals can be leveraged to develop practical methods for controlling model behavior.
Authors: Bingxiang He, Ning Ding, Cheng Qian, Jia Deng, Ganqu Cui, Lifan Yuan, Huan-ang Gao, Huimin Chen, Zhiyuan Liu, Maosong Sun
Abstract: Understanding alignment techniques begins with comprehending zero-shot generalization brought by instruction tuning, but little of the mechanism has been understood. Existing work has largely been confined to the task level, without considering that tasks are artificially defined and, to LLMs, merely consist of tokens and representations. This line of research has been limited to examining transfer between tasks from a task-pair perspective, with few studies focusing on understanding zero-shot generalization from the perspective of the data itself. To bridge this gap, we first demonstrate through multiple metrics that zero-shot generalization during instruction tuning happens very early. Next, we investigate the facilitation of zero-shot generalization from both data similarity and granularity perspectives, confirming that encountering highly similar and fine-grained training data earlier during instruction tuning, without the constraints of defined "tasks", enables better generalization. Finally, we propose a more grounded training data arrangement method, Test-centric Multi-turn Arrangement, and show its effectiveness in promoting continual learning and further loss reduction. For the first time, we show that zero-shot generalization during instruction tuning is a form of similarity-based generalization between training and test data at the instance level. We hope our analysis will advance the understanding of zero-shot generalization during instruction tuning and contribute to the development of more aligned LLMs. Our code is released at https://github.com/HBX-hbx/dynamics_of_zero-shot_generalization.
URLs: https://github.com/HBX-hbx/dynamics_of_zero-shot_generalization.
Authors: Fangzhi Xu, Qiushi Sun, Kanzhi Cheng, Jun Liu, Yu Qiao, Zhiyong Wu
Abstract: One of the primary driving forces contributing to the superior performance of Large Language Models (LLMs) is the extensive availability of human-annotated natural language data, which is used for alignment fine-tuning. This inspired researchers to investigate self-training methods to mitigate the extensive reliance on human annotations. However, the current success of self-training has been primarily observed in natural language scenarios, rather than in the increasingly important neural-symbolic scenarios. To this end, we propose an environment-guided neural-symbolic self-training framework named ENVISIONS. It aims to overcome two main challenges: (1) the scarcity of symbolic data, and (2) the limited proficiency of LLMs in processing symbolic language. Extensive evaluations conducted on three distinct domains demonstrate the effectiveness of our approach. Additionally, we have conducted a comprehensive analysis to uncover the factors contributing to ENVISIONS's success, thereby offering valuable insights for future research in this area. Code will be available at \url{https://github.com/xufangzhi/ENVISIONS}.
Authors: Haojie Huang, Karl Schmeckpeper, Dian Wang, Ondrej Biza, Yaoyao Qian, Haotian Liu, Mingxi Jia, Robert Platt, Robin Walters
Abstract: Humans can imagine goal states during planning and perform actions to match those goals. In this work, we propose Imagination Policy, a novel multi-task key-frame policy network for solving high-precision pick and place tasks. Instead of learning actions directly, Imagination Policy generates point clouds to imagine desired states which are then translated to actions using rigid action estimation. This transforms action inference into a local generative task. We leverage pick and place symmetries underlying the tasks in the generation process and achieve extremely high sample efficiency and generalizability to unseen configurations. Finally, we demonstrate state-of-the-art performance across various tasks on the RLbench benchmark compared with several strong baselines.
Authors: Edwin Zhang, Vincent Zhu, Naomi Saphra, Anat Kleiman, Benjamin L. Edelman, Milind Tambe, Sham M. Kakade, Eran Malach
Abstract: Generative models are trained with the simple objective of imitating the conditional probability distribution induced by the data they are trained on. Therefore, when trained on data generated by humans, we may not expect the artificial model to outperform the humans on their original objectives. In this work, we study the phenomenon of transcendence: when a generative model achieves capabilities that surpass the abilities of the experts generating its data. We demonstrate transcendence by training an autoregressive transformer to play chess from game transcripts, and show that the trained model can sometimes achieve better performance than all players in the dataset. We theoretically prove that transcendence is enabled by low-temperature sampling, and rigorously assess this experimentally. Finally, we discuss other sources of transcendence, laying the groundwork for future investigation of this phenomenon in a broader setting.
Authors: Trish E. Nowak, Andy T. Augousti, Benno I. Simmons, Stefan Siegert
Abstract: Suspended in the atmosphere are millions of tonnes of mineral dust which interacts with weather and climate. Accurate representation of mineral dust in weather models is vital, yet remains challenging. Large scale weather models use high power supercomputers and take hours to complete the forecast. Such computational burden allows them to only include monthly climatological means of mineral dust as input states inhibiting their forecasting accuracy. Here, we introduce DustNet a simple, accurate and super fast forecasting model for 24-hours ahead predictions of aerosol optical depth AOD. DustNet trains in less than 8 minutes and creates predictions in 2 seconds on a desktop computer. Created by DustNet predictions outperform the state-of-the-art physics-based model on coarse 1 x 1 degree resolution at 95% of grid locations when compared to ground truth satellite data. Our results show DustNet has a potential for fast and accurate AOD forecasting which could transform our understanding of dust impacts on weather patterns.
Authors: Sreyan Ghosh, Sonal Kumar, Ashish Seth, Chandra Kiran Reddy Evuru, Utkarsh Tyagi, S Sakshi, Oriol Nieto, Ramani Duraiswami, Dinesh Manocha
Abstract: Perceiving and understanding non-speech sounds and non-verbal speech is essential to making decisions that help us interact with our surroundings. In this paper, we propose GAMA, a novel General-purpose Large Audio-Language Model (LALM) with Advanced Audio Understanding and Complex Reasoning Abilities. We build GAMA by integrating an LLM with multiple types of audio representations, including features from a custom Audio Q-Former, a multi-layer aggregator that aggregates features from multiple layers of an audio encoder. We fine-tune GAMA on a large-scale audio-language dataset, which augments it with audio understanding capabilities. Next, we propose CompA-R (Instruction-Tuning for Complex Audio Reasoning), a synthetically generated instruction-tuning (IT) dataset with instructions that require the model to perform complex reasoning on the input audio. We instruction-tune GAMA with CompA-R to endow it with complex reasoning abilities, where we further add a soft prompt as input with high-level semantic evidence by leveraging event tags of the input audio. Finally, we also propose CompA-R-test, a human-labeled evaluation dataset for evaluating the capabilities of LALMs on open-ended audio question-answering that requires complex reasoning. Through automated and expert human evaluations, we show that GAMA outperforms all other LALMs in literature on diverse audio understanding tasks by margins of 1%-84%. Further, GAMA IT-ed on CompA-R proves to be superior in its complex reasoning and instruction following capabilities.
Authors: David Herrera-Poyatos, Andr\'es Herrera-Poyatos, Rosana Montes, Paloma de Palacios, Luis G. Esteban, Alberto Garc\'ia Iruela, Francisco Garc\'ia Fern\'andez, Francisco Herrera
Abstract: Significant advancements in the field of wood species identification are needed worldwide to support sustainable timber trade. In this work we contribute to automate the identification of wood species via high-resolution macroscopic images of timber. The main challenge of this problem is that fine-grained patterns in timber are crucial in order to accurately identify wood species, and these patterns are not properly learned by traditional convolutional neural networks (CNNs) trained on low/medium resolution images. We propose a Timber Deep Learning Identification with Patch-based Inference Voting methodology, abbreviated TDLI-PIV methodology. Our proposal exploits the concept of patching and the availability of high-resolution macroscopic images of timber in order to overcome the inherent challenges that CNNs face in timber identification. The TDLI-PIV methodology is able to capture fine-grained patterns in timber and, moreover, boosts robustness and prediction accuracy via a collaborative voting inference process. In this work we also introduce a new data set of marcroscopic images of timber, called GOIMAI-Phase-I, which has been obtained using optical magnification in order to capture fine-grained details, which contrasts to the other datasets that are publicly available. More concretely, images in GOIMAI-Phase-I are taken with a smartphone with a 24x magnifying lens attached to the camera. Our data set contains 2120 images of timber and covers 37 legally protected wood species. Our experiments have assessed the performance of the TDLI-PIV methodology, involving the comparison with other methodologies available in the literature, exploration of data augmentation methods and the effect that the dataset size has on the accuracy of TDLI-PIV.
Authors: Jieyu Zhang, Weikai Huang, Zixian Ma, Oscar Michel, Dong He, Tanmay Gupta, Wei-Chiu Ma, Ali Farhadi, Aniruddha Kembhavi, Ranjay Krishna
Abstract: Benchmarks for large multimodal language models (MLMs) now serve to simultaneously assess the general capabilities of models instead of evaluating for a specific capability. As a result, when a developer wants to identify which models to use for their application, they are overwhelmed by the number of benchmarks and remain uncertain about which benchmark's results are most reflective of their specific use case. This paper introduces Task-Me-Anything, a benchmark generation engine which produces a benchmark tailored to a user's needs. Task-Me-Anything maintains an extendable taxonomy of visual assets and can programmatically generate a vast number of task instances. Additionally, it algorithmically addresses user queries regarding MLM performance efficiently within a computational budget. It contains 113K images, 10K videos, 2K 3D object assets, over 365 object categories, 655 attributes, and 335 relationships. It can generate 750M image/video question-answering pairs, which focus on evaluating MLM perceptual capabilities. Task-Me-Anything reveals critical insights: open-source MLMs excel in object and attribute recognition but lack spatial and temporal understanding; each model exhibits unique strengths and weaknesses; larger models generally perform better, though exceptions exist; and GPT4o demonstrates challenges in recognizing rotating/moving objects and distinguishing colors.
Authors: Swanand Ravindra Kadhe, Farhan Ahmed, Dennis Wei, Nathalie Baracaldo, Inkit Padhi
Abstract: Large language models (LLMs) have shown to pose social and ethical risks such as generating toxic language or facilitating malicious use of hazardous knowledge. Machine unlearning is a promising approach to improve LLM safety by directly removing harmful behaviors and knowledge. In this paper, we propose "SPlit, UNlearn, MerGE" (SPUNGE), a framework that can be used with any unlearning method to amplify its effectiveness. SPUNGE leverages data attributes during unlearning by splitting unlearning data into subsets based on specific attribute values, unlearning each subset separately, and merging the unlearned models. We empirically demonstrate that SPUNGE significantly improves the performance of two recent unlearning methods on state-of-the-art LLMs while maintaining their general capabilities on standard academic benchmarks.
Authors: Peter Baile Chen, Yi Zhang, Chunwei Liu, Sejal Gupta, Yoon Kim, Michael Cafarella
Abstract: The same real-life questions posed to different individuals may lead to different answers based on their unique situations. For instance, whether a student is eligible for a scholarship depends on eligibility conditions, such as major or degree required. ConditionalQA was proposed to evaluate models' capability of reading a document and answering eligibility questions, considering unmentioned conditions. However, it is limited to questions on single documents, neglecting harder cases that may require cross-document reasoning and optimization, for example, "What is the maximum number of scholarships attainable?" Such questions over multiple documents are not only more challenging due to more context having to understand, but also because the model has to (1) explore all possible combinations of unmentioned conditions and (2) understand the relationship between conditions across documents, to reason about the optimal outcome. To evaluate models' capability of answering such questions, we propose a new dataset MDCR, which can reflect real-world challenges and serve as a new test bed for complex conditional reasoning that requires optimization. We evaluate this dataset using the most recent LLMs and demonstrate their limitations in solving this task. We believe this dataset will facilitate future research in answering optimization questions with unknown conditions.
Authors: Ronny Luss, Erik Miehling, Amit Dhurandhar
Abstract: The advent of black-box deep neural network classification models has sparked the need to explain their decisions. However, in the case of generative AI such as large language models (LLMs), there is no class prediction to explain. Rather, one can ask why an LLM output a particular response to a given prompt. In this paper, we answer this question by proposing, to the best of our knowledge, the first contrastive explanation methods requiring simply black-box/query access. Our explanations suggest that an LLM outputs a reply to a given prompt because if the prompt was slightly modified, the LLM would have given a different response that is either less preferable or contradicts the original response. The key insight is that contrastive explanations simply require a distance function that has meaning to the user and not necessarily a real valued representation of a specific response (viz. class label). We offer two algorithms for finding contrastive explanations: i) A myopic algorithm, which although effective in creating contrasts, requires many model calls and ii) A budgeted algorithm, our main algorithmic contribution, which intelligently creates contrasts adhering to a query budget, necessary for longer contexts. We show the efficacy of these methods on diverse natural language tasks such as open-text generation, automated red teaming, and explaining conversational degradation.
Authors: Abhi Kamboj, Katherine Driggs-Campbell
Abstract: Robotic grasping presents a difficult motor task in real-world scenarios, constituting a major hurdle to the deployment of capable robots across various industries. Notably, the scarcity of data makes grasping particularly challenging for learned models. Recent advancements in computer vision have witnessed a growth of successful unsupervised training mechanisms predicated on massive amounts of data sourced from the Internet, and now nearly all prominent models leverage pretrained backbone networks. Against this backdrop, we begin to investigate the potential benefits of large-scale visual pretraining in enhancing robot grasping performance. This preliminary literature review sheds light on critical challenges and delineates prospective directions for future research in visual pretraining for robotic manipulation.
Authors: Joao Monteiro, Pierre-Andre Noel, Etienne Marcotte, Sai Rajeswar, Valentina Zantedeschi, David Vazquez, Nicolas Chapados, Christopher Pal, Perouz Taslakian
Abstract: Large Language Models (LLMs) are trained on vast amounts of data, most of which is automatically scraped from the internet. This data includes encyclopedic documents that harbor a vast amount of general knowledge (e.g., Wikipedia) but also potentially overlap with benchmark datasets used for evaluating LLMs. Consequently, evaluating models on test splits that might have leaked into the training set is prone to misleading conclusions. To foster sound evaluation of language models, we introduce a new test dataset named RepLiQA, suited for question-answering and topic retrieval tasks. RepLiQA is a collection of five splits of test sets, four of which have not been released to the internet or exposed to LLM APIs prior to this publication. Each sample in RepLiQA comprises (1) a reference document crafted by a human annotator and depicting an imaginary scenario (e.g., a news article) absent from the internet; (2) a question about the document's topic; (3) a ground-truth answer derived directly from the information in the document; and (4) the paragraph extracted from the reference document containing the answer. As such, accurate answers can only be generated if a model can find relevant content within the provided document. We run a large-scale benchmark comprising several state-of-the-art LLMs to uncover differences in performance across models of various types and sizes in a context-conditional language modeling setting. Released splits of RepLiQA can be found here: https://huggingface.co/datasets/ServiceNow/repliqa.
Authors: Jie Liu, Zhanhui Zhou, Jiaheng Liu, Xingyuan Bu, Chao Yang, Han-Sen Zhong, Wanli Ouyang
Abstract: Direct Preference Optimization (DPO), a standard method for aligning language models with human preferences, is traditionally applied to offline preferences. Recent studies show that DPO benefits from iterative training with online preferences labeled by a trained reward model. In this work, we identify a pitfall of vanilla iterative DPO - improved response quality can lead to increased verbosity. To address this, we introduce iterative length-regularized DPO (iLR-DPO) to penalize response length. Our empirical results show that iLR-DPO can enhance a 7B model to perform on par with GPT-4 without increasing verbosity. Specifically, our 7B model achieves a $50.5\%$ length-controlled win rate against $\texttt{GPT-4 Preview}$ on AlpacaEval 2.0, and excels across standard benchmarks including MT-Bench, Arena-Hard and OpenLLM Leaderboard. These results demonstrate the effectiveness of iterative DPO in aligning language models with human feedback.
Authors: Zhenyu Wu, Ziwei Wang, Xiuwei Xu, Jiwen Lu, Haibin Yan
Abstract: Enabling embodied agents to complete complex human instructions from natural language is crucial to autonomous systems in household services. Conventional methods can only accomplish human instructions in the known environment where all interactive objects are provided to the embodied agent, and directly deploying the existing approaches for the unknown environment usually generates infeasible plans that manipulate non-existing objects. On the contrary, we propose an embodied instruction following (EIF) method for complex tasks in the unknown environment, where the agent efficiently explores the unknown environment to generate feasible plans with existing objects to accomplish abstract instructions. Specifically, we build a hierarchical embodied instruction following framework including the high-level task planner and the low-level exploration controller with multimodal large language models. We then construct a semantic representation map of the scene with dynamic region attention to demonstrate the known visual clues, where the goal of task planning and scene exploration is aligned for human instruction. For the task planner, we generate the feasible step-by-step plans for human goal accomplishment according to the task completion process and the known visual clues. For the exploration controller, the optimal navigation or object interaction policy is predicted based on the generated step-wise plans and the known visual clues. The experimental results demonstrate that our method can achieve 45.09% success rate in 204 complex human instructions such as making breakfast and tidying rooms in large house-level scenes.
Authors: Wenxuan Zhou, Ravi Agrawal, Shujian Zhang, Sathish Reddy Indurthi, Sanqiang Zhao, Kaiqiang Song, Silei Xu, Chenguang Zhu
Abstract: Reinforcement learning from human feedback (RLHF) is a promising solution to align large language models (LLMs) more closely with human values. Off-policy preference optimization, where the preference data is obtained from other models, is widely adopted due to its cost efficiency and scalability. However, off-policy preference optimization often suffers from a distributional gap between the policy used for data collection and the target policy, leading to suboptimal optimization. In this paper, we propose a novel strategy to mitigate this problem by simulating on-policy learning with off-policy preference data. Our Weighted Preference Optimization (WPO) method adapts off-policy data to resemble on-policy data more closely by reweighting preference pairs according to their probability under the current policy. This method not only addresses the distributional gap problem but also enhances the optimization process without incurring additional costs. We validate our method on instruction following benchmarks including Alpaca Eval 2 and MT-bench. WPO not only outperforms Direct Preference Optimization (DPO) by up to 5.6% on Alpaca Eval 2 but also establishes a remarkable length-controlled winning rate against GPT-4-turbo of 48.6% based on Llama-3-8B-Instruct, making it the strongest 8B model on the leaderboard. We will release the code and models at https://github.com/wzhouad/WPO.
Authors: Belinda Z. Li, Emmy Liu, Alexis Ross, Abbas Zeitoun, Graham Neubig, Jacob Andreas
Abstract: When the world changes, so does the text that humans write about it. How do we build language models that can be easily updated to reflect these changes? One popular approach is retrieval-augmented generation, in which new documents are inserted into a knowledge base and retrieved during prediction for downstream tasks. Most prior work on these systems have focused on improving behavior during prediction through better retrieval or reasoning. This paper introduces ERASE, which instead improves model behavior when new documents are acquired, by incrementally deleting or rewriting other entries in the knowledge base each time a document is added. In two new benchmark datasets evaluating models' ability to answer questions about a stream of news articles or conversations, ERASE improves accuracy relative to conventional retrieval-augmented generation by 7-13% (Mixtral-8x7B) and 6-10% (Llama-3-8B) absolute. Code and data are available at https://github.com/belindal/ERASE
Authors: Ziyu Liu, Tao Chu, Yuhang Zang, Xilin Wei, Xiaoyi Dong, Pan Zhang, Zijian Liang, Yuanjun Xiong, Yu Qiao, Dahua Lin, Jiaqi Wang
Abstract: Generating natural and meaningful responses to communicate with multi-modal human inputs is a fundamental capability of Large Vision-Language Models(LVLMs). While current open-source LVLMs demonstrate promising performance in simplified scenarios such as single-turn single-image input, they fall short in real-world conversation scenarios such as following instructions in a long context history with multi-turn and multi-images. Existing LVLM benchmarks primarily focus on single-choice questions or short-form responses, which do not adequately assess the capabilities of LVLMs in real-world human-AI interaction applications. Therefore, we introduce MMDU, a comprehensive benchmark, and MMDU-45k, a large-scale instruction tuning dataset, designed to evaluate and improve LVLMs' abilities in multi-turn and multi-image conversations. We employ the clustering algorithm to ffnd the relevant images and textual descriptions from the open-source Wikipedia and construct the question-answer pairs by human annotators with the assistance of the GPT-4o model. MMDU has a maximum of 18k image+text tokens, 20 images, and 27 turns, which is at least 5x longer than previous benchmarks and poses challenges to current LVLMs. Our in-depth analysis of 15 representative LVLMs using MMDU reveals that open-source LVLMs lag behind closed-source counterparts due to limited conversational instruction tuning data. We demonstrate that ffne-tuning open-source LVLMs on MMDU-45k signiffcantly address this gap, generating longer and more accurate conversations, and improving scores on MMDU and existing benchmarks (MMStar: +1.1%, MathVista: +1.5%, ChartQA:+1.2%). Our contributions pave the way for bridging the gap between current LVLM models and real-world application demands. This project is available at https://github.com/Liuziyu77/MMDU.
Authors: Fei Wang, Wenxuan Zhou, James Y. Huang, Nan Xu, Sheng Zhang, Hoifung Poon, Muhao Chen
Abstract: Direct preference optimization (DPO) has shown to be an effective method for large language model (LLM) alignment. Recent works have attempted to apply DPO to multimodal scenarios but have found it challenging to achieve consistent improvement. Through a comparative experiment, we identify the unconditional preference problem in multimodal preference optimization, where the model overlooks the image condition. To address this problem, we propose mDPO, a multimodal DPO objective that prevents the over-prioritization of language-only preferences by also optimizing image preference. Moreover, we introduce a reward anchor that forces the reward to be positive for chosen responses, thereby avoiding the decrease in their likelihood -- an intrinsic problem of relative preference optimization. Experiments on two multimodal LLMs of different sizes and three widely used benchmarks demonstrate that mDPO effectively addresses the unconditional preference problem in multimodal preference optimization and significantly improves model performance, particularly in reducing hallucination.
Authors: Akira Matsui, Emilio Ferrara
Abstract: To extract essential information from complex data, computer scientists have been developing machine learning models that learn low-dimensional representation mode. From such advances in machine learning research, not only computer scientists but also social scientists have benefited and advanced their research because human behavior or social phenomena lies in complex data. However, this emerging trend is not well documented because different social science fields rarely cover each other's work, resulting in fragmented knowledge in the literature. To document this emerging trend, we survey recent studies that apply word embedding techniques to human behavior mining. We built a taxonomy to illustrate the methods and procedures used in the surveyed papers, aiding social science researchers in contextualizing their research within the literature on word embedding applications. This survey also conducts a simple experiment to warn that common similarity measurements used in the literature could yield different results even if they return consistent results at an aggregate level.
Authors: Roy Abel, Shimon Ullman
Abstract: As part of understanding how the brain learns, ongoing work seeks to combine biological knowledge and current artificial intelligence (AI) modeling in an attempt to find an efficient biologically plausible learning scheme. Current models of biologically plausible learning often use a cortical-like combination of bottom-up (BU) and top-down (TD) processing, where the TD part carries feedback signals used for learning. However, in the visual cortex, the TD pathway plays a second major role of visual attention, by guiding the visual process to locations and tasks of interest. A biological model should therefore combine the two tasks, and learn to guide the visual process. We introduce a model that uses a cortical-like combination of BU and TD processing that naturally integrates the two major functions of the TD stream. The integrated model is obtained by an appropriate connectivity pattern between the BU and TD streams, a novel processing cycle that uses the TD part twice, and the use of 'Counter-Hebb' learning that operates across the streams. We show that the 'Counter-Hebb' mechanism can provide an exact backpropagation synaptic modification. We further demonstrate the model's ability to guide the visual stream to perform a task of interest, achieving competitive performance compared with AI models on standard multi-task learning benchmarks. The successful combination of learning and visual guidance could provide a new view on combining BU and TD processing in human vision, and suggests possible directions for both biologically plausible models and artificial instructed models, such as vision-language models (VLMs).
Authors: Kailas Vodrahalli, James Zou
Abstract: As generative AI becomes more prevalent, it is important to study how human users interact with such models. In this work, we investigate how people use text-to-image models to generate desired target images. To study this interaction, we created ArtWhisperer, an online game where users are given a target image and are tasked with iteratively finding a prompt that creates a similar-looking image as the target. Through this game, we recorded over 50,000 human-AI interactions; each interaction corresponds to one text prompt created by a user and the corresponding generated image. The majority of these are repeated interactions where a user iterates to find the best prompt for their target image, making this a unique sequential dataset for studying human-AI collaborations. In an initial analysis of this dataset, we identify several characteristics of prompt interactions and user strategies. People submit diverse prompts and are able to discover a variety of text descriptions that generate similar images. Interestingly, prompt diversity does not decrease as users find better prompts. We further propose a new metric to quantify the steerability of AI using our dataset. We define steerability as the expected number of interactions required to adequately complete a task. We estimate this value by fitting a Markov chain for each target task and calculating the expected time to reach an adequate score in the Markov chain. We quantify and compare AI steerability across different types of target images and two different models, finding that images of cities and natural world images are more steerable than artistic and fantasy images. These findings provide insights into human-AI interaction behavior, present a concrete method of assessing AI steerability, and demonstrate the general utility of the ArtWhisperer dataset.
Authors: Dezhao Yang, Jianghong Ma, Shanshan Feng, Haijun Zhang, Zhao Zhang
Abstract: In the information age, recommendation systems are vital for efficiently filtering information and identifying user preferences. Online social platforms have enriched these systems by providing valuable auxiliary information. Socially connected users are assumed to share similar preferences, enhancing recommendation accuracy and addressing cold start issues. However, empirical findings challenge the assumption, revealing that certain social connections can actually harm system performance. Our statistical analysis indicates a significant amount of noise in the social network, where many socially connected users do not share common interests. To address this issue, we propose an innovative \underline{I}nterest-aware \underline{D}enoising and \underline{V}iew-guided \underline{T}uning (IDVT) method for the social recommendation. The first ID part effectively denoises social connections. Specifically, the denoising process considers both social network structure and user interaction interests in a global view. Moreover, in this global view, we also integrate denoised social information (social domain) into the propagation of the user-item interactions (collaborative domain) and aggregate user representations from two domains using a gating mechanism. To tackle potential user interest loss and enhance model robustness within the global view, our second VT part introduces two additional views (local view and dropout-enhanced view) for fine-tuning user representations in the global view through contrastive learning. Extensive evaluations on real-world datasets with varying noise ratios demonstrate the superiority of IDVT over state-of-the-art social recommendation methods.
Authors: Tom Yotam, Vadim Indelman
Abstract: Decision making under uncertainty is at the heart of any autonomous system acting with imperfect information. The cost of solving the decision making problem is exponential in the action and observation spaces, thus rendering it unfeasible for many online systems. This paper introduces a novel approach to efficient decision-making, by partitioning the high-dimensional observation space. Using the partitioned observation space, we formulate analytical bounds on the expected information-theoretic reward, for general belief distributions. These bounds are then used to plan efficiently while keeping performance guarantees. We show that the bounds are adaptive, computationally efficient, and that they converge to the original solution. We extend the partitioning paradigm and present a hierarchy of partitioned spaces that allows greater efficiency in planning. We then propose a specific variant of these bounds for Gaussian beliefs and show a theoretical performance improvement of at least a factor of 4. Finally, we compare our novel method to other state of the art algorithms in active SLAM scenarios, in simulation and in real experiments. In both cases we show a significant speed-up in planning with performance guarantees.
Authors: Yi Wang, Jieliang Luo, Adam Gaier, Evan Atherton, Hilmar Koch
Abstract: World-building, the process of developing both the narrative and physical world of a game, plays a vital role in the game's experience. Critically acclaimed independent and AAA video games are praised for strong world building, with game maps that masterfully intertwine with and elevate the narrative, captivating players and leaving a lasting impression. However, designing game maps that support a desired narrative is challenging, as it requires satisfying complex constraints from various considerations. Most existing map generation methods focus on considerations about gameplay mechanics or map topography, while the need to support the story is typically neglected. As a result, extensive manual adjustment is still required to design a game world that facilitates particular stories. In this work, we approach this problem by introducing an extra layer of plot facility layout design that is independent of the underlying map generation method in a world-building pipeline. Concretely, we present a system that leverages Reinforcement Learning (RL) to automatically assign concrete locations on a game map to abstract locations mentioned in a given story (plot facilities), following spatial constraints derived from the story. A decision-making agent moves the plot facilities around, considering their relationship to the map and each other, to locations on the map that best satisfy the constraints of the story. Our system considers input from multiple modalities: map images as pixels, facility locations as real values, and story constraints expressed in natural language. We develop a method of generating datasets of facility layout tasks, create an RL environment to train and evaluate RL models, and further analyze the behaviors of the agents through a group of comprehensive experiments and ablation studies, aiming to provide insights for RL-based plot facility layout design.
Authors: Junchi Yu, Ran He, Rex Ying
Abstract: Large Language Models (LLMs) have achieved remarkable success in reasoning tasks with the development of prompting methods. However, existing prompting approaches cannot reuse insights of solving similar problems and suffer from accumulated errors in multi-step reasoning, since they prompt LLMs to reason \textit{from scratch}. To address these issues, we propose \textbf{\textit{Thought Propagation} (TP)}, which explores the analogous problems and leverages their solutions to enhance the complex reasoning ability of LLMs. These analogous problems are related to the input one, with reusable solutions and problem-solving strategies. Thus, it is promising to propagate insights of solving previous analogous problems to inspire new problem-solving. To achieve this, TP first prompts LLMs to propose and solve a set of analogous problems that are related to the input one. Then, TP reuses the results of analogous problems to directly yield a new solution or derive a knowledge-intensive plan for execution to amend the initial solution obtained from scratch. TP is compatible with existing prompting approaches, allowing plug-and-play generalization and enhancement in a wide range of tasks without much labor in task-specific prompt engineering. Experiments across three challenging tasks demonstrate TP enjoys a substantial improvement over the baselines by an average of 12\% absolute increase in finding the optimal solutions in Shortest-path Reasoning, 13\% improvement of human preference in Creative Writing, and 15\% enhancement in the task completion rate of LLM-Agent Planning.
Authors: Weiyu Ma, Qirui Mi, Xue Yan, Yuqiao Wu, Runji Lin, Haifeng Zhang, Jun Wang
Abstract: StarCraft II is a challenging benchmark for AI agents due to the necessity of both precise micro level operations and strategic macro awareness. Previous works, such as Alphastar and SCC, achieve impressive performance on tackling StarCraft II , however, still exhibit deficiencies in long term strategic planning and strategy interpretability. Emerging large language model (LLM) agents, such as Voyage and MetaGPT, presents the immense potential in solving intricate tasks. Motivated by this, we aim to validate the capabilities of LLMs on StarCraft II, a highly complex RTS game.To conveniently take full advantage of LLMs` reasoning abilities, we first develop textual StratCraft II environment, called TextStarCraft II, which LLM agent can interact. Secondly, we propose a Chain of Summarization method, including single frame summarization for processing raw observations and multi frame summarization for analyzing game information, providing command recommendations, and generating strategic decisions. Our experiment consists of two parts: first, an evaluation by human experts, which includes assessing the LLMs`s mastery of StarCraft II knowledge and the performance of LLM agents in the game; second, the in game performance of LLM agents, encompassing aspects like win rate and the impact of Chain of Summarization.Experiment results demonstrate that: 1. LLMs possess the relevant knowledge and complex planning abilities needed to address StarCraft II scenarios; 2. Human experts consider the performance of LLM agents to be close to that of an average player who has played StarCraft II for eight years; 3. LLM agents are capable of defeating the built in AI at the Harder(Lv5) difficulty level. We have open sourced the code and released demo videos of LLM agent playing StarCraft II.
Authors: Weidong Guo, Jiuding Yang, Kaitong Yang, Xiangyang Li, Zhuwei Rao, Yu Xu, Di Niu
Abstract: The fine-tuning of Large Language Models (LLMs) specialized in code generation has seen notable advancements through the use of open-domain coding queries. Despite the successes, existing methodologies like Evol-Instruct encounter performance limitations, impeding further enhancements in code generation tasks. This paper examines the constraints of existing prompt evolution techniques and introduces a novel approach, Instruction Fusion (IF). IF innovatively combines two distinct prompts through a hybridization process, thereby enhancing the evolution of training prompts for code LLMs. Our experimental results reveal that the proposed novel method effectively addresses the shortcomings of prior methods, significantly improving the performance of Code LLMs across five code generation benchmarks, namely HumanEval, HumanEval+, MBPP, MBPP+ and MultiPL-E, which underscore the effectiveness of Instruction Fusion in advancing the capabilities of LLMs in code generation.
Authors: Liman Wang, Hanyang Zhong
Abstract: This study explores integrating large language models (LLMs) with situational awareness-based planning (SAP) to enhance the decision-making capabilities of AI agents in dynamic and uncertain environments. We employ a multi-agent reasoning framework to develop a methodology that anticipates and actively mitigates potential risks through iterative feedback and evaluation processes. Our approach diverges from traditional automata theory by incorporating the complexity of human-centric interactions into the planning process, thereby expanding the planning scope of LLMs beyond structured and predictable scenarios. The results demonstrate significant improvements in the model's ability to provide comparative safe actions within hazard interactions, offering a perspective on proactive and reactive planning strategies. This research highlights the potential of LLMs to perform human-like action planning, thereby paving the way for more sophisticated, reliable, and safe AI systems in unpredictable real-world applications.
Authors: Chuanyang Jin, Yutong Wu, Jing Cao, Jiannan Xiang, Yen-Ling Kuo, Zhiting Hu, Tomer Ullman, Antonio Torralba, Joshua B. Tenenbaum, Tianmin Shu
Abstract: Theory of Mind (ToM), the ability to understand people's mental states, is an essential ingredient for developing machines with human-level social intelligence. Recent machine learning models, particularly large language models, seem to show some aspects of ToM understanding. However, existing ToM benchmarks use unimodal datasets - either video or text. Human ToM, on the other hand, is more than video or text understanding. People can flexibly reason about another person's mind based on conceptual representations (e.g., goals, beliefs, plans) extracted from any available data. To address this, we introduce a multimodal Theory of Mind question answering (MMToM-QA) benchmark. MMToM-QA comprehensively evaluates machine ToM both on multimodal data and on different kinds of unimodal data about a person's activity in a household environment. To engineer multimodal ToM capacity, we propose a novel method, BIP-ALM (Bayesian Inverse Planning Accelerated by Language Models). BIP-ALM extracts unified representations from multimodal data and utilizes language models for scalable Bayesian inverse planning. We conducted a systematic comparison of human performance, BIP-ALM, and state-of-the-art models, including GPT-4. The experiments demonstrate that large language models and large multimodal models still lack robust ToM capacity. BIP-ALM, on the other hand, shows promising results, by leveraging the power of both model-based mental inference and language models.
Authors: Zane Durante, Bidipta Sarkar, Ran Gong, Rohan Taori, Yusuke Noda, Paul Tang, Ehsan Adeli, Shrinidhi Kowshika Lakshmikanth, Kevin Schulman, Arnold Milstein, Demetri Terzopoulos, Ade Famoti, Noboru Kuno, Ashley Llorens, Hoi Vo, Katsu Ikeuchi, Li Fei-Fei, Jianfeng Gao, Naoki Wake, Qiuyuan Huang
Abstract: The development of artificial intelligence systems is transitioning from creating static, task-specific models to dynamic, agent-based systems capable of performing well in a wide range of applications. We propose an Interactive Agent Foundation Model that uses a novel multi-task agent training paradigm for training AI agents across a wide range of domains, datasets, and tasks. Our training paradigm unifies diverse pre-training strategies, including visual masked auto-encoders, language modeling, and next-action prediction, enabling a versatile and adaptable AI framework. We demonstrate the performance of our framework across three separate domains -- Robotics, Gaming AI, and Healthcare. Our model demonstrates its ability to generate meaningful and contextually relevant outputs in each area. The strength of our approach lies in its generality, leveraging a variety of data sources such as robotics sequences, gameplay data, large-scale video datasets, and textual information for effective multimodal and multi-task learning. Our approach provides a promising avenue for developing generalist, action-taking, multimodal systems.
Authors: Edwin Zhang, Sadie Zhao, Tonghan Wang, Safwan Hossain, Henry Gasztowtt, Stephan Zheng, David C. Parkes, Milind Tambe, Yiling Chen
Abstract: Artificial Intelligence (AI) holds promise as a technology that can be used to improve government and economic policy-making. This paper proposes a new research agenda towards this end by introducing Social Environment Design, a general framework for the use of AI for automated policy-making that connects with the Reinforcement Learning, EconCS, and Computational Social Choice communities. The framework seeks to capture general economic environments, includes voting on policy objectives, and gives a direction for the systematic analysis of government and economic policy through AI simulation. We highlight key open problems for future research in AI-based policy-making. By solving these challenges, we hope to achieve various social welfare objectives, thereby promoting more ethical and responsible decision making.
Authors: Long Li, Xuzheng He
Abstract: Program-of-Thought (PoT) replaces natural language-based Chain-of-Thought (CoT) as the most popular method in Large Language Models (LLMs) mathematical reasoning tasks by utilizing external tool calls to circumvent computational errors. However, our evaluation of the GPT-4 and Llama series reveals that using PoT introduces more reasoning errors, such as incorrect formulas or flawed logic, compared to CoT. To address this issue, we propose Human-Think Language (HTL), which leverages a suite of strategies that help integrate PoT and CoT, encompassing: (1) a new generation paradigm that uses full CoT reasoning to control code generation. (2) Focus Attention, that directs model attention to the CoT reasoning during PoT to generate more logical code. (3) reinforcement learning that utilizes the accuracy of both CoT and PoT responses as rewards to prevent repetitive reasoning steps in LLMs when solving difficult math problems. Our method achieves an average improvement of 6.5% on the Llama-Base model and 4.3% on the Mistral-Base model across 8 mathematical calculation datasets. It also shows significant effectiveness on five out-of-domain datasets by controlling the model's information flow, exhibiting strong transferability. Additionally, HTL shows the most significant improvement in non-mathematical natural language inference task, contributing to a unified reasoning task framework
Authors: Ruoxi Cheng, Haoxuan Ma, Shuirong Cao, Tianyu Shi
Abstract: Biases in LLMs can harm user experience and societal outcomes. Current bias mitigation methods such as RLHF usually rely on costly human feedback, lack transferability to other topics, and show poor performance. We find that informing the LLMs that their generated content is not generated by them and querying about potential biases greatly boosts their awareness and ability to mitigate biases. Based on this, we propose RLDF (Reinforcement Learning from Multi-role Debates as Feedback), replacing human feedback with AI for bias mitigation. RLDF engages LLMs in multi-role debates to expose biases and gradually reduce biases in each iteration using a ranking scoring mechanism. The dialogue are then used to create a dataset composed of both high bias and low bias instances to train the reward model in reinforcement learning. This dataset can be generated by the same LLM for self-reflection or a superior LLM like an API which guides the former one in a teacher-student mode. Experimental results across different LLMs and types of bias show the effectiveness of our approach in bias mitigation.
Authors: Haoyuan Jiang, Ziyue Li, Hua Wei, Xuantang Xiong, Jingqing Ruan, Jiaming Lu, Hangyu Mao, Rui Zhao
Abstract: The effectiveness of traffic light control has been significantly improved by current reinforcement learning-based approaches via better cooperation among multiple traffic lights. However, a persisting issue remains: how to obtain a multi-agent traffic signal control algorithm with remarkable transferability across diverse cities? In this paper, we propose a Transformer on Transformer (TonT) model for cross-city meta multi-agent traffic signal control, named as X-Light: We input the full Markov Decision Process trajectories, and the Lower Transformer aggregates the states, actions, rewards among the target intersection and its neighbors within a city, and the Upper Transformer learns the general decision trajectories across different cities. This dual-level approach bolsters the model's robust generalization and transferability. Notably, when directly transferring to unseen scenarios, ours surpasses all baseline methods with +7.91% on average, and even +16.3% in some cases, yielding the best results.
Authors: Fan Wang, Chuan Lin, Yang Cao, Yu Kang
Abstract: In-context learning (ICL) is becoming increasingly appealing to the AI community due to its flexibility, generality, sample efficiency, and exemption from artificial optimization skills. It is desirable to further enhance the generality and capability of ICL, which gives rise to the concept of general-purpose in-context learning (GPICL). We aim to extend ICL to address a broader range of tasks with an extended learning horizon and higher improvement potential, albeit with relatively limited zero-shot generalization. To this end, we introduce two lightweight but insightful benchmarks specifically crafted to train and evaluate GPICL functionalities. Each benchmark includes a vast number of tasks characterized by significant task variance, featuring minimal inductive bias. These tasks are also designed to facilitate lifelong in-context learning through continuous generation and interaction. These features pose significant challenges for models that rely on context or interactions to improve their proficiency, including language models, decision models, and world models. Our experiments reveal that the scale of parameters alone may not be crucial for ICL or GPICL, suggesting alternative approaches such as increasing the scale of contexts and memory states.
Authors: Xinzhe Li
Abstract: Recent advancements in Large Language Models (LLMs) have catalyzed the development of sophisticated frameworks for developing LLM-based agents. However, the complexity of these frameworks r poses a hurdle for nuanced differentiation at a granular level, a critical aspect for enabling efficient implementations across different frameworks and fostering future research. Hence, the primary purpose of this survey is to facilitate a cohesive understanding of diverse recently proposed frameworks by identifying common workflows and reusable LLM-Profiled Components (LMPCs).
Authors: Venkat Venkatasubramanian
Abstract: Large Language Models (LLMs) are often criticized for lacking true "understanding" and the ability to "reason" with their knowledge, being seen merely as autocomplete systems. We believe that this assessment might be missing a nuanced insight. We suggest that LLMs do develop a kind of empirical "understanding" that is "geometry"-like, which seems adequate for a range of applications in NLP, computer vision, coding assistance, etc. However, this "geometric" understanding, built from incomplete and noisy data, makes them unreliable, difficult to generalize, and lacking in inference capabilities and explanations, similar to the challenges faced by heuristics-based expert systems decades ago. To overcome these limitations, we suggest that LLMs should be integrated with an "algebraic" representation of knowledge that includes symbolic AI elements used in expert systems. This integration aims to create large knowledge models (LKMs) that not only possess "deep" knowledge grounded in first principles, but also have the ability to reason and explain, mimicking human expert capabilities. To harness the full potential of generative AI safely and effectively, a paradigm shift is needed from LLM to more comprehensive LKM.
Authors: Teun van der Weij, Felix Hofst\"atter, Ollie Jaffe, Samuel F. Brown, Francis Rhys Ward
Abstract: Trustworthy capability evaluations are crucial for ensuring the safety of AI systems, and are becoming a key component of AI regulation. However, the developers of an AI system, or the AI system itself, may have incentives for evaluations to understate the AI's actual capability. These conflicting interests lead to the problem of sandbagging $\unicode{x2013}$ which we define as "strategic underperformance on an evaluation". In this paper we assess sandbagging capabilities in contemporary language models (LMs). We prompt frontier LMs, like GPT-4 and Claude 3 Opus, to selectively underperform on dangerous capability evaluations, while maintaining performance on general (harmless) capability evaluations. Moreover, we find that models can be fine-tuned, on a synthetic dataset, to hide specific capabilities unless given a password. This behaviour generalizes to high-quality, held-out benchmarks such as WMDP. In addition, we show that both frontier and smaller models can be prompted, or password-locked, to target specific scores on a capability evaluation. Even more, we found that a capable password-locked model (Llama 3 70b) is reasonably able to emulate a less capable model (Llama 2 7b). Overall, our results suggest that capability evaluations are vulnerable to sandbagging. This vulnerability decreases the trustworthiness of evaluations, and thereby undermines important safety decisions regarding the development and deployment of advanced AI systems.
Authors: Carson Denison, Monte MacDiarmid, Fazl Barez, David Duvenaud, Shauna Kravec, Samuel Marks, Nicholas Schiefer, Ryan Soklaski, Alex Tamkin, Jared Kaplan, Buck Shlegeris, Samuel R. Bowman, Ethan Perez, Evan Hubinger
Abstract: In reinforcement learning, specification gaming occurs when AI systems learn undesired behaviors that are highly rewarded due to misspecified training goals. Specification gaming can range from simple behaviors like sycophancy to sophisticated and pernicious behaviors like reward-tampering, where a model directly modifies its own reward mechanism. However, these more pernicious behaviors may be too complex to be discovered via exploration. In this paper, we study whether Large Language Model (LLM) assistants which find easily discovered forms of specification gaming will generalize to perform rarer and more blatant forms, up to and including reward-tampering. We construct a curriculum of increasingly sophisticated gameable environments and find that training on early-curriculum environments leads to more specification gaming on remaining environments. Strikingly, a small but non-negligible proportion of the time, LLM assistants trained on the full curriculum generalize zero-shot to directly rewriting their own reward function. Retraining an LLM not to game early-curriculum environments mitigates, but does not eliminate, reward-tampering in later environments. Moreover, adding harmlessness training to our gameable environments does not prevent reward-tampering. These results demonstrate that LLMs can generalize from common forms of specification gaming to more pernicious reward tampering and that such behavior may be nontrivial to remove.
Authors: Bruce W. Lee, Yoo Sung Jang, Jason Hyung-Jong Lee
Abstract: We report two essential improvements in readability assessment: 1. three novel features in advanced semantics and 2. the timely evidence that traditional ML models (e.g. Random Forest, using handcrafted features) can combine with transformers (e.g. RoBERTa) to augment model performance. First, we explore suitable transformers and traditional ML models. Then, we extract 255 handcrafted linguistic features using self-developed extraction software. Finally, we assemble those to create several hybrid models, achieving state-of-the-art (SOTA) accuracy on popular datasets in readability assessment. The use of handcrafted features help model performance on smaller datasets. Notably, our RoBERTA-RF-T1 hybrid achieves the near-perfect classification accuracy of 99%, a 20.3% increase from the previous SOTA.
Authors: Maximilian Lam, Michael Mitzenmacher, Vijay Janapa Reddi, Gu-Yeon Wei, David Brooks
Abstract: Multiparty computation approaches to secure neural network inference commonly rely on garbled circuits for securely executing nonlinear activation functions. However, garbled circuits require excessive communication between server and client, impose significant storage overheads, and incur large runtime penalties. To reduce these costs, we propose an alternative to garbled circuits: Tabula, an algorithm based on secure lookup tables. Our approach precomputes lookup tables during an offline phase that contains the result of all possible nonlinear function calls. Because these tables incur exponential storage costs in the number of operands and the precision of the input values, we use quantization to reduce these storage costs to make this approach practical. This enables an online phase where securely computing the result of a nonlinear function requires just a single round of communication, with communication cost equal to twice the number of bits of the input to the nonlinear function. In practice our approach costs 2 bytes of communication per nonlinear function call in the online phase. Compared to garbled circuits with 8-bit quantized inputs, when computing individual nonlinear functions during the online phase, experiments show Tabula with 8-bit activations uses between $280$-$560 \times$ less communication, is over $100\times$ faster, and uses a comparable (within a factor of 2) amount of storage; compared against other state-of-the-art protocols Tabula achieves greater than $40\times$ communication reduction. This leads to significant performance gains over garbled circuits with quantized inputs during the online phase of secure inference of neural networks: Tabula reduces end-to-end inference communication by up to $9 \times$ and achieves an end-to-end inference speedup of up to $50 \times$, while imposing comparable storage and offline preprocessing costs.
Authors: Sahisnu Mazumder, Bing Liu
Abstract: Dialogue systems, commonly known as chatbots, have gained escalating popularity in recent times due to their wide-spread applications in carrying out chit-chat conversations with users and task-oriented dialogues to accomplish various user tasks. Existing chatbots are usually trained from pre-collected and manually-labeled data and/or written with handcrafted rules. Many also use manually-compiled knowledge bases (KBs). Their ability to understand natural language is still limited, and they tend to produce many errors resulting in poor user satisfaction. Typically, they need to be constantly improved by engineers with more labeled data and more manually compiled knowledge. This book introduces the new paradigm of lifelong learning dialogue systems to endow chatbots the ability to learn continually by themselves through their own self-initiated interactions with their users and working environments to improve themselves. As the systems chat more and more with users or learn more and more from external sources, they become more and more knowledgeable and better and better at conversing. The book presents the latest developments and techniques for building such continual learning dialogue systems that continuously learn new language expressions and lexical and factual knowledge during conversation from users and off conversation from external sources, acquire new training examples during conversation, and learn conversational skills. Apart from these general topics, existing works on continual learning of some specific aspects of dialogue systems are also surveyed. The book concludes with a discussion of open challenges for future research.
Authors: Bruce W. Lee, Jason Hyung-Jong Lee
Abstract: We propose the novel adaptation of a pre-trained seq2seq model for readability assessment. We prove that a seq2seq model - T5 or BART - can be adapted to discern which text is more difficult from two given texts (pairwise). As an exploratory study to prompt-learn a neural network for text readability in a text-to-text manner, we report useful tips for future work in seq2seq training and ranking-based approach to readability assessment. Specifically, we test nine input-output formats/prefixes and show that they can significantly influence the final model performance. Also, we argue that the combination of text-to-text training and pairwise ranking setup 1) enables leveraging multiple parallel text simplification data for teaching readability and 2) trains a neural model for the general concept of readability (therefore, better cross-domain generalization). At last, we report a 99.6% pairwise classification accuracy on Newsela and a 98.7% for OneStopEnglish, through a joint training approach.
Authors: Shangxi Wu, Qiuyang He, Dongyuan Lu, Jian Yu, Jitao Sang
Abstract: With the swift advancement of deep learning, state-of-the-art algorithms have been utilized in various social situations. Nonetheless, some algorithms have been discovered to exhibit biases and provide unequal results. The current debiasing methods face challenges such as poor utilization of data or intricate training requirements. In this work, we found that the backdoor attack can construct an artificial bias similar to the model bias derived in standard training. Considering the strong adjustability of backdoor triggers, we are motivated to mitigate the model bias by carefully designing reverse artificial bias created from backdoor attack. Based on this, we propose a backdoor debiasing framework based on knowledge distillation, which effectively reduces the model bias from original data and minimizes security risks from the backdoor attack. The proposed solution is validated on both image and structured datasets, showing promising results. This work advances the understanding of backdoor attacks and highlights its potential for beneficial applications. The code for the study can be found at \url{https://anonymous.4open.science/r/DwB-BC07/}.
Authors: Pengyuan Zhou
Abstract: Incorporating artificial intelligence (AI) technology, particularly large language models (LLMs), is becoming increasingly vital for developing immersive and interactive metaverse experiences. GPT, a representative LLM developed by OpenAI, is leading LLM development and gaining attention for its potential in building the metaverse. The article delves into the pros and cons of utilizing GPT for metaverse-based education, entertainment, personalization, and support. Dynamic and personalized experiences are possible with this technology, but there are also legitimate privacy, bias, and ethical issues to consider. This article aims to help readers understand the possible influence of GPT, according to its unique technological advantages, on the metaverse and how it may be used to effectively create a more immersive and engaging virtual environment by evaluating these opportunities and obstacles.
Authors: Qijie Bai, Jiawen Guo, Haiwei Zhang, Changli Nie, Lin Zhang, Xiaojie Yuan
Abstract: Temporal heterogeneous information network (temporal HIN) embedding, aiming to represent various types of nodes of different timestamps into low dimensional spaces while preserving structural and semantic information, is of vital importance in diverse real-life tasks. Researchers have made great efforts on temporal HIN embedding in Euclidean spaces and got some considerable achievements. However, there is always a fundamental conflict that many real-world networks show hierarchical property and power-law distribution, and are not isometric of Euclidean spaces. Recently, representation learning in hyperbolic spaces has been proved to be valid for data with hierarchical and power-law structure. Inspired by this character, we propose a hyperbolic heterogeneous temporal network embedding ($\text{H}^2\text{TNE}$) model for temporal HINs. Specifically, we leverage a temporally and heterogeneously double-constrained random walk strategy to capture the structural and semantic information, and then calculate the embedding by exploiting hyperbolic distance in proximity measurement. Experimental results show that our method has superior performance on temporal link prediction and node classification compared with SOTA models.
Authors: Ahmed Salih, Zahra Raisi-Estabragh, Ilaria Boscolo Galazzo, Petia Radeva, Steffen E. Petersen, Gloria Menegaz, Karim Lekadir
Abstract: eXplainable artificial intelligence (XAI) methods have emerged to convert the black box of machine learning (ML) models into a more digestible form. These methods help to communicate how the model works with the aim of making ML models more transparent and increasing the trust of end-users into their output. SHapley Additive exPlanations (SHAP) and Local Interpretable Model Agnostic Explanation (LIME) are two widely used XAI methods, particularly with tabular data. In this perspective piece, we discuss the way the explainability metrics of these two methods are generated and propose a framework for interpretation of their outputs, highlighting their weaknesses and strengths. Specifically, we discuss their outcomes in terms of model-dependency and in the presence of collinearity among the features, relying on a case study from the biomedical domain (classification of individuals with or without myocardial infarction). The results indicate that SHAP and LIME are highly affected by the adopted ML model and feature collinearity, raising a note of caution on their usage and interpretation.
Authors: Yuanhang Zheng, Zhixing Tan, Peng Li, Yang Liu
Abstract: Black-box prompt tuning employs derivative-free optimization algorithms to learn prompts within low-dimensional subspaces rather than back-propagating through the network of Large Language Models (LLMs). Recent studies reveal that black-box prompt tuning lacks versatility across tasks and LLMs, which we believe is related to the suboptimal choice of subspaces. In this paper, we introduce Black-box prompt tuning with Subspace Learning (BSL) to enhance the versatility of black-box prompt tuning. Based on the assumption that nearly optimal prompts for similar tasks reside in a common subspace, we propose identifying such subspaces through meta-learning on a collection of similar source tasks. Consequently, for a target task that shares similarities with the source tasks, we expect that optimizing within the identified subspace can yield a prompt that performs well on the target task. Experimental results confirm that our BSL framework consistently achieves competitive performance across various downstream tasks and LLMs.
Authors: Philipp D. L\"osel, Jacob J. Relle, Samuel Vo{\ss}, Ramesch Raschidi, Regine Nessel, Johannes G\"orich, Mark O. Wielp\"utz, Thorsten L\"offler, Vincent Heuveline, Friedrich Kallinowski
Abstract: Abdominal wall defects often lead to pain, discomfort, and recurrence of incisional hernias, resulting in significant morbidity and repeated surgical repairs worldwide. Mesh repair for large hernias is usually based on the defect area with a fixed overlap, neglecting biomechanical factors such as muscle activation, intra-abdominal pressure, tissue elasticity, and abdominal wall distension. To address this issue, we present a biomechanical approach to incisional hernia repair that takes into account the unstable abdominal wall. Additionally, we introduce HEDI, a tool that uses computed tomography with Valsalva maneuver to automatically detect and assess hernia size, volume, and abdominal wall instability. Our first clinical application of HEDI in the preoperative evaluation of 31 patients shows significantly improved success rates compared to reported rates, with all patients remaining pain-free and experiencing no hernia recurrence after three years of follow-up.
Authors: Mattia Silvestri, Senne Berden, Jayanta Mandi, Ali \.Irfan Mahmuto\u{g}ullar{\i}, Brandon Amos, Tias Guns, Michele Lombardi
Abstract: Many real-world optimization problems contain parameters that are unknown before deployment time, either due to stochasticity or to lack of information (e.g., demand or travel times in delivery problems). A common strategy in such cases is to estimate said parameters via machine learning (ML) models trained to minimize the prediction error, which however is not necessarily aligned with the downstream task-level error. The decision-focused learning (DFL) paradigm overcomes this limitation by training to directly minimize a task loss, e.g. regret. Since the latter has non-informative gradients for combinatorial problems, state-of-the-art DFL methods introduce surrogates and approximations that enable training. But these methods exploit specific assumptions about the problem structures (e.g., convex or linear problems, unknown parameters only in the objective function). We propose an alternative method that makes no such assumptions, it combines stochastic smoothing with score function gradient estimation which works on any task loss. This opens up the use of DFL methods to nonlinear objectives, uncertain parameters in the problem constraints, and even two-stage stochastic optimization. Experiments show that it typically requires more epochs, but that it is on par with specialized methods and performs especially well for the difficult case of problems with uncertainty in the constraints, in terms of solution quality, scalability, or both.
Authors: Stefano Favaro, Boris Hanin, Domenico Marinucci, Ivan Nourdin, Giovanni Peccati
Abstract: We study the distribution of a fully connected neural network with random Gaussian weights and biases in which the hidden layer widths are proportional to a large constant $n$. Under mild assumptions on the non-linearity, we obtain quantitative bounds on normal approximations valid at large but finite $n$ and any fixed network depth. Our theorems show both for the finite-dimensional distributions and the entire process, that the distance between a random fully connected network (and its derivatives) to the corresponding infinite width Gaussian process scales like $n^{-\gamma}$ for $\gamma>0$, with the exponent depending on the metric used to measure discrepancy. Our bounds are strictly stronger in terms of their dependence on network width than any previously available in the literature; in the one-dimensional case, we also prove that they are optimal, i.e., we establish matching lower bounds.
Authors: Yanran Wang, Qiuchen Qian, David Boyle
Abstract: Reinforcement learning can provide effective reasoning for sequential decision-making problems with variable dynamics. Such reasoning in practical implementation, however, poses a persistent challenge in interpreting the reward function and the corresponding optimal policy. Consequently, representing sequential decision-making problems as probabilistic inference can have considerable value, as, in principle, the inference offers diverse and powerful mathematical tools to infer the stochastic dynamics whilst suggesting a probabilistic interpretation of policy optimization. In this study, we propose a novel Adaptive Wasserstein Variational Optimization, namely AWaVO, to tackle these interpretability challenges. Our approach uses formal methods to achieve the interpretability for convergence guarantee, training transparency, and intrinsic decision-interpretation. To demonstrate its practicality, we showcase guaranteed interpretability with an optimal global convergence rate in simulation and in practical quadrotor tasks. In comparison with state-of-the-art benchmarks including TRPO-IPO, PCPO and CRPO, we empirically verify that AWaVO offers a reasonable trade-off between high performance and sufficient interpretability.
Authors: Zhiyuan Peng, Xuyang Wu, Qifan Wang, Yi Fang
Abstract: Dense retrieval (DR) converts queries and documents into dense embeddings and measures the similarity between queries and documents in vector space. One of the challenges in DR is the lack of domain-specific training data. While DR models can learn from large-scale public datasets like MS MARCO through transfer learning, evidence shows that not all DR models and domains can benefit from transfer learning equally. Recently, some researchers have resorted to large language models (LLMs) to improve the zero-shot and few-shot DR models. However, the hard prompts or human-written prompts utilized in these works cannot guarantee the good quality of generated weak queries. To tackle this, we propose soft prompt tuning for augmenting DR (SPTAR): For each task, we leverage soft prompt-tuning to optimize a task-specific soft prompt on limited ground truth data and then prompt the LLMs to tag unlabeled documents with weak queries, yielding enough weak document-query pairs to train task-specific dense retrievers. We design a filter to select high-quality example document-query pairs in the prompt to further improve the quality of weak tagged queries. To the best of our knowledge, there is no prior work utilizing soft prompt tuning to augment DR models. The experiments demonstrate that SPTAR outperforms the unsupervised baselines BM25 and the recently proposed LLMs-based augmentation method for DR.
Authors: Tingwei Zhang, Rishi Jha, Eugene Bagdasaryan, Vitaly Shmatikov
Abstract: Multi-modal embeddings encode texts, images, thermal images, sounds, and videos into a single embedding space, aligning representations across different modalities (e.g., associate an image of a dog with a barking sound). In this paper, we show that multi-modal embeddings can be vulnerable to an attack we call "adversarial illusions." Given an image or a sound, an adversary can perturb it to make its embedding close to an arbitrary, adversary-chosen input in another modality. These attacks are cross-modal and targeted: the adversary can align any image or sound with any target of his choice. Adversarial illusions exploit proximity in the embedding space and are thus agnostic to downstream tasks and modalities, enabling a wholesale compromise of current and future tasks, as well as modalities not available to the adversary. Using ImageBind and AudioCLIP embeddings, we demonstrate how adversarially aligned inputs, generated without knowledge of specific downstream tasks, mislead image generation, text generation, zero-shot classification, and audio retrieval. We investigate transferability of illusions across different embeddings and develop a black-box version of our method that we use to demonstrate the first adversarial alignment attack on Amazon's commercial, proprietary Titan embedding. Finally, we analyze countermeasures and evasion attacks.
Authors: Yubiao Yue, Xiaoqiang Shi, Li Qin, Xinyue Zhang, Jialong Xu, Zipei Zheng, Zhenzhang Li, Yang Li
Abstract: Due to the absence of more efficient diagnostic tools, the spread of mpox continues to be unchecked. Although related studies have demonstrated the high efficiency of deep learning models in diagnosing mpox, key aspects such as model inference speed and parameter size have always been overlooked. Herein, an ultrafast and ultralight network named Fast-MpoxNet is proposed. Fast-MpoxNet, with only 0.27M parameters, can process input images at 68 frames per second (FPS) on the CPU. To detect subtle image differences and optimize model parameters better, Fast-MpoxNet incorporates an attention-based feature fusion module and a multiple auxiliary losses enhancement strategy. Experimental results indicate that Fast-MpoxNet, utilizing transfer learning and data augmentation, produces 98.40% classification accuracy for four classes on the mpox dataset. Furthermore, its Recall for early-stage mpox is 93.65%. Most importantly, an application system named Mpox-AISM V2 is developed, suitable for both personal computers and smartphones. Mpox-AISM V2 can rapidly and accurately diagnose mpox and can be easily deployed in various scenarios to offer the public real-time mpox diagnosis services. This work has the potential to mitigate future mpox outbreaks and pave the way for developing real-time diagnostic tools in the healthcare field.
Authors: Matias D. Cattaneo, Jason M. Klusowski, Boris Shigida
Abstract: In previous literature, backward error analysis was used to find ordinary differential equations (ODEs) approximating the gradient descent trajectory. It was found that finite step sizes implicitly regularize solutions because terms appearing in the ODEs penalize the two-norm of the loss gradients. We prove that the existence of similar implicit regularization in RMSProp and Adam depends on their hyperparameters and the training stage, but with a different "norm" involved: the corresponding ODE terms either penalize the (perturbed) one-norm of the loss gradients or, conversely, impede its reduction (the latter case being typical). We also conduct numerical experiments and discuss how the proven facts can influence generalization.
Authors: Jin Huang, Xingjian Zhang, Qiaozhu Mei, Jiaqi Ma
Abstract: Large language models (LLMs) are gaining increasing attention for their capability to process graphs with rich text attributes, especially in a zero-shot fashion. Recent studies demonstrate that LLMs obtain decent text classification performance on common text-rich graph benchmarks, and the performance can be improved by appending encoded structural information as natural languages into prompts. We aim to understand why the incorporation of structural information inherent in graph data can improve the prediction performance of LLMs. First, we rule out the concern of data leakage by curating a novel leakage-free dataset and conducting a comparative analysis alongside a previously widely-used dataset. Second, as past work usually encodes the ego-graph by describing the graph structure in natural language, we ask the question: do LLMs understand the graph structure in accordance with the intent of the prompt designers? Third, we investigate why LLMs can improve their performance after incorporating structural information. Our exploration of these questions reveals that (i) there is no substantial evidence that the performance of LLMs is significantly attributed to data leakage; (ii) instead of understanding prompts as graph structures as intended by the prompt designers, LLMs tend to process prompts more as contextual paragraphs and (iii) the most efficient elements of the local neighborhood included in the prompt are phrases that are pertinent to the node label, rather than the graph structure.
Authors: Zhaowei Zhang, Fengshuo Bai, Jun Gao, Yaodong Yang
Abstract: Personal values are a crucial factor behind human decision-making. Considering that Large Language Models (LLMs) have been shown to impact human decisions significantly, it is essential to make sure they accurately understand human values to ensure their safety. However, evaluating their grasp of these values is complex due to the value's intricate and adaptable nature. We argue that truly understanding values in LLMs requires considering both "know what" and "know why". To this end, we present a comprehensive evaluation metric, ValueDCG (Value Discriminator-Critique Gap), to quantitatively assess the two aspects with an engineering implementation. We assess four representative LLMs and provide compelling evidence that the growth rates of LLM's "know what" and "know why" capabilities do not align with increases in parameter numbers, resulting in a decline in the models' capacity to understand human values as larger amounts of parameters. This may further suggest that LLMs might craft plausible explanations based on the provided context without truly understanding their inherent value, indicating potential risks.
Authors: Mingyu Derek Ma, Jiun-Yu Kao, Arpit Gupta, Yu-Hsiang Lin, Wenbo Zhao, Tagyoung Chung, Wei Wang, Kai-Wei Chang, Nanyun Peng
Abstract: Models of various NLP tasks have been shown to exhibit stereotypes, and the bias in the question answering (QA) models is especially harmful as the output answers might be directly consumed by the end users. There have been datasets to evaluate bias in QA models, while bias mitigation technique for the QA models is still under-explored. In this work, we propose BMBI, an approach to mitigate the bias of multiple-choice QA models. Based on the intuition that a model would lean to be more biased if it learns from a biased example, we measure the bias level of a query instance by observing its influence on another instance. If the influenced instance is more biased, we derive that the query instance is biased. We then use the bias level detected as an optimization objective to form a multi-task learning setting in addition to the original QA task. We further introduce a new bias evaluation metric to quantify bias in a comprehensive and sensitive way. We show that our method could be applied to multiple QA formulations across multiple bias categories. It can significantly reduce the bias level in all 9 bias categories in the BBQ dataset while maintaining comparable QA accuracy.
Authors: Bruce W. Lee, Hyunsoo Cho, Kang Min Yoo
Abstract: In this work, we (1) introduce Curriculum Instruction Tuning, (2) explore the potential advantages of employing diverse curriculum strategies, and (3) delineate a synthetic instruction-response generation framework that complements our theoretical approach. Distinct from the existing instruction tuning dataset, our generation pipeline is systematically structured to emulate the sequential and orderly characteristic of human learning. Additionally, we describe a methodology for generating instruction-response datasets that extensively span the various stages of human education, from middle school through the graduate level, utilizing educational subject catalogs. Before training, we meticulously organize the instruction data to ensure that questions escalate in difficulty regarding (A) the subject matter and (B) the intricacy of the instructions. The findings of our study reveal that substantial improvements in performance can be achieved through the mere application of curriculum ordering to instruction data (achieving gains of +4.76 on TruthfulQA, +2.98 on MMLU, +2.8 on OpenbookQA, and +1.28 on ARC-hard) compared to random shuffling. This enhancement is achieved without incurring additional computational expenses. Through comprehensive experimentation, we observe that the advantages of our proposed method are consistently evident across nine benchmarks.
Authors: Ming-Hao Hsu, Kai-Wei Chang, Shang-Wen Li, Hung-yi Lee
Abstract: Ever since the development of GPT-3 in the natural language processing (NLP) field, in-context learning (ICL) has played an essential role in utilizing large language models (LLMs). By presenting the LM utterance-label demonstrations at the input, the LM can accomplish few-shot learning without relying on gradient descent or requiring explicit modification of its parameters. This enables the LM to perform various downstream tasks in a black-box manner. Despite the success of ICL in NLP, little work is exploring the possibility of ICL in speech processing. This study is the first work exploring ICL for speech classification tasks with textless speech LM. We first show that the current speech LM lacks the ICL capability. We then perform warmup training on the speech LM, equipping the LM with demonstration learning capability. This paper explores and proposes the first speech LM capable of performing unseen classification tasks in an ICL manner.
Authors: Yufei Wang, Zhou Xian, Feng Chen, Tsun-Hsuan Wang, Yian Wang, Katerina Fragkiadaki, Zackory Erickson, David Held, Chuang Gan
Abstract: We present RoboGen, a generative robotic agent that automatically learns diverse robotic skills at scale via generative simulation. RoboGen leverages the latest advancements in foundation and generative models. Instead of directly using or adapting these models to produce policies or low-level actions, we advocate for a generative scheme, which uses these models to automatically generate diversified tasks, scenes, and training supervisions, thereby scaling up robotic skill learning with minimal human supervision. Our approach equips a robotic agent with a self-guided propose-generate-learn cycle: the agent first proposes interesting tasks and skills to develop, and then generates corresponding simulation environments by populating pertinent objects and assets with proper spatial configurations. Afterwards, the agent decomposes the proposed high-level task into sub-tasks, selects the optimal learning approach (reinforcement learning, motion planning, or trajectory optimization), generates required training supervision, and then learns policies to acquire the proposed skill. Our work attempts to extract the extensive and versatile knowledge embedded in large-scale models and transfer them to the field of robotics. Our fully generative pipeline can be queried repeatedly, producing an endless stream of skill demonstrations associated with diverse tasks and environments.
Authors: Shuo Cheng, Caelan Garrett, Ajay Mandlekar, Danfei Xu
Abstract: Solving complex manipulation tasks in household and factory settings remains challenging due to long-horizon reasoning, fine-grained interactions, and broad object and scene diversity. Learning skills from demonstrations can be an effective strategy, but such methods often have limited generalizability beyond training data and struggle to solve long-horizon tasks. To overcome this, we propose to synergistically combine two paradigms: Neural Object Descriptors (NODs) that produce generalizable object-centric features and Task and Motion Planning (TAMP) frameworks that chain short-horizon skills to solve multi-step tasks. We introduce NOD-TAMP, a TAMP-based framework that extracts short manipulation trajectories from a handful of human demonstrations, adapts these trajectories using NOD features, and composes them to solve broad long-horizon, contact-rich tasks. NOD-TAMP solves existing manipulation benchmarks with a handful of demonstrations and significantly outperforms prior NOD-based approaches on new tabletop manipulation tasks that require diverse generalization. Finally, we deploy NOD-TAMP on a number of real-world tasks, including tool-use and high-precision insertion. For more details, please visit https://sites.google.com/view/nod-tamp/.
Authors: Yuhang Zhou, Paiheng Xu, Xiaoyu Liu, Bang An, Wei Ai, Furong Huang
Abstract: Language models (LMs) have achieved notable success in numerous NLP tasks, employing both fine-tuning and in-context learning (ICL) methods. While language models demonstrate exceptional performance, they face robustness challenges due to spurious correlations arising from imbalanced label distributions in training data or ICL exemplars. Previous research has primarily concentrated on word, phrase, and syntax features, neglecting the concept level, often due to the absence of concept labels and difficulty in identifying conceptual content in input texts. This paper introduces two main contributions. First, we employ ChatGPT to assign concept labels to texts, assessing concept bias in models during fine-tuning or ICL on test data. We find that LMs, when encountering spurious correlations between a concept and a label in training or prompts, resort to shortcuts for predictions. Second, we introduce a data rebalancing technique that incorporates ChatGPT-generated counterfactual data, thereby balancing label distribution and mitigating spurious correlations. Our method's efficacy, surpassing traditional token removal approaches, is validated through extensive testing.
Authors: Jinghan Yang, Shuming Ma, Furu Wei
Abstract: With in-context learning ability, the performance of large language models can be significantly boosted when provided with appropriate context. However, existing in-context learning methods mainly rely on human-provided contexts, such as labeled examples and explicit instructions. Writing context by humans is labor-intensive on various tasks and limits the model to tasks manageable by humans. To overcome these limitations, we propose Automatic In-Context Learning framework that enables the model to autonomously generate examples and instructions for problem-solving. With experiments across various models and datasets, results show that model-generated contexts outperform human-annotated contexts, including Few-Shot and Few-Shot-CoT methods, and surpass existing self-generated context methods like Zero-CoT and Auto-CoT.
Authors: Junlei Zhang, Hongliang He, Nirui Song, Zhanchao Zhou, Shuyuan He, Shuai Zhang, Huachuan Qiu, Anqi Li, Yong Dai, Lizhi Ma, Zhenzhong Lan
Abstract: The critical field of psychology necessitates a comprehensive benchmark to enhance the evaluation and development of domain-specific Large Language Models (LLMs). Existing MMLU-type benchmarks, such as C-EVAL and CMMLU, include psychology-related subjects, but their limited number of questions and lack of systematic concept sampling strategies mean they cannot cover the concepts required in psychology. Consequently, despite their broad subject coverage, these benchmarks lack the necessary depth in the psychology domain, making them inadequate as psychology-specific evaluation suite. To address this issue, this paper presents ConceptPsy, designed to evaluate Chinese complex reasoning and knowledge abilities in psychology. ConceptPsy includes 12 core subjects and 1383 manually collected concepts. Specifically, we prompt GPT-4 to generate questions for each concept using carefully designed diverse prompts and hire professional psychologists to review these questions. To help to understand the fine-grained performances and enhance the weaknesses, we annotate each question with a chapter label and provide chapter-wise accuracy. Based on ConceptPsy, we evaluate a broad range of LLMs. We observe that, although some LLMs achieve similar accuracies on overall performances, they exhibit significant performance variations across different psychology concepts, even when they are models from the same series. We hope our work can facilitate the development of LLMs in the field of psychology.
Authors: Jinke Ren, Zezhong Zhang, Jie Xu, Guanying Chen, Yaping Sun, Ping Zhang, Shuguang Cui
Abstract: Semantic communication is widely touted as a key technology for propelling the sixth-generation (6G) wireless networks. However, providing effective semantic representation is quite challenging in practice. To address this issue, this article takes a crack at exploiting semantic knowledge base (KB) to usher in a new era of generative semantic communication. Via semantic KB, source messages can be characterized in low-dimensional subspaces without compromising their desired meanings, thus significantly enhancing the communication efficiency. The fundamental principle of semantic KB is first introduced, and a generative semantic communication architecture is developed by presenting three sub-KBs, namely source, task, and channel KBs. Then, the detailed construction approaches for each sub-KB are described, followed by their utilization in terms of semantic coding and transmission. A case study is also provided to showcase the superiority of generative semantic communication over conventional syntactic communication and classical semantic communication. In a nutshell, this article establishes a scientific foundation for the exciting uncharted frontier of generative semantic communication.
Authors: Jiayun Luo, Siddhesh Khandelwal, Leonid Sigal, Boyang Li
Abstract: From image-text pairs, large-scale vision-language models (VLMs) learn to implicitly associate image regions with words, which prove effective for tasks like visual question answering. However, leveraging the learned association for open-vocabulary semantic segmentation remains a challenge. In this paper, we propose a simple, yet extremely effective, training-free technique, Plug-and-Play Open-Vocabulary Semantic Segmentation (PnP-OVSS) for this task. PnP-OVSS leverages a VLM with direct text-to-image cross-attention and an image-text matching loss. To balance between over-segmentation and under-segmentation, we introduce Salience Dropout; by iteratively dropping patches that the model is most attentive to, we are able to better resolve the entire extent of the segmentation mask. PnP-OVSS does not require any neural network training and performs hyperparameter tuning without the need for any segmentation annotations, even for a validation set. PnP-OVSS demonstrates substantial improvements over comparable baselines (+26.2% mIoU on Pascal VOC, +20.5% mIoU on MS COCO, +3.1% mIoU on COCO Stuff and +3.0% mIoU on ADE20K). Our codebase is at https://github.com/letitiabanana/PnP-OVSS.
Authors: Yanxi Chen, Xuchen Pan, Yaliang Li, Bolin Ding, Jingren Zhou
Abstract: We present EE-LLM, a framework for large-scale training and inference of early-exit large language models (LLMs). While recent works have shown preliminary evidence for the efficacy of early exiting in accelerating LLM inference, EE-LLM makes a foundational step towards scaling up early-exit LLMs by supporting their training and inference with massive 3D parallelism. Built upon Megatron-LM, EE-LLM implements a variety of algorithmic innovations and performance optimizations tailored to early exiting, including a lightweight method that facilitates backpropagation for the early-exit training objective with pipeline parallelism, techniques of leveraging idle resources in the original pipeline schedule for computation related to early-exit layers, and two approaches of early-exit inference that are compatible with KV caching for autoregressive generation. Our analytical and empirical study shows that EE-LLM achieves great training efficiency with negligible computational overhead compared to standard LLM training, as well as outstanding inference speedup without compromising output quality. To facilitate further research and adoption, we release EE-LLM at https://github.com/pan-x-c/EE-LLM.
Authors: Dashiell Stander, Qinan Yu, Honglu Fan, Stella Biderman
Abstract: The complex and unpredictable nature of deep neural networks prevents their safe use in many high-stakes applications. There have been many techniques developed to interpret deep neural networks, but all have substantial limitations. Algorithmic tasks have proven to be a fruitful test ground for interpreting a neural network end-to-end. Building on previous work, we completely reverse engineer fully connected one-hidden layer networks that have ``grokked'' the arithmetic of the permutation groups $S_5$ and $S_6$. The models discover the true subgroup structure of the full group and converge on neural circuits that decompose the group arithmetic using the permutation group's subgroups. We relate how we reverse engineered the model's mechanisms and confirmed our theory was a faithful description of the circuit's functionality. We also draw attention to current challenges in conducting interpretability research by comparing our work to Chughtai et al. [4] which alleges to find a different algorithm for this same problem.
Authors: Silu He, Qinyao Luo, Xinsha Fu, Ling Zhao, Ronghua Du, Haifeng Li
Abstract: Local Attention-guided Message Passing Mechanism (LAMP) adopted in Graph Attention Networks (GATs) is designed to adaptively learn the importance of neighboring nodes for better local aggregation on the graph, which can bring the representations of similar neighbors closer effectively, thus showing stronger discrimination ability. However, existing GATs suffer from a significant discrimination ability decline in heterophilic graphs because the high proportion of dissimilar neighbors can weaken the self-attention of the central node, jointly resulting in the deviation of the central node from similar nodes in the representation space. This kind of effect generated by neighboring nodes is called the Distraction Effect (DE) in this paper. To estimate and weaken the DE of neighboring nodes, we propose a Causally graph Attention network for Trimming heterophilic graph (CAT). To estimate the DE, since the DE are generated through two paths (grab the attention assigned to neighbors and reduce the self-attention of the central node), we use Total Effect to model DE, which is a kind of causal estimand and can be estimated from intervened data; To weaken the DE, we identify the neighbors with the highest DE (we call them Distraction Neighbors) and remove them. We adopt three representative GATs as the base model within the proposed CAT framework and conduct experiments on seven heterophilic datasets in three different sizes. Comparative experiments show that CAT can improve the node classification accuracy of all base GAT models. Ablation experiments and visualization further validate the enhancement of discrimination ability brought by CAT. The source code is available at https://github.com/GeoX-Lab/CAT.
Authors: Michael Psenka, Alejandro Escontrela, Pieter Abbeel, Yi Ma
Abstract: Diffusion models have become a popular choice for representing actor policies in behavior cloning and offline reinforcement learning. This is due to their natural ability to optimize an expressive class of distributions over a continuous space. However, previous works fail to exploit the score-based structure of diffusion models, and instead utilize a simple behavior cloning term to train the actor, limiting their ability in the actor-critic setting. In this paper, we present a theoretical framework linking the structure of diffusion model policies to a learned Q-function, by linking the structure between the score of the policy to the action gradient of the Q-function. We focus on off-policy reinforcement learning and propose a new policy update method from this theory, which we denote Q-score matching. Notably, this algorithm only needs to differentiate through the denoising model rather than the entire diffusion model evaluation, and converged policies through Q-score matching are implicitly multi-modal and explorative in continuous domains. We conduct experiments in simulated environments to demonstrate the viability of our proposed method and compare to popular baselines. Source code is available from the project website: https://scorematchingrl.com.
Authors: Gwladys Kelodjou, Laurence Roz\'e, V\'eronique Masson, Luis Gal\'arraga, Romaric Gaudel, Maurice Tchuente, Alexandre Termier
Abstract: Machine learning techniques, such as deep learning and ensemble methods, are widely used in various domains due to their ability to handle complex real-world tasks. However, their black-box nature has raised multiple concerns about the fairness, trustworthiness, and transparency of computer-assisted decision-making. This has led to the emergence of local post-hoc explainability methods, which offer explanations for individual decisions made by black-box algorithms. Among these methods, Kernel SHAP is widely used due to its model-agnostic nature and its well-founded theoretical framework. Despite these strengths, Kernel SHAP suffers from high instability: different executions of the method with the same inputs can lead to significantly different explanations, which diminishes the relevance of the explanations. The contribution of this paper is two-fold. On the one hand, we show that Kernel SHAP's instability is caused by its stochastic neighbor selection procedure, which we adapt to achieve full stability without compromising explanation fidelity. On the other hand, we show that by restricting the neighbors generation to perturbations of size 1 -- which we call the coalitions of Layer 1 -- we obtain a novel feature-attribution method that is fully stable, computationally efficient, and still meaningful.
Authors: Wenzhao Jiang, Hao Liu, Hui Xiong
Abstract: Graph Neural Networks (GNNs) have emerged as powerful representation learning tools for capturing complex dependencies within diverse graph-structured data. Despite their success in a wide range of graph mining tasks, GNNs have raised serious concerns regarding their trustworthiness, including susceptibility to distribution shift, biases towards certain populations, and lack of explainability. Recently, integrating causal learning techniques into GNNs has sparked numerous ground-breaking studies since many GNN trustworthiness issues can be alleviated by capturing the underlying data causality rather than superficial correlations. In this survey, we comprehensively review recent research efforts on Causality-Inspired GNNs (CIGNNs). Specifically, we first employ causal tools to analyze the primary trustworthiness risks of existing GNNs, underscoring the necessity for GNNs to comprehend the causal mechanisms within graph data. Moreover, we introduce a taxonomy of CIGNNs based on the type of causal learning capability they are equipped with, i.e., causal reasoning and causal representation learning. Besides, we systematically introduce typical methods within each category and discuss how they mitigate trustworthiness risks. Finally, we summarize useful resources and discuss several future directions, hoping to shed light on new research opportunities in this emerging field. The representative papers, along with open-source data and codes, are available in https://github.com/usail-hkust/Causality-Inspired-GNNs.
URLs: https://github.com/usail-hkust/Causality-Inspired-GNNs.
Authors: Oscar Dabrowski (Computer Science Department, Faculty of Science, University of Geneva, Switzerland, Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Switzerland), Jean-Luc Falcone (Computer Science Department, Faculty of Science, University of Geneva, Switzerland), Antoine Klauser (Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Switzerland, CIBM Center for Biomedical Imaging, MRI HUG-UNIGE, Geneva, Switzerland), Julien Songeon (Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Switzerland, CIBM Center for Biomedical Imaging, MRI HUG-UNIGE, Geneva, Switzerland), Michel Kocher (EPFL Biomedical Imaging Group), Bastien Chopard (Computer Science Department, Faculty of Science, University of Geneva, Switzerland), Fran\c{c}ois Lazeyras (Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Switzerland, CIBM Center for Biomedical Imaging, MRI HUG-UNIGE, Geneva, Switzerland), S\'ebastien Courvoisier (Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Switzerland, CIBM Center for Biomedical Imaging, MRI HUG-UNIGE, Geneva, Switzerland)
Abstract: MRI, a widespread non-invasive medical imaging modality, is highly sensitive to patient motion. Despite many attempts over the years, motion correction remains a difficult problem and there is no general method applicable to all situations. We propose a retrospective method for motion estimation and correction to tackle the problem of in-plane rigid-body motion, apt for classical 2D Spin-Echo scans of the brain, which are regularly used in clinical practice. Due to the sequential acquisition of k-space, motion artifacts are well localized. The method leverages the power of deep neural networks to estimate motion parameters in k-space and uses a model-based approach to restore degraded images to avoid ''hallucinations''. Notable advantages are its ability to estimate motion occurring in high spatial frequencies without the need of a motion-free reference. The proposed method operates on the whole k-space dynamic range and is moderately affected by the lower SNR of higher harmonics. As a proof of concept, we provide models trained using supervised learning on 600k motion simulations based on motion-free scans of 43 different subjects. Generalization performance was tested with simulations as well as in-vivo. Qualitative and quantitative evaluations are presented for motion parameter estimations and image reconstruction. Experimental results show that our approach is able to obtain good generalization performance on simulated data and in-vivo acquisitions. We provide a Python implementation at https://gitlab.unige.ch/Oscar.Dabrowski/sismik_mri/.
Authors: Zonghai Yao, Nandyala Siddharth Kantu, Guanghao Wei, Hieu Tran, Zhangqi Duan, Sunjae Kwon, Zhichao Yang, README annotation team, Hong Yu
Abstract: The advancement in healthcare has shifted focus toward patient-centric approaches, particularly in self-care and patient education, facilitated by access to Electronic Health Records (EHR). However, medical jargon in EHRs poses significant challenges in patient comprehension. To address this, we introduce a new task of automatically generating lay definitions, aiming to simplify complex medical terms into patient-friendly lay language. We first created the README dataset, an extensive collection of over 50,000 unique (medical term, lay definition) pairs and 300,000 mentions, each offering context-aware lay definitions manually annotated by domain experts. We have also engineered a data-centric Human-AI pipeline that synergizes data filtering, augmentation, and selection to improve data quality. We then used README as the training data for models and leveraged a Retrieval-Augmented Generation method to reduce hallucinations and improve the quality of model outputs. Our extensive automatic and human evaluations demonstrate that open-source mobile-friendly models, when fine-tuned with high-quality data, are capable of matching or even surpassing the performance of state-of-the-art closed-source large language models like ChatGPT. This research represents a significant stride in closing the knowledge gap in patient education and advancing patient-centric healthcare solutions.
Authors: Wei-Jer Chang, Francesco Pittaluga, Masayoshi Tomizuka, Wei Zhan, Manmohan Chandraker
Abstract: Evaluating the performance of autonomous vehicle planning algorithms necessitates simulating long-tail safety-critical traffic scenarios. However, traditional methods for generating such scenarios often fall short in terms of controllability and realism and neglect the dynamics of agent interactions. To mitigate these limitations, we introduce SAFE-SIM, a novel diffusion-based controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) the generation of realistic long-tail safety-critical scenarios that closely emulate real-world conditions, and 2) enhanced controllability, enabling more comprehensive and interactive evaluations. We develop a novel approach to simulate safety-critical scenarios through an adversarial term in the denoising process, which allows an adversarial agent to challenge a planner with plausible maneuvers while all agents in the scene exhibit reactive and realistic behaviors. Furthermore, we propose novel guidance objectives and a partial diffusion process that enables a user to control key aspects of the generated scenarios, such as the collision type and aggressiveness of the adversarial driver, while maintaining the realism of the behavior. We validate our framework empirically using the NuScenes dataset, demonstrating improvements in both realism and controllability. These findings affirm that diffusion models provide a robust and versatile foundation for safety-critical, interactive traffic simulation, extending their utility across the broader landscape of autonomous driving. For supplementary videos, visit our project at https://safe-sim.github.io/.
Authors: Zixiang Chen, Yihe Deng, Huizhuo Yuan, Kaixuan Ji, Quanquan Gu
Abstract: Harnessing the power of human-annotated data through Supervised Fine-Tuning (SFT) is pivotal for advancing Large Language Models (LLMs). In this paper, we delve into the prospect of growing a strong LLM out of a weak one without the need for acquiring additional human-annotated data. We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN), which starts from a supervised fine-tuned model. At the heart of SPIN lies a self-play mechanism, where the LLM refines its capability by playing against instances of itself. More specifically, the LLM generates its own training data from its previous iterations, refining its policy by discerning these self-generated responses from those obtained from human-annotated data. Our method progressively elevates the LLM from a nascent model to a formidable one, unlocking the full potential of human-annotated demonstration data for SFT. Theoretically, we prove that the global optimum to the training objective function of our method is achieved only when the LLM policy aligns with the target data distribution. Empirically, we evaluate our method on several benchmark datasets including the HuggingFace Open LLM Leaderboard, MT-Bench, and datasets from Big-Bench. Our results show that SPIN can significantly improve the LLM's performance across a variety of benchmarks and even outperform models trained through direct preference optimization (DPO) supplemented with extra GPT-4 preference data. This sheds light on the promise of self-play, enabling the achievement of human-level performance in LLMs without the need for expert opponents. Codes are available at https://github.com/uclaml/SPIN.
Authors: William Yue, Bo Liu, Peter Stone
Abstract: Deep generative replay has emerged as a promising approach for continual learning in decision-making tasks. This approach addresses the problem of catastrophic forgetting by leveraging the generation of trajectories from previously encountered tasks to augment the current dataset. However, existing deep generative replay methods for continual learning rely on autoregressive models, which suffer from compounding errors in the generated trajectories. In this paper, we propose a simple, scalable, and non-autoregressive method for continual learning in decision-making tasks using a generative model that generates task samples conditioned on the trajectory timestep. We evaluate our method on Continual World benchmarks and find that our approach achieves state-of-the-art performance on the average success rate metric among continual learning methods. Code is available at https://github.com/WilliamYue37/t-DGR.
Authors: Zilin Huang, Zihao Sheng, Chengyuan Ma, Sikai Chen
Abstract: Despite significant progress in autonomous vehicles (AVs), the development of driving policies that ensure both the safety of AVs and traffic flow efficiency has not yet been fully explored. In this paper, we propose an enhanced human-in-the-loop reinforcement learning method, termed the Human as AI mentor-based deep reinforcement learning (HAIM-DRL) framework, which facilitates safe and efficient autonomous driving in mixed traffic platoon. Drawing inspiration from the human learning process, we first introduce an innovative learning paradigm that effectively injects human intelligence into AI, termed Human as AI mentor (HAIM). In this paradigm, the human expert serves as a mentor to the AI agent. While allowing the agent to sufficiently explore uncertain environments, the human expert can take control in dangerous situations and demonstrate correct actions to avoid potential accidents. On the other hand, the agent could be guided to minimize traffic flow disturbance, thereby optimizing traffic flow efficiency. In detail, HAIM-DRL leverages data collected from free exploration and partial human demonstrations as its two training sources. Remarkably, we circumvent the intricate process of manually designing reward functions; instead, we directly derive proxy state-action values from partial human demonstrations to guide the agents' policy learning. Additionally, we employ a minimal intervention technique to reduce the human mentor's cognitive load. Comparative results show that HAIM-DRL outperforms traditional methods in driving safety, sampling efficiency, mitigation of traffic flow disturbance, and generalizability to unseen traffic scenarios. The code and demo videos for this paper can be accessed at: https://zilin-huang.github.io/HAIM-DRL-website/
Authors: Changrong Xiao, Wenxing Ma, Qingping Song, Sean Xin Xu, Kunpeng Zhang, Yufang Wang, Qi Fu
Abstract: Receiving timely and personalized feedback is essential for second-language learners, especially when human instructors are unavailable. This study explores the effectiveness of Large Language Models (LLMs), including both proprietary and open-source models, for Automated Essay Scoring (AES). Through extensive experiments with public and private datasets, we find that while LLMs do not surpass conventional state-of-the-art (SOTA) grading models in performance, they exhibit notable consistency, generalizability, and explainability. We propose an open-source LLM-based AES system, inspired by the dual-process theory. Our system offers accurate grading and high-quality feedback, at least comparable to that of fine-tuned proprietary LLMs, in addition to its ability to alleviate misgrading. Furthermore, we conduct human-AI co-grading experiments with both novice and expert graders. We find that our system not only automates the grading process but also enhances the performance and efficiency of human graders, particularly for essays where the model has lower confidence. These results highlight the potential of LLMs to facilitate effective human-AI collaboration in the educational context, potentially transforming learning experiences through AI-generated feedback.
Authors: Slavisa Tomic, Jo\~ao Pedro Matos-Carvalho, Marko Beko
Abstract: This work addresses weight optimization problem for fully-connected feed-forward neural networks. Unlike existing approaches that are based on back-propagation (BP) and chain rule gradient-based optimization (which implies iterative execution, potentially burdensome and time-consuming in some cases), the proposed approach offers the solution for weight optimization in closed-form by means of least squares (LS) methodology. In the case where the input-to-output mapping is injective, the new approach optimizes the weights in a back-propagating fashion in a single iteration by jointly optimizing a set of weights in each layer for each neuron. In the case where the input-to-output mapping is not injective (e.g., in classification problems), the proposed solution is easily adapted to obtain its final solution in a few iterations. An important advantage over the existing solutions is that these computations (for all neurons in a layer) are independent from each other; thus, they can be carried out in parallel to optimize all weights in a given layer simultaneously. Furthermore, its running time is deterministic in the sense that one can obtain the exact number of computations necessary to optimize the weights in all network layers (per iteration, in the case of non-injective mapping). Our simulation and empirical results show that the proposed scheme, BPLS, works well and is competitive with existing ones in terms of accuracy, but significantly surpasses them in terms of running time. To summarize, the new method is straightforward to implement, is competitive and computationally more efficient than the existing ones, and is well-tailored for parallel implementation.
Authors: Muhammad Naveed Riaz, Maciej Wielgosz, Abel Garcia Romera, Antonio M. Lopez
Abstract: Pedestrian intention prediction is crucial for autonomous driving. In particular, knowing if pedestrians are going to cross in front of the ego-vehicle is core to performing safe and comfortable maneuvers. Creating accurate and fast models that predict such intentions from sequential images is challenging. A factor contributing to this is the lack of datasets with diverse crossing and non-crossing (C/NC) scenarios. We address this scarceness by introducing a framework, named ARCANE, which allows programmatically generating synthetic datasets consisting of C/NC video clip samples. As an example, we use ARCANE to generate a large and diverse dataset named PedSynth. We will show how PedSynth complements widely used real-world datasets such as JAAD and PIE, so enabling more accurate models for C/NC prediction. Considering the onboard deployment of C/NC prediction models, we also propose a deep model named PedGNN, which is fast and has a very low memory footprint. PedGNN is based on a GNN-GRU architecture that takes a sequence of pedestrian skeletons as input to predict crossing intentions.
Authors: Rohan Wadhawan, Hritik Bansal, Kai-Wei Chang, Nanyun Peng
Abstract: Many real-world tasks require an agent to reason jointly over text and visual objects, (e.g., navigating in public spaces), which we refer to as context-sensitive text-rich visual reasoning. Specifically, these tasks require an understanding of the context in which the text interacts with visual elements within an image. However, there is a lack of existing datasets to benchmark the state-of-the-art multimodal models' capability on context-sensitive text-rich visual reasoning. In this paper, we introduce ConTextual, a novel dataset featuring human-crafted instructions that require context-sensitive reasoning for text-rich images. We conduct experiments to assess the performance of 14 foundation models (GPT-4V, Gemini-Pro-Vision, LLaVA-Next) and establish a human performance baseline. Further, we perform human evaluations of the model responses and observe a significant performance gap of 30.8% between GPT-4V (the current best-performing Large Multimodal Model) and human performance. Our fine-grained analysis reveals that GPT-4V encounters difficulties interpreting time-related data and infographics. However, it demonstrates proficiency in comprehending abstract visual contexts such as memes and quotes. Finally, our qualitative analysis uncovers various factors contributing to poor performance including lack of precise visual perception and hallucinations. Our dataset, code, and leaderboard can be found on the project page https://con-textual.github.io/
Authors: Zhenyu He, Guhao Feng, Shengjie Luo, Kai Yang, Liwei Wang, Jingjing Xu, Zhi Zhang, Hongxia Yang, Di He
Abstract: In this work, we leverage the intrinsic segmentation of language sequences and design a new positional encoding method called Bilevel Positional Encoding (BiPE). For each position, our BiPE blends an intra-segment encoding and an inter-segment encoding. The intra-segment encoding identifies the locations within a segment and helps the model capture the semantic information therein via absolute positional encoding. The inter-segment encoding specifies the segment index, models the relationships between segments, and aims to improve extrapolation capabilities via relative positional encoding. Theoretical analysis shows this disentanglement of positional information makes learning more effective. The empirical results also show that our BiPE has superior length extrapolation capabilities across a wide range of tasks in diverse text modalities.
Authors: Andreas Opedal, Alessandro Stolfo, Haruki Shirakami, Ying Jiao, Ryan Cotterell, Bernhard Sch\"olkopf, Abulhair Saparov, Mrinmaya Sachan
Abstract: There is increasing interest in employing large language models (LLMs) as cognitive models. For such purposes, it is central to understand which properties of human cognition are well-modeled by LLMs, and which are not. In this work, we study the biases of LLMs in relation to those known in children when solving arithmetic word problems. Surveying the learning science literature, we posit that the problem-solving process can be split into three distinct steps: text comprehension, solution planning and solution execution. We construct tests for each one in order to understand whether current LLMs display the same cognitive biases as children in these steps. We generate a novel set of word problems for each of these tests, using a neuro-symbolic approach that enables fine-grained control over the problem features. We find evidence that LLMs, with and without instruction-tuning, exhibit human-like biases in both the text-comprehension and the solution-planning steps of the solving process, but not in the final step, in which the arithmetic expressions are executed to obtain the answer.
Authors: J. E. Eicher, R. F. Irgoli\v{c}
Abstract: Large Language Models (LLMs) like gpt-3.5-turbo-0613 and claude-instant-1.2 are vital in interpreting and executing semantic tasks. Unfortunately, these models' inherent biases adversely affect their performance Particularly affected is object selection from lists; a fundamental operation in digital navigation and decision-making. This research critically examines these biases and quantifies the effects on a representative list selection task. To explore these biases, we experiment manipulating temperature, list length, object identity, object type, prompt complexity, and model. We isolated and measured the influence of the biases on selection behavior. Our findings show that bias structure is strongly dependent on the model, with object type modulating the magnitude of the effect. With a strong primacy effect, causing the first objects in a list to be disproportionately represented in outputs. The usage of guard rails, a prompt engineering method of ensuring a response structure, increases bias and decreases instruction adherence when to a selection task. The bias is ablated when the guard rail step is separated from the list sampling step, lowering the complexity of each individual task. We provide LLM applications and theoretically suggest that LLMs experience a form of cognitive load that is compensated for with bias.
Authors: Zihan Ding, Amy Zhang, Yuandong Tian, Qinqing Zheng
Abstract: We introduce Diffusion World Model (DWM), a conditional diffusion model capable of predicting multistep future states and rewards concurrently. As opposed to traditional one-step dynamics models, DWM offers long-horizon predictions in a single forward pass, eliminating the need for recursive queries. We integrate DWM into model-based value estimation, where the short-term return is simulated by future trajectories sampled from DWM. In the context of offline reinforcement learning, DWM can be viewed as a conservative value regularization through generative modeling. Alternatively, it can be seen as a data source that enables offline Q-learning with synthetic data. Our experiments on the D4RL dataset confirm the robustness of DWM to long-horizon simulation. In terms of absolute performance, DWM significantly surpasses one-step dynamics models with a $44\%$ performance gain, and is comparable to or slightly surpassing their model-free counterparts.
Authors: Yufei Wang, Zhanyi Sun, Jesse Zhang, Zhou Xian, Erdem Biyik, David Held, Zackory Erickson
Abstract: Reward engineering has long been a challenge in Reinforcement Learning (RL) research, as it often requires extensive human effort and iterative processes of trial-and-error to design effective reward functions. In this paper, we propose RL-VLM-F, a method that automatically generates reward functions for agents to learn new tasks, using only a text description of the task goal and the agent's visual observations, by leveraging feedbacks from vision language foundation models (VLMs). The key to our approach is to query these models to give preferences over pairs of the agent's image observations based on the text description of the task goal, and then learn a reward function from the preference labels, rather than directly prompting these models to output a raw reward score, which can be noisy and inconsistent. We demonstrate that RL-VLM-F successfully produces effective rewards and policies across various domains - including classic control, as well as manipulation of rigid, articulated, and deformable objects - without the need for human supervision, outperforming prior methods that use large pretrained models for reward generation under the same assumptions. Videos can be found on our project website: https://rlvlmf2024.github.io/
Authors: Oubo Ma, Yuwen Pu, Linkang Du, Yang Dai, Ruo Wang, Xiaolei Liu, Yingcai Wu, Shouling Ji
Abstract: Recent advancements in multi-agent reinforcement learning (MARL) have opened up vast application prospects, such as swarm control of drones, collaborative manipulation by robotic arms, and multi-target encirclement. However, potential security threats during the MARL deployment need more attention and thorough investigation. Recent research reveals that attackers can rapidly exploit the victim's vulnerabilities, generating adversarial policies that result in the failure of specific tasks. For instance, reducing the winning rate of a superhuman-level Go AI to around 20%. Existing studies predominantly focus on two-player competitive environments, assuming attackers possess complete global state observation. In this study, we unveil, for the first time, the capability of attackers to generate adversarial policies even when restricted to partial observations of the victims in multi-agent competitive environments. Specifically, we propose a novel black-box attack (SUB-PLAY) that incorporates the concept of constructing multiple subgames to mitigate the impact of partial observability and suggests sharing transitions among subpolicies to improve attackers' exploitative ability. Extensive evaluations demonstrate the effectiveness of SUB-PLAY under three typical partial observability limitations. Visualization results indicate that adversarial policies induce significantly different activations of the victims' policy networks. Furthermore, we evaluate three potential defenses aimed at exploring ways to mitigate security threats posed by adversarial policies, providing constructive recommendations for deploying MARL in competitive environments.
Authors: Matthew Renze, Erhan Guven
Abstract: In this research study, we empirically investigate the effect of sampling temperature on the performance of Large Language Models (LLMs) on various problem-solving tasks. We created a multiple-choice question-and-answer (MCQA) exam by randomly sampling problems from standard LLM benchmarks. Then, we used nine popular LLMs with five prompt-engineering techniques to solve the MCQA problems while increasing the sampling temperature from 0.0 to 1.6. Despite anecdotal reports to the contrary, our empirical results indicate that changes in temperature from 0.0 to 1.0 do not have a statistically significant impact on LLM performance for problem-solving tasks. In addition, these results appear to generalize across LLMs, prompt-engineering techniques, and problem domains. All code, data, and supplemental materials are available on GitHub at: https://github.com/matthewrenze/jhu-llm-temperature
Authors: Yongchao Chen, Jacob Arkin, Yilun Hao, Yang Zhang, Nicholas Roy, Chuchu Fan
Abstract: Prompt optimization aims to find the best prompt to a large language model (LLM) for a given task. LLMs have been successfully used to help find and improve prompt candidates for single-step tasks. However, realistic tasks for agents are multi-step and introduce new challenges: (1) Prompt content is likely to be more extensive and complex, making it more difficult for LLMs to analyze errors, (2) the impact of an individual step is difficult to evaluate, and (3) different people may have varied preferences about task execution. While humans struggle to optimize prompts, they are good at providing feedback about LLM outputs; we therefore introduce a new LLM-driven discrete prompt optimization framework PROMST that incorporates human-designed feedback rules to automatically offer direct suggestions for improvement. We also use an extra learned heuristic model that predicts prompt performance to efficiently sample from prompt candidates. This approach significantly outperforms both human-engineered prompts and several other prompt optimization methods across 11 representative multi-step tasks (an average 10.6\%-29.3\% improvement to current best methods on five LLMs respectively). We believe our work can serve as a benchmark for automatic prompt optimization for LLM-driven multi-step tasks. Datasets and Codes are available at https://github.com/yongchao98/PROMST. Project Page is available at https://yongchao98.github.io/MIT-REALM-PROMST/.
URLs: https://github.com/yongchao98/PROMST., https://yongchao98.github.io/MIT-REALM-PROMST/.
Authors: Aliakbar Nafar, Kristen Brent Venable, Parisa Kordjamshidi
Abstract: This paper considers the challenges Large Language Models (LLMs) face when reasoning over text that includes information involving uncertainty explicitly quantified via probability values. This type of reasoning is relevant to a variety of contexts ranging from everyday conversations to medical decision-making. Despite improvements in the mathematical reasoning capabilities of LLMs, they still exhibit significant difficulties when it comes to probabilistic reasoning. To deal with this problem, we introduce the Bayesian Linguistic Inference Dataset (BLInD), a new dataset specifically designed to test the probabilistic reasoning capabilities of LLMs. We use BLInD to find out the limitations of LLMs for tasks involving probabilistic reasoning. In addition, we present several prompting strategies that map the problem to different formal representations, including Python code, probabilistic algorithms, and probabilistic logical programming. We conclude by providing an evaluation of our methods on BLInD and an adaptation of a causal reasoning question-answering dataset. Our empirical results highlight the effectiveness of our proposed strategies for multiple LLMs.
Authors: Tianyi Qiu, Fanzhi Zeng, Jiaming Ji, Dong Yan, Kaile Wang, Jiayi Zhou, Yang Han, Josef Dai, Xuehai Pan, Yaodong Yang
Abstract: Existing alignment methods share a common topology of information flow, where reward information is collected from humans, modeled with preference learning, and used to tune language models. However, this shared topology has not been systematically characterized, nor have its alternatives been thoroughly explored, leaving the problems of low data efficiency and unreliable generalization unaddressed. As a solution, we introduce a theoretical framework for investigating reward generalization in reinforcement learning from human feedback (RLHF), focusing on the topology of information flow at both macro and micro levels. At the macro level, we portray the RLHF information flow as an autoencoding process over behavior distributions, formalizing the RLHF objective of distributional consistency between human preference and model behavior. At the micro level, we present induced Bayesian networks as a theory of reward generalization in RLHF, introducing fine-grained dataset topologies into generalization bounds. Combining analysis on both levels, we propose reward modeling from tree-structured preference information. It is shown to reduce reward uncertainty by up to $\Theta(\log n/\log\log n)$ times compared to baselines, where $n$ is the dataset size. Validation on three NLP tasks shows that our tree-based reward model achieves an average win rate of 65% against baseline methods, thus improving reward generalization for free via topology design.
Authors: Xiyang Wu, Souradip Chakraborty, Ruiqi Xian, Jing Liang, Tianrui Guan, Fuxiao Liu, Brian M. Sadler, Dinesh Manocha, Amrit Singh Bedi
Abstract: In this paper, we highlight the critical issues of robustness and safety associated with integrating large language models (LLMs) and vision-language models (VLMs) into robotics applications. Recent works focus on using LLMs and VLMs to improve the performance of robotics tasks, such as manipulation and navigation. Despite these improvements, analyzing the safety of such systems remains underexplored yet extremely critical. LLMs and VLMs are highly susceptible to adversarial inputs, prompting a significant inquiry into the safety of robotic systems. This concern is important because robotics operate in the physical world where erroneous actions can result in severe consequences. This paper explores this issue thoroughly, presenting a mathematical formulation of potential attacks on LLM/VLM-based robotic systems and offering experimental evidence of the safety challenges. Our empirical findings highlight a significant vulnerability: simple modifications to the input can drastically reduce system effectiveness. Specifically, our results demonstrate an average performance deterioration of 19.4% under minor input prompt modifications and a more alarming 29.1% under slight perceptual changes. These findings underscore the urgent need for robust countermeasures to ensure the safe and reliable deployment of advanced LLM/VLM-based robotic systems.
Authors: Haoqiang Kang, Terra Blevins, Luke Zettlemoyer
Abstract: While many hallucination detection techniques have been evaluated on English text, their effectiveness in multilingual contexts remains unknown. This paper assesses how well various factual hallucination detection metrics (lexical metrics like ROUGE and Named Entity Overlap, and Natural Language Inference (NLI)-based metrics) identify hallucinations in generated biographical summaries across languages. We compare how well automatic metrics correlate to each other and whether they agree with human judgments of factuality. Our analysis reveals that while the lexical metrics are ineffective, NLI-based metrics perform well, correlating with human annotations in many settings and often outperforming supervised models. However, NLI metrics are still limited, as they do not detect single-fact hallucinations well and fail for lower-resource languages. Therefore, our findings highlight the gaps in exisiting hallucination detection methods for non-English languages and motivate future research to develop more robust multilingual detection methods for LLM hallucinations.
Authors: Xin Xu, Shizhe Diao, Can Yang, Yang Wang
Abstract: Chain-of-Thought (CoT) prompting has marked a significant advancement in enhancing the reasoning capabilities of large language models (LLMs). Previous studies have developed various extensions of CoT, which focus primarily on enhancing end-task performance. In addition, there has been research on assessing the quality of reasoning chains in CoT. This raises an intriguing question: Is it possible to predict the accuracy of LLM outputs by scrutinizing the reasoning chains they generate? To answer this research question, we introduce a benchmark, R2PE, designed specifically to explore the relationship between reasoning chains and performance in various reasoning tasks spanning five different domains. This benchmark aims to measure the falsehood of the final output of LLMs based on the reasoning steps. To make full use of information in multiple reasoning chains, we propose the process discernibility score (PDS) framework that beats the answer-checking baseline by a large margin. Concretely, this resulted in an average of $5.1\%$ increase in the F1 score and $2.97\%$ improvement in AUC-PR across all 45 subsets within R2PE. We further demonstrate our PDS's efficacy in advancing open-domain QA accuracy. Data and code are available at https://github.com/XinXU-USTC/R2PE.
Authors: Yogesh Tripathi, Raghav Donakanti, Sahil Girhepuje, Ishan Kavathekar, Bhaskara Hanuma Vedula, Gokul S Krishnan, Shreya Goyal, Anmol Goel, Balaraman Ravindran, Ponnurangam Kumaraguru
Abstract: Recent advancements in language technology and Artificial Intelligence have resulted in numerous Language Models being proposed to perform various tasks in the legal domain ranging from predicting judgments to generating summaries. Despite their immense potential, these models have been proven to learn and exhibit societal biases and make unfair predictions. In this study, we explore the ability of Large Language Models (LLMs) to perform legal tasks in the Indian landscape when social factors are involved. We present a novel metric, $\beta$-weighted $\textit{Legal Safety Score ($LSS_{\beta}$)}$, which encapsulates both the fairness and accuracy aspects of the LLM. We assess LLMs' safety by considering its performance in the $\textit{Binary Statutory Reasoning}$ task and its fairness exhibition with respect to various axes of disparities in the Indian society. Task performance and fairness scores of LLaMA and LLaMA--2 models indicate that the proposed $LSS_{\beta}$ metric can effectively determine the readiness of a model for safe usage in the legal sector. We also propose finetuning pipelines, utilising specialised legal datasets, as a potential method to mitigate bias and improve model safety. The finetuning procedures on LLaMA and LLaMA--2 models increase the $LSS_{\beta}$, improving their usability in the Indian legal domain. Our code is publicly released.
Authors: Atsuki Yamaguchi, Aline Villavicencio, Nikolaos Aletras
Abstract: The development of state-of-the-art generative large language models (LLMs) disproportionately relies on English-centric tokenizers, vocabulary and pre-training data. Despite the fact that some LLMs have multilingual capabilities, recent studies have shown that their inference efficiency deteriorates when generating text in languages other than English. This results in increased inference time and costs. Cross-lingual vocabulary adaptation (CVA) methods have been proposed for adapting models to a target language aiming to improve downstream performance. However, the effectiveness of these methods on increasing inference efficiency of generative LLMs has yet to be explored. In this paper, we perform an empirical study of five CVA methods on four generative LLMs (including monolingual and multilingual models) across four typologically-diverse languages and four natural language understanding tasks. We find that CVA substantially contributes to LLM inference speedups of up to 271.5\%. We also show that adapting LLMs that have been pre-trained on more balanced multilingual data results in downstream performance comparable to the original models.
Authors: Yebowen Hu, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang, Hassan Foroosh, Dong Yu, Fei Liu
Abstract: Large language models hold significant potential for integrating various data types, such as text documents and database records, for advanced analytics. However, blending text and numerical data presents substantial challenges. LLMs need to process and cross-reference entities and numbers, handle data inconsistencies and redundancies, and develop planning capabilities such as building a working memory for managing complex data queries. In this paper, we introduce four novel tasks centered around sports data analytics to evaluate the numerical reasoning and information fusion capabilities of LLMs. These tasks involve providing LLMs with detailed, play-by-play sports game descriptions, then challenging them with adversarial scenarios such as new game rules, longer durations, scrambled narratives, and analyzing key statistics in game summaries. We conduct extensive experiments on NBA and NFL games to assess the performance of LLMs on these tasks. Our benchmark, SportsMetrics, introduces a new mechanism for assessing LLMs' numerical reasoning and fusion skills.
Authors: Xinbang Dai, Yuncheng Hua, Tongtong Wu, Yang Sheng, Qiu Ji, Guilin Qi
Abstract: As the parameter scale of large language models (LLMs) grows, jointly training knowledge graph (KG) embeddings with model parameters to enhance LLM capabilities becomes increasingly costly. Consequently, the community has shown interest in developing prompt strategies that effectively integrate KG information into LLMs. However, the format for incorporating KGs into LLMs lacks standardization; for instance, KGs can be transformed into linearized triples or natural language (NL) text. Current prompting methods often rely on a trial-and-error approach, leaving researchers with an incomplete understanding of which KG input format best facilitates LLM comprehension of KG content. To elucidate this, we design a series of experiments to explore LLMs' understanding of different KG input formats within the context of prompt engineering. Our analysis examines both literal and attention distribution levels. Through extensive experiments, we indicate a counter-intuitive phenomenon: when addressing fact-related questions, unordered linearized triples are more effective for LLMs' understanding of KGs compared to fluent NL text. Furthermore, noisy, incomplete, or marginally relevant subgraphs can still enhance LLM performance. Finally, different LLMs have distinct preferences for different formats of organizing unordered triples.
Authors: Guiming Hardy Chen, Shunian Chen, Ruifei Zhang, Junying Chen, Xiangbo Wu, Zhiyi Zhang, Zhihong Chen, Jianquan Li, Xiang Wan, Benyou Wang
Abstract: Large vision-language models (LVLMs) have shown premise in a broad range of vision-language tasks with their strong reasoning and generalization capabilities. However, they require considerable computational resources for training and deployment. This study aims to bridge the performance gap between traditional-scale LVLMs and resource-friendly lite versions by adopting high-quality training data. To this end, we propose a comprehensive pipeline for generating a synthetic dataset. The key idea is to leverage strong proprietary models to generate (i) fine-grained image annotations for vision-language alignment and (ii) complex reasoning visual question-answering pairs for visual instruction fine-tuning, yielding 1.3M samples in total. We train a series of lite VLMs on the synthetic dataset and experimental results demonstrate the effectiveness of the proposed scheme, where they achieve competitive performance on 17 benchmarks among 4B LVLMs, and even perform on par with 7B/13B-scale models on various benchmarks. This work highlights the feasibility of adopting high-quality data in crafting more efficient LVLMs. We name our dataset \textit{ALLaVA}, and open-source it to research community for developing better resource-efficient LVLMs for wider usage.
Authors: Che Zhang, Zhenyang Xiao, Chengcheng Han, Yixin Lian, Yuejian Fang
Abstract: Self-correction has achieved impressive results in enhancing the style and security of the generated output from large language models (LLMs). However, recent studies suggest that self-correction might be limited or even counterproductive in reasoning tasks due to LLMs' difficulties in identifying logical mistakes. In this paper, we aim to enhance the self-checking capabilities of LLMs by constructing training data for checking tasks. Specifically, we apply the Chain of Thought (CoT) methodology to self-checking tasks, utilizing fine-grained step-level analyses and explanations to assess the correctness of reasoning paths. We propose a specialized checking format called "Step CoT Check". Following this format, we construct a checking-correction dataset that includes detailed step-by-step analysis and checking. Then we fine-tune LLMs to enhance their error detection and correction abilities. Our experiments demonstrate that fine-tuning with the "Step CoT Check" format significantly improves the self-checking and self-correction abilities of LLMs across multiple benchmarks. This approach outperforms other formats, especially in locating the incorrect position, with greater benefits observed in larger models. For reproducibility, all the datasets and code are provided in https://github.com/bammt/Learn-to-check.
Authors: Long Zhao, Nitesh B. Gundavarapu, Liangzhe Yuan, Hao Zhou, Shen Yan, Jennifer J. Sun, Luke Friedman, Rui Qian, Tobias Weyand, Yue Zhao, Rachel Hornung, Florian Schroff, Ming-Hsuan Yang, David A. Ross, Huisheng Wang, Hartwig Adam, Mikhail Sirotenko, Ting Liu, Boqing Gong
Abstract: We introduce VideoPrism, a general-purpose video encoder that tackles diverse video understanding tasks with a single frozen model. We pretrain VideoPrism on a heterogeneous corpus containing 36M high-quality video-caption pairs and 582M video clips with noisy parallel text (e.g., ASR transcripts). The pretraining approach improves upon masked autoencoding by global-local distillation of semantic video embeddings and a token shuffling scheme, enabling VideoPrism to focus primarily on the video modality while leveraging the invaluable text associated with videos. We extensively test VideoPrism on four broad groups of video understanding tasks, from web video question answering to CV for science, achieving state-of-the-art performance on 31 out of 33 video understanding benchmarks.
Authors: Michal Spiegel, Dominik Macko
Abstract: SemEval-2024 Task 8 is focused on multigenerator, multidomain, and multilingual black-box machine-generated text detection. Such a detection is important for preventing a potential misuse of large language models (LLMs), the newest of which are very capable in generating multilingual human-like texts. We have coped with this task in multiple ways, utilizing language identification and parameter-efficient fine-tuning of smaller LLMs for text classification. We have further used the per-language classification-threshold calibration to uniquely combine fine-tuned models predictions with statistical detection metrics to improve generalization of the system detection performance. Our submitted method achieved competitive results, ranking at the fourth place, just under 1 percentage point behind the winner.
Authors: Yuheng Chen, Pengfei Cao, Yubo Chen, Yining Wang, Shengping Liu, Kang Liu, Jun Zhao
Abstract: Large language models (LLMs) store extensive factual knowledge, but the underlying mechanisms remain unclear. Previous research suggests that factual knowledge is stored within multi-layer perceptron weights, and some storage units exhibit degeneracy, referred to as Degenerate Knowledge Neurons (DKNs). Despite the novelty and unique properties of this concept, it has not been rigorously defined or systematically studied. We first consider the connection weight patterns of MLP neurons and define DKNs from both structural and functional aspects. Based on this, we introduce the Neurological Topology Clustering method, which allows the formation of DKNs in any numbers and structures, leading to a more accurate DKN acquisition. Furthermore, inspired by cognitive science, we explore the relationship between DKNs and the robustness, evolvability, and complexity of LLMs. Our execution of 34 experiments under 6 settings demonstrates the connection between DKNs and these three properties. The code will be available soon.
Authors: Wen Huang, Hongbin Liu, Minxin Guo, Neil Zhenqiang Gong
Abstract: Visual hallucination (VH) means that a multi-modal LLM (MLLM) imagines incorrect details about an image in visual question answering. Existing studies find VH instances only in existing image datasets, which results in biased understanding of MLLMs' performance under VH due to limited diversity of such VH instances. In this work, we propose a tool called VHTest to generate a diverse set of VH instances. Specifically, VHTest finds some initial VH instances in existing image datasets (e.g., COCO), generates a text description for each VH mode, and uses a text-to-image generative model (e.g., DALL-E-3) to generate VH images based on the text descriptions. We collect a benchmark dataset with 1,200 VH instances in 8 VH modes using VHTest. We find that existing MLLMs such as GPT-4V, LLaVA-1.5, and MiniGPT-v2 hallucinate for a large fraction of the instances in our benchmark. Moreover, we find that fine-tuning an MLLM using our benchmark dataset reduces its likelihood to hallucinate without sacrificing its performance on other benchmarks. Our benchmarks are publicly available: https://github.com/wenhuang2000/VHTest.
Authors: Priyanshul Govil, Hemang Jain, Vamshi Krishna Bonagiri, Aman Chadha, Ponnurangam Kumaraguru, Manas Gaur, Sanorita Dey
Abstract: Large Language Models (LLMs) are trained on extensive web corpora, which enable them to understand and generate human-like text. However, this training process also results in inherent biases within the models. These biases arise from web data's diverse and often uncurated nature, containing various stereotypes and prejudices. Previous works on debiasing models rely on benchmark datasets to measure their method's performance. However, these datasets suffer from several pitfalls due to the highly subjective understanding of bias, highlighting a critical need for contextual exploration. We propose understanding the context of inputs by considering the diverse situations in which they may arise. Our contribution is two-fold: (i) we augment 2,291 stereotyped statements from two existing bias-benchmark datasets with points for adding context; (ii) we develop the Context-Oriented Bias Indicator and Assessment Score (COBIAS) to assess a statement's contextual reliability in measuring bias. Our metric aligns with human judgment on contextual reliability of statements (Spearman's $\rho = 0.65, p = 3.4 * 10^{-60}$) and can be used to create reliable datasets, which would assist bias mitigation works.
Authors: YongKyung Oh, Dongyoung Lim, Sungil Kim
Abstract: Irregular sampling intervals and missing values in real-world time series data present challenges for conventional methods that assume consistent intervals and complete data. Neural Ordinary Differential Equations (Neural ODEs) offer an alternative approach, utilizing neural networks combined with ODE solvers to learn continuous latent representations through parameterized vector fields. Neural Stochastic Differential Equations (Neural SDEs) extend Neural ODEs by incorporating a diffusion term, although this addition is not trivial, particularly when addressing irregular intervals and missing values. Consequently, careful design of drift and diffusion functions is crucial for maintaining stability and enhancing performance, while incautious choices can result in adverse properties such as the absence of strong solutions, stochastic destabilization, or unstable Euler discretizations, significantly affecting Neural SDEs' performance. In this study, we propose three stable classes of Neural SDEs: Langevin-type SDE, Linear Noise SDE, and Geometric SDE. Then, we rigorously demonstrate their robustness in maintaining excellent performance under distribution shift, while effectively preventing overfitting. To assess the effectiveness of our approach, we conduct extensive experiments on four benchmark datasets for interpolation, forecasting, and classification tasks, and analyze the robustness of our methods with 30 public datasets under different missing rates. Our results demonstrate the efficacy of the proposed method in handling real-world irregular time series data.
Authors: Xiao Chen, Quanyi Li, Tai Wang, Tianfan Xue, Jiangmiao Pang
Abstract: While recent advances in neural radiance field enable realistic digitization for large-scale scenes, the image-capturing process is still time-consuming and labor-intensive. Previous works attempt to automate this process using the Next-Best-View (NBV) policy for active 3D reconstruction. However, the existing NBV policies heavily rely on hand-crafted criteria, limited action space, or per-scene optimized representations. These constraints limit their cross-dataset generalizability. To overcome them, we propose GenNBV, an end-to-end generalizable NBV policy. Our policy adopts a reinforcement learning (RL)-based framework and extends typical limited action space to 5D free space. It empowers our agent drone to scan from any viewpoint, and even interact with unseen geometries during training. To boost the cross-dataset generalizability, we also propose a novel multi-source state embedding, including geometric, semantic, and action representations. We establish a benchmark using the Isaac Gym simulator with the Houses3K and OmniObject3D datasets to evaluate this NBV policy. Experiments demonstrate that our policy achieves a 98.26% and 97.12% coverage ratio on unseen building-scale objects from these datasets, respectively, outperforming prior solutions.
Authors: Saeed Khorram, Mingqi Jiang, Mohamad Shahbazi, Mohamad H. Danesh, Li Fuxin
Abstract: Despite extensive research on training generative adversarial networks (GANs) with limited training data, learning to generate images from long-tailed training distributions remains fairly unexplored. In the presence of imbalanced multi-class training data, GANs tend to favor classes with more samples, leading to the generation of low-quality and less diverse samples in tail classes. In this study, we aim to improve the training of class-conditional GANs with long-tailed data. We propose a straightforward yet effective method for knowledge sharing, allowing tail classes to borrow from the rich information from classes with more abundant training data. More concretely, we propose modifications to existing class-conditional GAN architectures to ensure that the lower-resolution layers of the generator are trained entirely unconditionally while reserving class-conditional generation for the higher-resolution layers. Experiments on several long-tail benchmarks and GAN architectures demonstrate a significant improvement over existing methods in both the diversity and fidelity of the generated images. The code is available at https://github.com/khorrams/utlo.
Authors: Roy Xie, Chengxuan Huang, Junlin Wang, Bhuwan Dhingra
Abstract: Large language models (LLMs) have significantly transformed the educational landscape. As current plagiarism detection tools struggle to keep pace with LLMs' rapid advancements, the educational community faces the challenge of assessing students' true problem-solving abilities in the presence of LLMs. In this work, we explore a new paradigm for ensuring fair evaluation -- generating adversarial examples which preserve the structure and difficulty of the original questions aimed for assessment, but are unsolvable by LLMs. Focusing on the domain of math word problems, we leverage abstract syntax trees to structurally generate adversarial examples that cause LLMs to produce incorrect answers by simply editing the numeric values in the problems. We conduct experiments on various open- and closed-source LLMs, quantitatively and qualitatively demonstrating that our method significantly degrades their math problem-solving ability. We identify shared vulnerabilities among LLMs and propose a cost-effective approach to attack high-cost models. Additionally, we conduct automatic analysis to investigate the cause of failure, providing further insights into the limitations of LLMs.
Authors: Xingchen Zou, Yibo Yan, Xixuan Hao, Yuehong Hu, Haomin Wen, Erdong Liu, Junbo Zhang, Yong Li, Tianrui Li, Yu Zheng, Yuxuan Liang
Abstract: As cities continue to burgeon, Urban Computing emerges as a pivotal discipline for sustainable development by harnessing the power of cross-domain data fusion from diverse sources (e.g., geographical, traffic, social media, and environmental data) and modalities (e.g., spatio-temporal, visual, and textual modalities). Recently, we are witnessing a rising trend that utilizes various deep-learning methods to facilitate cross-domain data fusion in smart cities. To this end, we propose the first survey that systematically reviews the latest advancements in deep learning-based data fusion methods tailored for urban computing. Specifically, we first delve into data perspective to comprehend the role of each modality and data source. Secondly, we classify the methodology into four primary categories: feature-based, alignment-based, contrast-based, and generation-based fusion methods. Thirdly, we further categorize multi-modal urban applications into seven types: urban planning, transportation, economy, public safety, society, environment, and energy. Compared with previous surveys, we focus more on the synergy of deep learning methods with urban computing applications. Furthermore, we shed light on the interplay between Large Language Models (LLMs) and urban computing, postulating future research directions that could revolutionize the field. We firmly believe that the taxonomy, progress, and prospects delineated in our survey stand poised to significantly enrich the research community. The summary of the comprehensive and up-to-date paper list can be found at https://github.com/yoshall/Awesome-Multimodal-Urban-Computing.
URLs: https://github.com/yoshall/Awesome-Multimodal-Urban-Computing.
Authors: Philipp Schoenegger, Indre Tuminauskaite, Peter S. Park, Rafael Valdece Sousa Bastos, Philip E. Tetlock
Abstract: Human forecasting accuracy in practice relies on the 'wisdom of the crowd' effect, in which predictions about future events are significantly improved by aggregating across a crowd of individual forecasters. Past work on the forecasting ability of large language models (LLMs) suggests that frontier LLMs, as individual forecasters, underperform compared to the gold standard of a human-crowd forecasting-tournament aggregate. In Study 1, we expand this research by using an LLM ensemble approach consisting of a crowd of 12 LLMs. We compare the aggregated LLM predictions on 31 binary questions to those of a crowd of 925 human forecasters from a three-month forecasting tournament. Our preregistered main analysis shows that the LLM crowd outperforms a simple no-information benchmark, and is not statistically different from the human crowd. We also observe a set of human-like biases in machine responses, such as an acquiescence effect and a tendency to favour round numbers. In Study 2, we test whether LLM predictions (of GPT-4 and Claude 2) can be improved by drawing on human cognitive output. We find that both models' forecasting accuracy benefits from exposure to the median human prediction as information, improving accuracy by between 17% and 28%, though this leads to less accurate predictions than simply averaging human and machine forecasts. Our results suggest that LLMs can achieve forecasting accuracy rivaling that of the human crowd: via the simple, practically applicable method of forecast aggregation.
Authors: Bo Li, Qinghua Zhao, Lijie Wen
Abstract: Previous works have evaluated memorization by comparing model outputs with training corpora, examining how factors such as data duplication, model size, and prompt length influence memorization. However, analyzing these extensive training corpora is highly time-consuming. To address this challenge, this paper proposes an innovative approach named ROME that bypasses direct processing of the training data. Specifically, we select datasets categorized into three distinct types -- context-independent, conventional, and factual -- and redefine memorization as the ability to produce correct answers under these conditions. Our analysis then focuses on disparities between memorized and non-memorized samples by examining the logits and representations of generated texts. Experimental findings reveal that longer words are less likely to be memorized, higher confidence correlates with greater memorization, and representations of the same concepts are more similar across different contexts. Our code and data will be publicly available when the paper is accepted.
Authors: Saketh Reddy Karra, Theja Tulabandhula
Abstract: Weblogs, comprised of records detailing user activities on any website, offer valuable insights into user preferences, behavior, and interests. Numerous recommendation algorithms, employing strategies such as collaborative filtering, content-based filtering, and hybrid methods, leverage the data mined through these weblogs to provide personalized recommendations to users. Despite the abundance of information available in these weblogs, identifying and extracting pertinent information and key features from them necessitate extensive engineering endeavors. The intricate nature of the data also poses a challenge for interpretation, especially for non-experts. In this study, we introduce a sophisticated and interactive recommendation framework denoted as InteraRec, which diverges from conventional approaches that exclusively depend on weblogs for recommendation generation. InteraRec framework captures high-frequency screenshots of web pages as users navigate through a website. Leveraging state-of-the-art multimodal large language models (MLLMs), it extracts valuable insights into user preferences from these screenshots by generating a textual summary based on predefined keywords. Subsequently, an LLM-integrated optimization setup utilizes this summary to generate tailored recommendations. Through our experiments, we demonstrate the effectiveness of InteraRec in providing users with valuable and personalized offerings. Furthermore, we explore the integration of session-based recommendation systems into the InteraRec framework, aiming to enhance its overall performance. Finally, we curate a new dataset comprising of screenshots from product web pages on the Amazon website for the validation of the InteraRec framework. Detailed experiments demonstrate the efficacy of the InteraRec framework in delivering valuable and personalized recommendations tailored to individual user preferences.
Authors: Kedi Chen, Qin Chen, Jie Zhou, Yishen He, Liang He
Abstract: Since large language models (LLMs) achieve significant success in recent years, the hallucination issue remains a challenge, numerous benchmarks are proposed to detect the hallucination. Nevertheless, some of these benchmarks are not naturally generated by LLMs but are intentionally induced. Also, many merely focus on the factuality hallucination while ignoring the faithfulness hallucination. Additionally, although dialogue pattern is more widely utilized in the era of LLMs, current benchmarks only concentrate on sentence-level and passage-level hallucination. In this study, we propose DiaHalu, the first dialogue-level hallucination evaluation benchmark to our knowledge. Initially, we integrate the collected topics into system prompts and facilitate a dialogue between two ChatGPT3.5. Subsequently, we manually modify the contents that do not adhere to human language conventions and then have LLMs re-generate, simulating authentic human-machine interaction scenarios. Finally, professional scholars annotate all the samples in the dataset. DiaHalu covers four common multi-turn dialogue domains and five hallucination subtypes, extended from factuality and faithfulness hallucination. Experiments through some well-known LLMs and detection methods on the dataset show that DiaHalu is a challenging benchmark, holding significant value for further research.
Authors: Yuexin Li, Chengyu Huang, Shumin Deng, Mei Lin Lock, Tri Cao, Nay Oo, Hoon Wei Lim, Bryan Hooi
Abstract: Phishing attacks have inflicted substantial losses on individuals and businesses alike, necessitating the development of robust and efficient automated phishing detection approaches. Reference-based phishing detectors (RBPDs), which compare the logos on a target webpage to a known set of logos, have emerged as the state-of-the-art approach. However, a major limitation of existing RBPDs is that they rely on a manually constructed brand knowledge base, making it infeasible to scale to a large number of brands, which results in false negative errors due to the insufficient brand coverage of the knowledge base. To address this issue, we propose an automated knowledge collection pipeline, using which we collect a large-scale multimodal brand knowledge base, KnowPhish, containing 20k brands with rich information about each brand. KnowPhish can be used to boost the performance of existing RBPDs in a plug-and-play manner. A second limitation of existing RBPDs is that they solely rely on the image modality, ignoring useful textual information present in the webpage HTML. To utilize this textual information, we propose a Large Language Model (LLM)-based approach to extract brand information of webpages from text. Our resulting multimodal phishing detection approach, KnowPhish Detector (KPD), can detect phishing webpages with or without logos. We evaluate KnowPhish and KPD on a manually validated dataset, and a field study under Singapore's local context, showing substantial improvements in effectiveness and efficiency compared to state-of-the-art baselines.
Authors: Bosheng Ding, Chengwei Qin, Ruochen Zhao, Tianze Luo, Xinze Li, Guizhen Chen, Wenhan Xia, Junjie Hu, Anh Tuan Luu, Shafiq Joty
Abstract: In the rapidly evolving field of large language models (LLMs), data augmentation (DA) has emerged as a pivotal technique for enhancing model performance by diversifying training examples without the need for additional data collection. This survey explores the transformative impact of LLMs on DA, particularly addressing the unique challenges and opportunities they present in the context of natural language processing (NLP) and beyond. From both data and learning perspectives, we examine various strategies that utilize LLMs for data augmentation, including a novel exploration of learning paradigms where LLM-generated data is used for diverse forms of further training. Additionally, this paper highlights the primary open challenges faced in this domain, ranging from controllable data augmentation to multi-modal data augmentation. This survey highlights a paradigm shift introduced by LLMs in DA, and aims to serve as a comprehensive guide for researchers and practitioners.
Authors: Lilian Ngweta, Mayank Agarwal, Subha Maity, Alex Gittens, Yuekai Sun, Mikhail Yurochkin
Abstract: Large Language Models (LLMs) need to be aligned with human expectations to ensure their safety and utility in most applications. Alignment is challenging, costly, and needs to be repeated for every LLM and alignment criterion. We propose to decouple LLMs and alignment by training aligner models that can be used to align any LLM for a given criteria on an as-needed basis, thus also reducing the potential negative impacts of alignment on performance. Our recipe for training the aligner models solely relies on synthetic data generated with a (prompted) LLM and can be easily adjusted for a variety of alignment criteria. We use the same synthetic data to train inspectors, binary miss-alignment classification models to guide a "squad" of multiple aligners. Our empirical results demonstrate consistent improvements when applying aligner squad to various LLMs, including chat-aligned models, across several instruction-following and red-teaming datasets.
Authors: Xingwei Qu, Yiming Liang, Yucheng Wang, Tianyu Zheng, Tommy Yue, Lei Ma, Stephen W. Huang, Jiajun Zhang, Yinan Shi, Chenghua Lin, Jie Fu, Ge Zhang
Abstract: It has long been assumed that the sheer number of parameters in large language models (LLMs) drives in-context learning (ICL) capabilities, enabling remarkable performance improvements by leveraging task-specific demonstrations. Challenging this hypothesis, we introduce DEEP-ICL, a novel task Definition Enriched ExPert Ensembling methodology for ICL. DEEP-ICL explicitly extracts task definitions from given demonstrations and generates responses through learning task-specific examples. We argue that improvement from ICL does not directly rely on model size, but essentially stems from understanding task definitions and task-guided learning. Inspired by this, DEEP-ICL combines two 3B models with distinct roles (one for concluding task definitions and the other for learning task demonstrations) and achieves comparable performance to LLaMA2-13B. Furthermore, our framework outperforms conventional ICL by overcoming pretraining sequence length limitations, by supporting unlimited demonstrations. We contend that DEEP-ICL presents a novel alternative for achieving efficient few-shot learning, extending beyond the conventional ICL.
Authors: Weixin Liang, Zachary Izzo, Yaohui Zhang, Haley Lepp, Hancheng Cao, Xuandong Zhao, Lingjiao Chen, Haotian Ye, Sheng Liu, Zhi Huang, Daniel A. McFarland, James Y. Zou
Abstract: We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM). Our maximum likelihood model leverages expert-written and AI-generated reference texts to accurately and efficiently examine real-world LLM-use at the corpus level. We apply this approach to a case study of scientific peer review in AI conferences that took place after the release of ChatGPT: ICLR 2024, NeurIPS 2023, CoRL 2023 and EMNLP 2023. Our results suggest that between 6.5% and 16.9% of text submitted as peer reviews to these conferences could have been substantially modified by LLMs, i.e. beyond spell-checking or minor writing updates. The circumstances in which generated text occurs offer insight into user behavior: the estimated fraction of LLM-generated text is higher in reviews which report lower confidence, were submitted close to the deadline, and from reviewers who are less likely to respond to author rebuttals. We also observe corpus-level trends in generated text which may be too subtle to detect at the individual level, and discuss the implications of such trends on peer review. We call for future interdisciplinary work to examine how LLM use is changing our information and knowledge practices.
Authors: Alexandre Drouin, Maxime Gasse, Massimo Caccia, Issam H. Laradji, Manuel Del Verme, Tom Marty, L\'eo Boisvert, Megh Thakkar, Quentin Cappart, David Vazquez, Nicolas Chapados, Alexandre Lacoste
Abstract: We study the use of large language model-based agents for interacting with software via web browsers. Unlike prior work, we focus on measuring the agents' ability to perform tasks that span the typical daily work of knowledge workers utilizing enterprise software systems. To this end, we propose WorkArena, a remote-hosted benchmark of 33 tasks based on the widely-used ServiceNow platform. We also introduce BrowserGym, an environment for the design and evaluation of such agents, offering a rich set of actions as well as multimodal observations. Our empirical evaluation reveals that while current agents show promise on WorkArena, there remains a considerable gap towards achieving full task automation. Notably, our analysis uncovers a significant performance disparity between open and closed-source LLMs, highlighting a critical area for future exploration and development in the field.
Authors: Xiang Hu, Pengyu Ji, Qingyang Zhu, Wei Wu, Kewei Tu
Abstract: A syntactic language model (SLM) incrementally generates a sentence with its syntactic tree in a left-to-right manner. We present Generative Pretrained Structured Transformers (GPST), an unsupervised SLM at scale capable of being pre-trained from scratch on raw texts with high parallelism. GPST circumvents the limitations of previous SLMs such as relying on gold trees and sequential training. It consists of two components, a usual SLM supervised by a uni-directional language modeling loss, and an additional composition model, which induces syntactic parse trees and computes constituent representations, supervised by a bi-directional language modeling loss. We propose a representation surrogate to enable joint parallel training of the two models in a hard-EM fashion. We pre-train GPST on OpenWebText, a corpus with $9$ billion tokens, and demonstrate the superiority of GPST over GPT-2 with a comparable size in numerous tasks covering both language understanding and language generation. Meanwhile, GPST also significantly outperforms existing unsupervised SLMs on left-to-right grammar induction, while holding a substantial acceleration on training.
Authors: Danru Xu, Dingling Yao, S\'ebastien Lachapelle, Perouz Taslakian, Julius von K\"ugelgen, Francesco Locatello, Sara Magliacane
Abstract: Causal representation learning aims at identifying high-level causal variables from perceptual data. Most methods assume that all latent causal variables are captured in the high-dimensional observations. We instead consider a partially observed setting, in which each measurement only provides information about a subset of the underlying causal state. Prior work has studied this setting with multiple domains or views, each depending on a fixed subset of latents. Here, we focus on learning from unpaired observations from a dataset with an instance-dependent partial observability pattern. Our main contribution is to establish two identifiability results for this setting: one for linear mixing functions without parametric assumptions on the underlying causal model, and one for piecewise linear mixing functions with Gaussian latent causal variables. Based on these insights, we propose two methods for estimating the underlying causal variables by enforcing sparsity in the inferred representation. Experiments on different simulated datasets and established benchmarks highlight the effectiveness of our approach in recovering the ground-truth latents.
Authors: Lukas Rauch, Raphael Schwinger, Moritz Wirth, Ren\'e Heinrich, Denis Huseljic, Jonas Lange, Stefan Kahl, Bernhard Sick, Sven Tomforde, Christoph Scholz
Abstract: Deep learning (DL) models have emerged as a powerful tool in avian bioacoustics to assess environmental health. To maximize the potential of cost-effective and minimal-invasive passive acoustic monitoring (PAM), DL models must analyze bird vocalizations across a wide range of species and environmental conditions. However, data fragmentation challenges a comprehensive evaluation of generalization performance. Therefore, we introduce the BirdSet dataset, comprising approximately 520,000 global bird recordings for training and over 400 hours of PAM recordings for testing. Our benchmark offers baselines for several DL models to enhance comparability and consolidate research across studies, along with code implementations that include comprehensive training and evaluation protocols.
Authors: Paul S. Scotti, Mihir Tripathy, Cesar Kadir Torrico Villanueva, Reese Kneeland, Tong Chen, Ashutosh Narang, Charan Santhirasegaran, Jonathan Xu, Thomas Naselaris, Kenneth A. Norman, Tanishq Mathew Abraham
Abstract: Reconstructions of visual perception from brain activity have improved tremendously, but the practical utility of such methods has been limited. This is because such models are trained independently per subject where each subject requires dozens of hours of expensive fMRI training data to attain high-quality results. The present work showcases high-quality reconstructions using only 1 hour of fMRI training data. We pretrain our model across 7 subjects and then fine-tune on minimal data from a new subject. Our novel functional alignment procedure linearly maps all brain data to a shared-subject latent space, followed by a shared non-linear mapping to CLIP image space. We then map from CLIP space to pixel space by fine-tuning Stable Diffusion XL to accept CLIP latents as inputs instead of text. This approach improves out-of-subject generalization with limited training data and also attains state-of-the-art image retrieval and reconstruction metrics compared to single-subject approaches. MindEye2 demonstrates how accurate reconstructions of perception are possible from a single visit to the MRI facility. All code is available on GitHub.
Authors: Huy Nghiem, Hal Daum\'e III
Abstract: The widespread use of social media necessitates reliable and efficient detection of offensive content to mitigate harmful effects. Although sophisticated models perform well on individual datasets, they often fail to generalize due to varying definitions and labeling of "offensive content." In this paper, we introduce HateCOT, an English dataset with over 52,000 samples from diverse sources, featuring explanations generated by GPT-3.5Turbo and curated by humans. We demonstrate that pretraining on HateCOT significantly enhances the performance of open-source Large Language Models on three benchmark datasets for offensive content detection in both zero-shot and few-shot settings, despite differences in domain and task. Additionally, HateCOT facilitates effective K-shot fine-tuning of LLMs with limited data and improves the quality of their explanations, as confirmed by our human evaluation.
Authors: Tobias Hallmen, Fabian Deuser, Norbert Oswald, Elisabeth Andr\'e
Abstract: In this research, we introduce a novel methodology for assessing Emotional Mimicry Intensity (EMI) as part of the 6th Workshop and Competition on Affective Behavior Analysis in-the-wild. Our methodology utilises the Wav2Vec 2.0 architecture, which has been pre-trained on an extensive podcast dataset, to capture a wide array of audio features that include both linguistic and paralinguistic components. We refine our feature extraction process by employing a fusion technique that combines individual features with a global mean vector, thereby embedding a broader contextual understanding into our analysis. A key aspect of our approach is the multi-task fusion strategy that not only leverages these features but also incorporates a pre-trained Valence-Arousal-Dominance (VAD) model. This integration is designed to refine emotion intensity prediction by concurrently processing multiple emotional dimensions, thereby embedding a richer contextual understanding into our framework. For the temporal analysis of audio data, our feature fusion process utilises a Long Short-Term Memory (LSTM) network. This approach, which relies solely on the provided audio data, shows marked advancements over the existing baseline, offering a more comprehensive understanding of emotional mimicry in naturalistic settings, achieving the second place in the EMI challenge.
Authors: Bang Nguyen, Mengxia Yu, Yun Huang, Meng Jiang
Abstract: Reference-based metrics such as BLEU and BERTScore are widely used to evaluate question generation (QG). In this study, on QG benchmarks such as SQuAD and HotpotQA, we find that using human-written references cannot guarantee the effectiveness of the reference-based metrics. Most QG benchmarks have only one reference; we replicated the annotation process and collect another reference. A good metric was expected to grade a human-validated question no worse than generated questions. However, the results of reference-based metrics on our newly collected reference disproved the metrics themselves. We propose a reference-free metric consisted of multi-dimensional criteria such as naturalness, answerability, and complexity, utilizing large language models. These criteria are not constrained to the syntactic or semantic of a single reference question, and the metric does not require a diverse set of references. Experiments reveal that our metric accurately distinguishes between high-quality questions and flawed ones, and achieves state-of-the-art alignment with human judgment.
Authors: Yiwu Zhong, Zi-Yuan Hu, Michael R. Lyu, Liwei Wang
Abstract: Visual representation learning has been a cornerstone in computer vision, involving typical forms such as visual embeddings, structural symbols, and text-based representations. Despite the success of CLIP-type visual embeddings, they often lack access to world knowledge critical for visual reasoning. In this work, we propose Visual Table, a novel form of visual representation tailored for visual reasoning. Visual tables are constructed as hierarchical descriptions of visual scenes, featuring a scene description and multiple object-centric descriptions covering categories, attributes, and knowledge. Thanks to the structural and textual formats, visual tables offer unique advantages over mere visual embeddings, such as interpretability and controllable editing. Furthermore, they deliver instance-level world knowledge and detailed attributes that are essential for visual reasoning. To create visual tables, we develop a generator trained on the dataset with collected, small-scale annotations. Extensive results on 11 visual reasoning benchmarks demonstrate that the generated visual tables significantly outperform previous structural and text-based representations. Moreover, they consistently enhance state-of-the-art multimodal large language models across diverse benchmarks, showcasing their potential for advancing visual reasoning tasks. Our code is available at https://github.com/LaVi-Lab/Visual-Table.
Authors: Luke Rowe, Roger Girgis, Anthony Gosselin, Bruno Carrez, Florian Golemo, Felix Heide, Liam Paull, Christopher Pal
Abstract: Evaluating autonomous vehicle stacks (AVs) in simulation typically involves replaying driving logs from real-world recorded traffic. However, agents replayed from offline data are not reactive and hard to intuitively control. Existing approaches address these challenges by proposing methods that rely on heuristics or generative models of real-world data but these approaches either lack realism or necessitate costly iterative sampling procedures to control the generated behaviours. In this work, we take an alternative approach and propose CtRL-Sim, a method that leverages return-conditioned offline reinforcement learning to efficiently generate reactive and controllable traffic agents. Specifically, we process real-world driving data through a physics-enhanced Nocturne simulator to generate a diverse offline reinforcement learning dataset, annotated with various reward terms. With this dataset, we train a return-conditioned multi-agent behaviour model that allows for fine-grained manipulation of agent behaviours by modifying the desired returns for the various reward components. This capability enables the generation of a wide range of driving behaviours beyond the scope of the initial dataset, including adversarial behaviours. We demonstrate that CtRL-Sim can generate diverse and realistic safety-critical scenarios while providing fine-grained control over agent behaviours.
Authors: Rolf Bader, Simon Linke, Stefanie Gernert
Abstract: A nonlinear-dynamical algorithm for city planning is proposed as an Impulse Pattern Formulation (IPF) for predicting relevant parameters like health, artistic freedom, or financial developments of different social or political stakeholders over the cause of a planning process. The IPF has already shown high predictive precision at low computational cost in musical instrument simulations, brain dynamics, and human-human interactions. The social and political IPF consists of three basic equations of system state developments, self-adaptation of stakeholders, two adaptive interactions, and external impact terms suitable for respective planning situations. Typical scenarios of stakeholder interactions and developments are modeled by adjusting a set of system parameters. These include stakeholder reaction to external input, enhanced system stability through self-adaptation, stakeholder convergence due to adaptive interaction, as well as complex dynamics in terms of fixed stakeholder impacts. A workflow for implementing the algorithm in real city planning scenarios is outlined. This workflow includes machine learning of a suitable set of parameters suggesting best-practice planning to aim at the desired development of the planning process and its output.
Authors: Chuan Meng, Negar Arabzadeh, Arian Askari, Mohammad Aliannejadi, Maarten de Rijke
Abstract: Query performance prediction (QPP) aims to estimate the retrieval quality of a search system for a query without human relevance judgments. Previous QPP methods typically return a single scalar value and do not require the predicted values to approximate a specific information retrieval (IR) evaluation measure, leading to certain drawbacks: (i) a single scalar is insufficient to accurately represent different IR evaluation measures, especially when metrics do not highly correlate, and (ii) a single scalar limits the interpretability of QPP methods because solely using a scalar is insufficient to explain QPP results. To address these issues, we propose a QPP framework using automatically generated relevance judgments (QPP-GenRE), which decomposes QPP into independent subtasks of predicting the relevance of each item in a ranked list to a given query. This allows us to predict any IR evaluation measure using the generated relevance judgments as pseudo-labels. This also allows us to interpret predicted IR evaluation measures, and identify, track and rectify errors in generated relevance judgments to improve QPP quality. We predict an item's relevance by using open-source large language models (LLMs) to ensure scientific reproducibility. We face two main challenges: (i) excessive computational costs of judging an entire corpus for predicting a metric considering recall, and (ii) limited performance in prompting open-source LLMs in a zero-/few-shot manner. To solve the challenges, we devise an approximation strategy to predict an IR measure considering recall and propose to fine-tune open-source LLMs using human-labeled relevance judgments. Experiments on the TREC 2019-2022 deep learning tracks show that QPP-GenRE achieves state-of-the-art QPP quality for both lexical and neural rankers.
Authors: Taiqiang Wu, Chaofan Tao, Jiahao Wang, Zhe Zhao, Ngai Wong
Abstract: Kullback-Leiber divergence has been widely used in Knowledge Distillation (KD) to compress Large Language Models (LLMs). Contrary to prior assertions that reverse Kullback-Leibler (RKL) divergence is mode-seeking and thus preferable over the mean-seeking forward Kullback-Leibler (FKL) divergence, this study empirically and theoretically demonstrates that neither mode-seeking nor mean-seeking properties manifest in KD for LLMs. Instead, RKL and FKL are found to share the same optimization objective and both converge after a sufficient number of epochs. However, due to practical constraints, LLMs are seldom trained for such an extensive number of epochs. Meanwhile, we further find that RKL focuses on the tail part of the distributions, while FKL focuses on the head part at the beginning epochs. Consequently, we propose a simple yet effective Adaptive Kullback-Leiber (AKL) divergence method, which adaptively allocates weights to combine FKL and RKL. Metric-based and GPT-4-based evaluations demonstrate that the proposed AKL outperforms the baselines across various tasks and improves the diversity and quality of generated responses.
Authors: Tom\'as Vergara-Browne, \'Alvaro Soto, Akiko Aizawa
Abstract: We introduce eigenpruning, a method that removes singular values from weight matrices in an LLM to improve its performance in a particular task. This method is inspired by interpretability methods designed to automatically find subnetworks of a model which solve a specific task. In our tests, the pruned model outperforms the original model by a large margin, while only requiring minimal computation to prune the weight matrices. In the case of a small synthetic task in integer multiplication, the Phi-2 model can improve its accuracy in the test set from 13.75% to 97.50%. Interestingly, these results seem to indicate the existence of a computation path that can solve the task very effectively, but it was not being used by the original model. Finally, we publicly release our implementation.
Authors: Zi-Hao Qiu, Siqi Guo, Mao Xu, Tuo Zhao, Lijun Zhang, Tianbao Yang
Abstract: The temperature parameter plays a profound role during training and/or inference with large foundation models (LFMs) such as large language models (LLMs) and CLIP models. Particularly, it adjusts the logits in the softmax function in LLMs, which is crucial for next token generation, and it scales the similarities in the contrastive loss for training CLIP models. A significant question remains: Is it viable to learn a neural network to predict a personalized temperature of any input data for enhancing LFMs"? In this paper, we present a principled framework for learning a small yet generalizable temperature prediction network (TempNet) to improve LFMs. Our solution is composed of a novel learning framework with a robust loss underpinned by constrained distributionally robust optimization (DRO), and a properly designed TempNet with theoretical inspiration. TempNet can be trained together with a large foundation model from scratch or learned separately given a pretrained foundation model. It is not only useful for predicting personalized temperature to promote the training of LFMs but also generalizable and transferable to new tasks. Our experiments on LLMs and CLIP models demonstrate that TempNet greatly improves the performance of existing solutions or models, e.g. Table 1. The code to reproduce the experimental results in this paper can be found at https://github.com/zhqiu/TempNet.
Authors: Haokun Zhao, Haixia Han, Jie Shi, Chengyu Du, Jiaqing Liang, Yanghua Xiao
Abstract: As world knowledge evolves and new task paradigms emerge, Continual Learning (CL) is crucial for keeping Large Language Models (LLMs) up-to-date and addressing their shortcomings. In practical applications, LLMs often require both continual instruction tuning (CIT) and continual pre-training (CPT) to adapt to new task paradigms and acquire necessary knowledge for task-solving. However, it remains challenging to collect CPT data that addresses the knowledge deficiencies in models while maintaining adequate volume, and improving the efficiency of utilizing this data also presents significant difficulties. Inspired by the 'summarizing mistakes' learning skill, we propose the Continue Evolving from Mistakes (CEM) method, aiming to provide a data-efficient approach for collecting CPT data and continually improving LLMs' performance through iterative evaluation and supplementation with mistake-relevant knowledge. To efficiently utilize these CPT data and mitigate forgetting, we design a novel CL training set construction paradigm that integrates parallel CIT and CPT data. Extensive experiments demonstrate the efficacy of the CEM method, achieving up to a 17% improvement in accuracy in the best case. Furthermore, additional experiments confirm the potential of combining CEM with catastrophic forgetting mitigation methods, enabling iterative and continual model evolution.
Authors: Zihao Li, Yucheng Shi, Zirui Liu, Fan Yang, Ali Payani, Ninghao Liu, Mengnan Du
Abstract: The development of Large Language Models (LLMs) relies on extensive text corpora, which are often unevenly distributed across languages. This imbalance results in LLMs performing significantly better on high-resource languages like English, German, and French, while their capabilities in low-resource languages remain inadequate. Currently, there is a lack of quantitative methods to evaluate the performance of LLMs in these low-resource languages. To address this gap, we propose the Language Ranker, an intrinsic metric designed to benchmark and rank languages based on LLM performance using internal representations. By comparing the LLM's internal representation of various languages against a baseline derived from English, we can assess the model's multilingual capabilities in a robust and language-agnostic manner. Our analysis reveals that high-resource languages exhibit higher similarity scores with English, demonstrating superior performance, while low-resource languages show lower similarity scores, underscoring the effectiveness of our metric in assessing language-specific capabilities. Besides, the experiments show that there is a strong correlation between the LLM's performance in different languages and the proportion of those languages in its pre-training corpus. These insights underscore the efficacy of the Language Ranker as a tool for evaluating LLM performance across different languages, particularly those with limited resources.
Authors: Siya Qi, Yulan He, Zheng Yuan
Abstract: Hallucination in Natural Language Generation (NLG) is like the elephant in the room, obvious but often overlooked until recent achievements significantly improved the fluency and grammaticality of generated text. As the capabilities of text generation models have improved, researchers have begun to pay more attention to the phenomenon of hallucination. Despite significant progress in this field in recent years, the evaluation system for hallucination is complex and diverse, lacking clear organization. We are the first to comprehensively survey how various evaluation methods have evolved with the development of text generation models from three dimensions, including hallucinated fact granularity, evaluator design principles, and assessment facets. This survey aims to help researchers identify current limitations in hallucination evaluation and highlight future research directions.
Authors: Kunxi Li, Tianyu Zhan, Kairui Fu, Shengyu Zhang, Kun Kuang, Jiwei Li, Zhou Zhao, Fei Wu
Abstract: In this study, we focus on heterogeneous knowledge transfer across entirely different model architectures, tasks, and modalities. Existing knowledge transfer methods (e.g., backbone sharing, knowledge distillation) often hinge on shared elements within model structures or task-specific features/labels, limiting transfers to complex model types or tasks. To overcome these challenges, we present MergeNet, which learns to bridge the gap of parameter spaces of heterogeneous models, facilitating the direct interaction, extraction, and application of knowledge within these parameter spaces. The core mechanism of MergeNet lies in the parameter adapter, which operates by querying the source model's low-rank parameters and adeptly learning to identify and map parameters into the target model. MergeNet is learned alongside both models, allowing our framework to dynamically transfer and adapt knowledge relevant to the current stage, including the training trajectory knowledge of the source model. Extensive experiments on heterogeneous knowledge transfer demonstrate significant improvements in challenging settings, where representative approaches may falter or prove less applicable.
Authors: Yuhong Li, Yingbing Huang, Bowen Yang, Bharat Venkitesh, Acyr Locatelli, Hanchen Ye, Tianle Cai, Patrick Lewis, Deming Chen
Abstract: Large Language Models (LLMs) have made remarkable progress in processing extensive contexts, with the Key-Value (KV) cache playing a vital role in enhancing their performance. However, the growth of the KV cache in response to increasing input length poses challenges to memory and time efficiency. To address this problem, this paper introduces SnapKV, an innovative and fine-tuning-free approach that efficiently minimizes KV cache size while still delivering comparable performance in real-world applications. We discover that each attention head in the model consistently focuses on specific prompt attention features during generation. Meanwhile, this robust pattern can be obtained from an 'observation' window located at the end of the prompts. Drawing on this insight, SnapKV automatically compresses KV caches by selecting clustered important KV positions for each attention head. Our approach significantly reduces the growing computational overhead and memory footprint when processing long input sequences. Specifically, SnapKV achieves a consistent decoding speed with a 3.6x increase in generation speed and an 8.2x enhancement in memory efficiency compared to the baseline when processing inputs of 16K tokens. At the same time, it maintains comparable performance to the baseline models across 16 long sequence datasets. Moreover, SnapKV can process up to 380K context tokens on a single A100-80GB GPU using HuggingFace implementation with minor changes, exhibiting only a negligible accuracy drop in the Needle-in-a-Haystack test. Further comprehensive studies suggest SnapKV's potential for practical applications.
Authors: Siyin Wang, Chao-Han Huck Yang, Ji Wu, Chao Zhang
Abstract: Large language models (LLMs) can adapt to new tasks through in-context learning (ICL) based on a few examples presented in dialogue history without any model parameter update. Despite such convenience, the performance of ICL heavily depends on the quality of the in-context examples presented, which makes the in-context example selection approach a critical choice. This paper proposes a novel Bayesian in-Context example Selection method (ByCS) for ICL. Extending the inference probability conditioned on in-context examples based on Bayes' theorem, ByCS focuses on the inverse inference conditioned on test input. Following the assumption that accurate inverse inference probability (likelihood) will result in accurate inference probability (posterior), in-context examples are selected based on their inverse inference results. Diverse and extensive cross-tasking and cross-modality experiments are performed with speech, text, and image examples. Experimental results show the efficacy and robustness of our ByCS method on various models, tasks and modalities.
Authors: Ziming Liu, Yixuan Wang, Sachin Vaidya, Fabian Ruehle, James Halverson, Marin Solja\v{c}i\'c, Thomas Y. Hou, Max Tegmark
Abstract: Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs). While MLPs have fixed activation functions on nodes ("neurons"), KANs have learnable activation functions on edges ("weights"). KANs have no linear weights at all -- every weight parameter is replaced by a univariate function parametrized as a spline. We show that this seemingly simple change makes KANs outperform MLPs in terms of accuracy and interpretability. For accuracy, much smaller KANs can achieve comparable or better accuracy than much larger MLPs in data fitting and PDE solving. Theoretically and empirically, KANs possess faster neural scaling laws than MLPs. For interpretability, KANs can be intuitively visualized and can easily interact with human users. Through two examples in mathematics and physics, KANs are shown to be useful collaborators helping scientists (re)discover mathematical and physical laws. In summary, KANs are promising alternatives for MLPs, opening opportunities for further improving today's deep learning models which rely heavily on MLPs.
Authors: Wonjoong Kim, Sangwu Park, Yeonjun In, Seokwon Han, Chanyoung Park
Abstract: Recently, interpreting complex charts with logical reasoning has emerged as challenges due to the development of vision-language models. A prior state-of-the-art (SOTA) model has presented an end-to-end method that leverages the vision-language model to convert charts into table format utilizing Large Language Model (LLM) for reasoning. However, unlike natural images, charts contain a mix of essential and irrelevant information required for chart reasoning, and we discover that this characteristic can lower the performance of chart-to-table extraction. In this paper, we introduce SIMPLOT, a method designed to extract only the elements necessary for chart reasoning. The proposed method involves two steps: 1) training to mimic a simple plot that contains only the essential information from a complex chart for table extraction, followed by 2) performing reasoning based on the table. Our model enables accurate chart reasoning without the need for additional annotations or datasets, and its effectiveness is demonstrated through various experiments. Furthermore, we propose a novel prompt mimicking how human interpret charts for more accurate reasoning. Our source code is available at https://github.com/sangwu99/Simplot.
Authors: Yu Pan, Yuguang Yang, Heng Lu, Lei Ma, Jianjun Zhao
Abstract: The continuous evolution of pre-trained speech models has greatly advanced Speech Emotion Recognition (SER). However, current research typically relies on utterance-level emotion labels, inadequately capturing the complexity of emotions within a single utterance. In this paper, we introduce GMP-TL, a novel SER framework that employs gender-augmented multi-scale pseudo-label (GMP) based transfer learning to mitigate this gap. Specifically, GMP-TL initially uses the pre-trained HuBERT, implementing multi-task learning and multi-scale k-means clustering to acquire frame-level GMPs. Subsequently, to fully leverage frame-level GMPs and utterance-level emotion labels, a two-stage model fine-tuning approach is presented to further optimize GMP-TL. Experiments on IEMOCAP show that our GMP-TL attains a WAR of 80.0% and an UAR of 82.0%, achieving superior performance compared to state-of-the-art unimodal SER methods while also yielding comparable results to multimodal SER approaches.
Authors: Srikanth Malla, Joon Hee Choi, Chiho Choi
Abstract: Adapting pre-trained large language models to different domains in natural language processing requires two key considerations: high computational demands and model's inability to continual adaptation. To simultaneously address both issues, this paper presents COPAL (COntinual Pruning in Adaptive Language settings), an algorithm developed for pruning large language generative models under a continual model adaptation setting. While avoiding resource-heavy finetuning or retraining, our pruning process is guided by the proposed sensitivity analysis. The sensitivity effectively measures model's ability to withstand perturbations introduced by the new dataset and finds model's weights that are relevant for all encountered datasets. As a result, COPAL allows seamless model adaptation to new domains while enhancing the resource efficiency. Our empirical evaluation on a various size of LLMs show that COPAL outperforms baseline models, demonstrating its efficacy in efficiency and adaptability.
Authors: Chenkai Mao, Robert Lupoiu, Tianxiang Dai, Mingkun Chen, Jonathan A. Fan
Abstract: Surrogate neural network-based partial differential equation (PDE) solvers have the potential to solve PDEs in an accelerated manner, but they are largely limited to systems featuring fixed domain sizes, geometric layouts, and boundary conditions. We propose Specialized Neural Accelerator-Powered Domain Decomposition Methods (SNAP-DDM), a DDM-based approach to PDE solving in which subdomain problems containing arbitrary boundary conditions and geometric parameters are accurately solved using an ensemble of specialized neural operators. We tailor SNAP-DDM to 2D electromagnetics and fluidic flow problems and show how innovations in network architecture and loss function engineering can produce specialized surrogate subdomain solvers with near unity accuracy. We utilize these solvers with standard DDM algorithms to accurately solve freeform electromagnetics and fluids problems featuring a wide range of domain sizes.
Authors: Jesher Joshua M, Adhithya R, Sree Dananjay S, M Revathi
Abstract: Web phishing poses a dynamic threat, requiring detection systems to quickly adapt to the latest tactics. Traditional approaches of accumulating data and periodically retraining models are outpaced. We propose a novel paradigm combining federated learning and continual learning, enabling distributed nodes to continually update models on streams of new phishing data, without accumulating data. These locally adapted models are then aggregated at a central server via federated learning. To enhance detection, we introduce a custom attention-based classifier model with residual connections, tailored for web phishing, leveraging attention mechanisms to capture intricate phishing patterns. We evaluate our hybrid learning paradigm across continual learning strategies (cumulative, replay, MIR, LwF) and model architectures through an empirical investigation. Our main contributions are: (1) a new hybrid federated-continual learning paradigm for robust web phishing detection, and (2) a novel attention + residual connections based model explicitly designed for this task, attaining 0.93 accuracy, 0.90 precision, 0.96 recall and 0.93 f1-score with the LwF strategy, outperforming traditional approaches in detecting emerging phishing threats while retaining past knowledge.
Authors: Zineb Senane, Lele Cao, Valentin Leonhard Buchner, Yusuke Tashiro, Lei You, Pawel Herman, Mats Nordahl, Ruibo Tu, Vilhelm von Ehrenheim
Abstract: Time Series Representation Learning (TSRL) focuses on generating informative representations for various Time Series (TS) modeling tasks. Traditional Self-Supervised Learning (SSL) methods in TSRL fall into four main categories: reconstructive, adversarial, contrastive, and predictive, each with a common challenge of sensitivity to noise and intricate data nuances. Recently, diffusion-based methods have shown advanced generative capabilities. However, they primarily target specific application scenarios like imputation and forecasting, leaving a gap in leveraging diffusion models for generic TSRL. Our work, Time Series Diffusion Embedding (TSDE), bridges this gap as the first diffusion-based SSL TSRL approach. TSDE segments TS data into observed and masked parts using an Imputation-Interpolation-Forecasting (IIF) mask. It applies a trainable embedding function, featuring dual-orthogonal Transformer encoders with a crossover mechanism, to the observed part. We train a reverse diffusion process conditioned on the embeddings, designed to predict noise added to the masked part. Extensive experiments demonstrate TSDE's superiority in imputation, interpolation, forecasting, anomaly detection, classification, and clustering. We also conduct an ablation study, present embedding visualizations, and compare inference speed, further substantiating TSDE's efficiency and validity in learning representations of TS data.
Authors: Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, Qing Li
Abstract: As one of the most advanced techniques in AI, Retrieval-Augmented Generation (RAG) can offer reliable and up-to-date external knowledge, providing huge convenience for numerous tasks. Particularly in the era of AI-Generated Content (AIGC), the powerful capacity of retrieval in providing additional knowledge enables RAG to assist existing generative AI in producing high-quality outputs. Recently, Large Language Models (LLMs) have demonstrated revolutionary abilities in language understanding and generation, while still facing inherent limitations, such as hallucinations and out-of-date internal knowledge. Given the powerful abilities of RAG in providing the latest and helpful auxiliary information, Retrieval-Augmented Large Language Models (RA-LLMs) have emerged to harness external and authoritative knowledge bases, rather than solely relying on the model's internal knowledge, to augment the generation quality of LLMs. In this survey, we comprehensively review existing research studies in RA-LLMs, covering three primary technical perspectives: architectures, training strategies, and applications. As the preliminary knowledge, we briefly introduce the foundations and recent advances of LLMs. Then, to illustrate the practical significance of RAG for LLMs, we systematically review mainstream relevant work by their architectures, training strategies, and application areas, detailing specifically the challenges of each and the corresponding capabilities of RA-LLMs. Finally, to deliver deeper insights, we discuss current limitations and several promising directions for future research. Updated information about this survey can be found at https://advanced-recommender-systems.github.io/RAG-Meets-LLMs/
URLs: https://advanced-recommender-systems.github.io/RAG-Meets-LLMs/
Authors: Haitao Lin, Odin Zhang, Huifeng Zhao, Dejun Jiang, Lirong Wu, Zicheng Liu, Yufei Huang, Stan Z. Li
Abstract: Therapeutic peptides have proven to have great pharmaceutical value and potential in recent decades. However, methods of AI-assisted peptide drug discovery are not fully explored. To fill the gap, we propose a target-aware peptide design method called \textsc{PPFlow}, based on conditional flow matching on torus manifolds, to model the internal geometries of torsion angles for the peptide structure design. Besides, we establish a protein-peptide binding dataset named PPBench2024 to fill the void of massive data for the task of structure-based peptide drug design and to allow the training of deep learning methods. Extensive experiments show that PPFlow reaches state-of-the-art performance in tasks of peptide drug generation and optimization in comparison with baseline models, and can be generalized to other tasks including docking and side-chain packing.
Authors: Yifan Wu, Lutao Yan, Yuyu Luo, Yunhai Wang, Nan Tang
Abstract: In this paper, we explore a forward-thinking question: Is GPT-4V effective at low-level data analysis tasks on charts? To this end, we first curate a large-scale dataset, named ChartInsights, consisting of 89,388 quartets (chart, task, question, answer) and covering 10 widely-used low-level data analysis tasks on 7 chart types. Firstly, we conduct systematic evaluations to understand the capabilities and limitations of 18 advanced MLLMs, which include 12 open-source models and 6 closed-source models. Starting with a standard textual prompt approach, the average accuracy rate across the 18 MLLMs is 36.17%. Among all the models, GPT-4V achieves the highest accuracy, reaching 56.13%. To understand the limitations of multimodal large models in low-level data analysis tasks, we have designed various experiments to conduct an in-depth test of capabilities of GPT-4V. We further investigate how visual modifications to charts, such as altering visual elements (e.g. changing color schemes) and introducing perturbations (e.g. adding image noise), affect performance of GPT-4V. Secondly, we present 12 experimental findings. These findings suggest potential of GPT-4V to revolutionize interaction with charts and uncover the gap between human analytic needs and capabilities of GPT-4V. Thirdly, we propose a novel textual prompt strategy, named Chain-of-Charts, tailored for low-level analysis tasks, which boosts model performance by 24.36%, resulting in an accuracy of 80.49%. Furthermore, by incorporating a visual prompt strategy that directs attention of GPT-4V to question-relevant visual elements, we further improve accuracy to 83.83%. Our study not only sheds light on the capabilities and limitations of GPT-4V in low-level data analysis tasks but also offers valuable insights for future research.
Authors: Guanghui Wang, Dexi Liu, Jian-Yun Nie, Qizhi Wan, Rong Hu, Xiping Liu, Wanlong Liu, Jiaming Liu
Abstract: Recent advancements in event argument extraction (EAE) involve incorporating useful auxiliary information into models during training and inference, such as retrieved instances and event templates. These methods face two challenges: (1) the retrieval results may be irrelevant and (2) templates are developed independently for each event without considering their possible relationship. In this work, we propose DEGAP to address these challenges through a simple yet effective components: dual prefixes, i.e. learnable prompt vectors, where the instance-oriented prefix and template-oriented prefix are trained to learn information from different event instances and templates. Additionally, we propose an event-guided adaptive gating mechanism, which can adaptively leverage possible connections between different events and thus capture relevant information from the prefix. Finally, these event-guided prefixes provide relevant information as cues to EAE model without retrieval. Extensive experiments demonstrate that our method achieves new state-of-the-art performance on four datasets (ACE05, RAMS, WIKIEVENTS, and MLEE). Further analysis shows the impact of different components.
Authors: Adam Yang, Chen Chen, Konstantinos Pitas
Abstract: State-of-the-art large language models are sometimes distributed as open-source software but are also increasingly provided as a closed-source service. These closed-source large-language models typically see the widest usage by the public, however, they often do not provide an estimate of their uncertainty when responding to queries. As even the best models are prone to ``hallucinating" false information with high confidence, a lack of a reliable estimate of uncertainty limits the applicability of these models in critical settings. We explore estimating the uncertainty of closed-source LLMs via multiple rephrasings of an original base query. Specifically, we ask the model, multiple rephrased questions, and use the similarity of the answers as an estimate of uncertainty. We diverge from previous work in i) providing rules for rephrasing that are simple to memorize and use in practice ii) proposing a theoretical framework for why multiple rephrased queries obtain calibrated uncertainty estimates. Our method demonstrates significant improvements in the calibration of uncertainty estimates compared to the baseline and provides intuition as to how query strategies should be designed for optimal test calibration.
Authors: Yinuo Wang, Likun Wang, Yuxuan Jiang, Wenjun Zou, Tong Liu, Xujie Song, Wenxuan Wang, Liming Xiao, Jiang Wu, Jingliang Duan, Shengbo Eben Li
Abstract: Reinforcement learning (RL) has proven highly effective in addressing complex decision-making and control tasks. However, in most traditional RL algorithms, the policy is typically parameterized as a diagonal Gaussian distribution with learned mean and variance, which constrains their capability to acquire complex policies. In response to this problem, we propose an online RL algorithm termed diffusion actor-critic with entropy regulator (DACER). This algorithm conceptualizes the reverse process of the diffusion model as a novel policy function and leverages the capability of the diffusion model to fit multimodal distributions, thereby enhancing the representational capacity of the policy. Since the distribution of the diffusion policy lacks an analytical expression, its entropy cannot be determined analytically. To mitigate this, we propose a method to estimate the entropy of the diffusion policy utilizing Gaussian mixture model. Building on the estimated entropy, we can learn a parameter $\alpha$ that modulates the degree of exploration and exploitation. Parameter $\alpha$ will be employed to adaptively regulate the variance of the added noise, which is applied to the action output by the diffusion model. Experimental trials on MuJoCo benchmarks and a multimodal task demonstrate that the DACER algorithm achieves state-of-the-art (SOTA) performance in most MuJoCo control tasks while exhibiting a stronger representational capacity of the diffusion policy.
Authors: Abhishek Kumar, Robert Morabito, Sanzhar Umbet, Jad Kabbara, Ali Emami
Abstract: As the use of Large Language Models (LLMs) becomes more widespread, understanding their self-evaluation of confidence in generated responses becomes increasingly important as it is integral to the reliability of the output of these models. We introduce the concept of Confidence-Probability Alignment, that connects an LLM's internal confidence, quantified by token probabilities, to the confidence conveyed in the model's response when explicitly asked about its certainty. Using various datasets and prompting techniques that encourage model introspection, we probe the alignment between models' internal and expressed confidence. These techniques encompass using structured evaluation scales to rate confidence, including answer options when prompting, and eliciting the model's confidence level for outputs it does not recognize as its own. Notably, among the models analyzed, OpenAI's GPT-4 showed the strongest confidence-probability alignment, with an average Spearman's $\hat{\rho}$ of 0.42, across a wide range of tasks. Our work contributes to the ongoing efforts to facilitate risk assessment in the application of LLMs and to further our understanding of model trustworthiness.
Authors: Jiawei Shao, Jingwen Tong, Qiong Wu, Wei Guo, Zijian Li, Zehong Lin, Jun Zhang
Abstract: The rapid evolution of wireless technologies and the growing complexity of network infrastructures necessitate a paradigm shift in how communication networks are designed, configured, and managed. Recent advancements in Large Language Models (LLMs) have sparked interest in their potential to revolutionize wireless communication systems. However, existing studies on LLMs for wireless systems are limited to a direct application for telecom language understanding. To empower LLMs with knowledge and expertise in the wireless domain, this paper proposes WirelessLLM, a comprehensive framework for adapting and enhancing LLMs to address the unique challenges and requirements of wireless communication networks. We first identify three foundational principles that underpin WirelessLLM: knowledge alignment, knowledge fusion, and knowledge evolution. Then, we investigate the enabling technologies to build WirelessLLM, including prompt engineering, retrieval augmented generation, tool usage, multi-modal pre-training, and domain-specific fine-tuning. Moreover, we present three case studies to demonstrate the practical applicability and benefits of WirelessLLM for solving typical problems in wireless networks. Finally, we conclude this paper by highlighting key challenges and outlining potential avenues for future research.
Authors: Tianhao Zhang, Zhexiao Lin, Zhecheng Sheng, Chen Jiang, Dongyeop Kang
Abstract: Modeling and analyzing long sequences of text is an essential task for Natural Language Processing. Success in capturing long text dynamics using neural language models will facilitate many downstream tasks such as coherence evaluation, text generation, machine translation and so on. This paper presents a novel approach to model sequences through a stochastic process. We introduce a likelihood-based training objective for the text encoder and design a more thorough measurement (score) for long text evaluation compared to the previous approach. The proposed training objective effectively preserves the sequence coherence, while the new score comprehensively captures both temporal and spatial dependencies. Theoretical properties of our new score show its advantages in sequence evaluation. Experimental results show superior performance in various sequence evaluation tasks, including global and local discrimination within and between documents of different lengths. We also demonstrate the encoder achieves competitive results on discriminating human and AI written text.
Authors: Guanlin Li, Kangjie Chen, Shudong Zhang, Jie Zhang, Tianwei Zhang
Abstract: Large-scale pre-trained generative models are taking the world by storm, due to their abilities in generating creative content. Meanwhile, safeguards for these generative models are developed, to protect users' rights and safety, most of which are designed for large language models. Existing methods primarily focus on jailbreak and adversarial attacks, which mainly evaluate the model's safety under malicious prompts. Recent work found that manually crafted safe prompts can unintentionally trigger unsafe generations. To further systematically evaluate the safety risks of text-to-image models, we propose a novel Automatic Red-Teaming framework, ART. Our method leverages both vision language model and large language model to establish a connection between unsafe generations and their prompts, thereby more efficiently identifying the model's vulnerabilities. With our comprehensive experiments, we reveal the toxicity of the popular open-source text-to-image models. The experiments also validate the effectiveness, adaptability, and great diversity of ART. Additionally, we introduce three large-scale red-teaming datasets for studying the safety risks associated with text-to-image models. Datasets and models can be found in https://github.com/GuanlinLee/ART.
Authors: Shiyin Lu, Yang Li, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Han-Jia Ye
Abstract: Current Multimodal Large Language Models (MLLMs) typically integrate a pre-trained LLM with another pre-trained vision transformer through a connector, such as an MLP, endowing the LLM with visual capabilities. However, the misalignment between two embedding strategies in MLLMs -- the structural textual embeddings based on an embedding look-up table and the continuous embeddings generated directly by the vision encoder -- makes challenges for a more seamless fusion of visual and textual information. We propose Ovis, a novel MLLM architecture designed to structurally align visual and textual embeddings. Ovis integrates an additional learnable visual embedding table into the visual encoder's process. To capture rich visual semantics, each image patch indexes the visual embedding table multiple times, resulting in a final visual embedding that is a probabilistic combination of the indexed embeddings. This structural approach mirrors the method used for generating textual embeddings. Empirical evaluations on various multimodal benchmarks show that Ovis outperforms open-source MLLMs of similar parameter scales and even surpasses the proprietary model Qwen-VL-Plus overall. These results highlight the potential of Ovis' structured visual representation for advancing MLLM architectural design and promoting more effective multimodal learning. Code, datasets, and models are available at https://github.com/AIDC-AI/Ovis.
Authors: Shinnosuke Tanaka, James Barry, Vishnudev Kuruvanthodi, Movina Moses, Maxwell J. Giammona, Nathan Herr, Mohab Elkaref, Geeth De Mel
Abstract: This paper describes the KnowledgeHub tool, a scientific literature Information Extraction (IE) and Question Answering (QA) pipeline. This is achieved by supporting the ingestion of PDF documents that are converted to text and structured representations. An ontology can then be constructed where a user defines the types of entities and relationships they want to capture. A browser-based annotation tool enables annotating the contents of the PDF documents according to the ontology. Named Entity Recognition (NER) and Relation Classification (RC) models can be trained on the resulting annotations and can be used to annotate the unannotated portion of the documents. A knowledge graph is constructed from these entity and relation triples which can be queried to obtain insights from the data. Furthermore, we integrate a suite of Large Language Models (LLMs) that can be used for QA and summarisation that is grounded in the included documents via a retrieval component. KnowledgeHub is a unique tool that supports annotation, IE and QA, which gives the user full insight into the knowledge discovery pipeline.
Authors: Andrew C. Li, Zizhao Chen, Toryn Q. Klassen, Pashootan Vaezipoor, Rodrigo Toro Icarte, Sheila A. McIlraith
Abstract: Reward Machines provide an automata-inspired structure for specifying instructions, safety constraints, and other temporally extended reward-worthy behaviour. By exposing complex reward function structure, they enable counterfactual learning updates that have resulted in impressive sample efficiency gains. While Reward Machines have been employed in both tabular and deep RL settings, they have typically relied on a ground-truth interpretation of the domain-specific vocabulary that form the building blocks of the reward function. Such ground-truth interpretations can be elusive in many real-world settings, due in part to partial observability or noisy sensing. In this paper, we explore the use of Reward Machines for Deep RL in noisy and uncertain environments. We characterize this problem as a POMDP and propose a suite of RL algorithms that leverage task structure under uncertain interpretation of domain-specific vocabulary. Theoretical analysis exposes pitfalls in naive approaches to this problem, while experimental results show that our algorithms successfully leverage task structure to improve performance under noisy interpretations of the vocabulary. Our results provide a general framework for exploiting Reward Machines in partially observable environments.
Authors: Sarthak Harne, Monjoy Narayan Choudhury, Madhav Rao, TK Srikanth, Seema Mehrotra, Apoorva Vashisht, Aarushi Basu, Manjit Sodhi
Abstract: The limited availability of psychologists necessitates efficient identification of individuals requiring urgent mental healthcare. This study explores the use of Natural Language Processing (NLP) pipelines to analyze text data from online mental health forums used for consultations. By analyzing forum posts, these pipelines can flag users who may require immediate professional attention. A crucial challenge in this domain is data privacy and scarcity. To address this, we propose utilizing readily available curricular texts used in institutes specializing in mental health for pre-training the NLP pipelines. This helps us mimic the training process of a psychologist. Our work presents CASE-BERT that flags potential mental health disorders based on forum text. CASE-BERT demonstrates superior performance compared to existing methods, achieving an f1 score of 0.91 for Depression and 0.88 for Anxiety, two of the most commonly reported mental health disorders. Our code is publicly available.
Authors: Dinghuai Zhang, Yizhe Zhang, Jiatao Gu, Ruixiang Zhang, Josh Susskind, Navdeep Jaitly, Shuangfei Zhai
Abstract: Diffusion models have become the de-facto approach for generating visual data, which are trained to match the distribution of the training dataset. In addition, we also want to control generation to fulfill desired properties such as alignment to a text description, which can be specified with a black-box reward function. Prior works fine-tune pretrained diffusion models to achieve this goal through reinforcement learning-based algorithms. Nonetheless, they suffer from issues including slow credit assignment as well as low quality in their generated samples. In this work, we explore techniques that do not directly maximize the reward but rather generate high-reward images with relatively high probability -- a natural scenario for the framework of generative flow networks (GFlowNets). To this end, we propose the Diffusion Alignment with GFlowNet (DAG) algorithm to post-train diffusion models with black-box property functions. Extensive experiments on Stable Diffusion and various reward specifications corroborate that our method could effectively align large-scale text-to-image diffusion models with given reward information.
Authors: Amir Masoud Rahmani, Amir Haider, Mohammad Adeli, Olfa Mzoughi, Entesar Gemeay, Mokhtar Mohammadi, Hamid Alinejad-Rokny, Parisa Khoshvaght, Mehdi Hosseinzadeh
Abstract: This paper explores the efficacy of Mel Frequency Cepstral Coefficients (MFCCs) in detecting abnormal heart sounds using two classification strategies: a single classifier and an ensemble classifier approach. Heart sounds were first pre-processed to remove noise and then segmented into S1, systole, S2, and diastole intervals, with thirteen MFCCs estimated from each segment, yielding 52 MFCCs per beat. Finally, MFCCs were used for heart sound classification. For that purpose, in the single classifier strategy, the MFCCs from nine consecutive beats were averaged to classify heart sounds by a single classifier (either a support vector machine (SVM), the k nearest neighbors (kNN), or a decision tree (DT)). Conversely, the ensemble classifier strategy employed nine classifiers (either nine SVMs, nine kNN classifiers, or nine DTs) to individually assess beats as normal or abnormal, with the overall classification based on the majority vote. Both methods were tested on a publicly available phonocardiogram database. The heart sound classification accuracy was 91.95% for the SVM, 91.9% for the kNN, and 87.33% for the DT in the single classifier strategy. Also, the accuracy was 93.59% for the SVM, 91.84% for the kNN, and 92.22% for the DT in the ensemble classifier strategy. Overall, the results demonstrated that the ensemble classifier strategy improved the accuracies of the DT and the SVM by 4.89% and 1.64%, establishing MFCCs as more effective than other features, including time, time-frequency, and statistical features, evaluated in similar studies.
Authors: Zefan Cai., Yichi Zhang, Bofei Gao, Yuliang Liu, Tianyu Liu, Keming Lu, Wayne Xiong, Yue Dong, Baobao Chang, Junjie Hu, Wen Xiao
Abstract: In this study, we investigate whether attention-based information flow inside large language models (LLMs) is aggregated through noticeable patterns for long context processing. Our observations reveal that LLMs aggregate information through Pyramidal Information Funneling where attention is scattering widely in lower layers, progressively consolidating within specific contexts, and ultimately focusin on critical tokens (a.k.a massive activation or attention sink) in higher layers. Motivated by these insights, we developed PyramidKV, a novel and effective KV cache compression method. This approach dynamically adjusts the KV cache size across different layers, allocating more cache in lower layers and less in higher ones, diverging from traditional methods that maintain a uniform KV cache size. Our experimental evaluations, utilizing the LongBench benchmark, show that PyramidKV matches the performance of models with a full KV cache while retaining only 12% of the KV cache, thus significantly reducing memory usage. In scenarios emphasizing memory efficiency, where only 0.7% of the KV cache is maintained, PyramidKV surpasses other KV cache compression techniques achieving up to a 20.5 absolute accuracy improvement on TREC.
Authors: Ruizhe Huang, Xiaohui Zhang, Zhaoheng Ni, Li Sun, Moto Hira, Jeff Hwang, Vimal Manohar, Vineel Pratap, Matthew Wiesner, Shinji Watanabe, Daniel Povey, Sanjeev Khudanpur
Abstract: Connectionist temporal classification (CTC) models are known to have peaky output distributions. Such behavior is not a problem for automatic speech recognition (ASR), but it can cause inaccurate forced alignments (FA), especially at finer granularity, e.g., phoneme level. This paper aims at alleviating the peaky behavior for CTC and improve its suitability for forced alignment generation, by leveraging label priors, so that the scores of alignment paths containing fewer blanks are boosted and maximized during training. As a result, our CTC model produces less peaky posteriors and is able to more accurately predict the offset of the tokens besides their onset. It outperforms the standard CTC model and a heuristics-based approach for obtaining CTC's token offset timestamps by 12-40% in phoneme and word boundary errors (PBE and WBE) measured on the Buckeye and TIMIT data. Compared with the most widely used FA toolkit Montreal Forced Aligner (MFA), our method performs similarly on PBE/WBE on Buckeye, yet falls behind MFA on TIMIT. Nevertheless, our method has a much simpler training pipeline and better runtime efficiency. Our training recipe and pretrained model are released in TorchAudio.
Authors: Zengkui Sun, Yijin Liu, Jiaan Wang, Fandong Meng, Jinan Xu, Yufeng Chen, Jie Zhou
Abstract: Recently, Knowledge Editing has received increasing attention, since it could update the specific knowledge from outdated ones in pretrained models without re-training. However, as pointed out by recent studies, existing related methods tend to merely memorize the superficial word composition of the edited knowledge, rather than truly learning and absorbing it. Consequently, on the reasoning questions, we discover that existing methods struggle to utilize the edited knowledge to reason the new answer, and tend to retain outdated responses, which are generated by the original models utilizing original knowledge. Nevertheless, the outdated responses are unexpected for the correct answers to reasoning questions, which we named as the outdated issue. To alleviate this issue, in this paper, we propose a simple yet effective decoding strategy, i.e., outDated ISsue aware deCOding (DISCO), to enhance the performance of edited models on reasoning questions. Specifically, we capture the difference in the probability distribution between the original and edited models. Further, we amplify the difference of the token prediction in the edited model to alleviate the outdated issue, and thus enhance the model performance w.r.t the edited knowledge. Experimental results suggest that applying DISCO could enhance edited models to reason, e.g., on reasoning questions, DISCO outperforms the prior SOTA method by 12.99 F1 scores, and reduces the ratio of the outdated issue to 5.78% on the zsRE dataset.
Authors: Hsuan Su, Hua Farn, Fan-Yun Sun, Shang-Tse Chen, Hung-yi Lee
Abstract: Synthetic data is widely used in speech recognition due to the availability of text-to-speech models, which facilitate adapting models to previously unseen text domains. However, existing methods suffer in performance when they fine-tune an automatic speech recognition (ASR) model on synthetic data as they suffer from the distributional shift commonly referred to as the synthetic-to-real gap. In this paper, we find that task vector arithmetic is effective at mitigating this gap. Our proposed method, SYN2REAL task vector, shows an average improvement of 10.03\% improvement in word error rate over baselines on the SLURP dataset. Additionally, we show that an average of SYN2REAL task vectors, when we have real speeches from multiple different domains, can further adapt the original ASR model to perform better on the target text domain.
Authors: Matthew Nyaaba, Alyson Wright, Gyu Lim Choi
Abstract: This paper critically discusses how generative artificial intelligence (GenAI) might impose Western ideologies on non-Western societies, perpetuating digital neocolonialism in education through its inherent biases. It further suggests strategies for local and global stakeholders to mitigate these effects. Our discussions demonstrated that GenAI can foster cultural imperialism by generating content that primarily incorporates cultural references and examples relevant to Western students, thereby alienating students from non-Western backgrounds. Also, the predominant use of Western languages by GenAI can marginalize non-dominant languages, making educational content less accessible to speakers of indigenous languages and potentially impacting their ability to learn in their first language. Additionally, GenAI often generates content and curricula that reflect the perspectives of technologically dominant countries, overshadowing marginalized indigenous knowledge and practices. Moreover, the cost of access to GenAI intensifies educational inequality and the control of GenAI data could lead to commercial exploitation without benefiting local students and their communities. We propose human-centric reforms to prioritize cultural diversity and equity in GenAI development; a liberatory design to empower educators and students to identify and dismantle the oppressive structures within GenAI applications; foresight by design to create an adjustable GenAI system to meet future educational needs; and finally, effective prompting skills to reduce the retrieval of neocolonial outputs.
Authors: Arun D. Kulkarni
Abstract: Recently, convolution neural networks (CNNs) have attracted a great deal of attention due to their remarkable performance in various domains, particularly in image and text classification tasks. However, their application to tabular data classification remains underexplored. There are many fields such as bioinformatics, finance, medicine where nonimage data are prevalent. Adaption of CNNs to classify nonimage data remains highly challenging. This paper investigates the efficacy of CNNs for tabular data classification, aiming to bridge the gap between traditional machine learning approaches and deep learning techniques. We propose a novel framework fuzzy convolution neural network (FCNN) tailored specifically for tabular data to capture local patterns within feature vectors. In our approach, we map feature values to fuzzy memberships. The fuzzy membership vectors are converted into images that are used to train the CNN model. The trained CNN model is used to classify unknown feature vectors. To validate our approach, we generated six complex noisy data sets. We used randomly selected seventy percent samples from each data set for training and thirty percent for testing. The data sets were also classified using the state-of-the-art machine learning algorithms such as the decision tree (DT), support vector machine (SVM), fuzzy neural network (FNN), Bayes classifier, and Random Forest (RF). Experimental results demonstrate that our proposed model can effectively learn meaningful representations from tabular data, achieving competitive or superior performance compared to existing methods. Overall, our finding suggests that the proposed FCNN model holds promise as a viable alternative for tabular data classification tasks, offering a fresh prospective and potentially unlocking new opportunities for leveraging deep learning in structured data analysis.
Authors: Feilong Jiang, Xiaonan Hou, Min Xia
Abstract: As a promising framework for resolving partial differential equations (PDEs), physics-informed neural networks (PINNs) have received widespread attention from industrial and scientific fields. However, lack of expressive ability and initialization pathology issues are found to prevent the application of PINNs in complex PDEs. In this work, we propose Element-wise Multiplication Based Physics-informed Neural Networks (EM-PINNs) to resolve these issues. The element-wise multiplication operation is adopted to transform features into high-dimensional, non-linear spaces, which effectively enhance the expressive capability of PINNs. Benefiting from element-wise multiplication operation, EM-PINNs can eliminate the initialization pathologies of PINNs. The proposed structure is verified on various benchmarks. The results show that EM-PINNs have strong expressive ability.
Authors: Wei Pang, Chuan Zhou, Xiao-Hua Zhou, Xiaojie Wang
Abstract: Instruction Fine-Tuning enhances pre-trained language models from basic next-word prediction to complex instruction-following. However, existing One-off Instruction Fine-Tuning (One-off IFT) method, applied on a diverse instruction, may not effectively boost models' adherence to instructions due to the simultaneous handling of varying instruction complexities. To improve this, Phased Instruction Fine-Tuning (Phased IFT) is proposed, based on the idea that learning to follow instructions is a gradual process. It assesses instruction difficulty using GPT-4, divides the instruction data into subsets of increasing difficulty, and uptrains the model sequentially on these subsets. Experiments with Llama-2 7B/13B/70B, Llama3 8/70B and Mistral-7B models using Alpaca data show that Phased IFT significantly outperforms One-off IFT, supporting the progressive alignment hypothesis and providing a simple and efficient way to enhance large language models. Codes and datasets from our experiments are freely available at https://github.com/xubuvd/PhasedSFT.
Authors: Jamie Lohoff, Emre Neftci
Abstract: Computing Jacobians with automatic differentiation is ubiquitous in many scientific domains such as machine learning, computational fluid dynamics, robotics and finance. Even small savings in the number of computations or memory usage in Jacobian computations can already incur massive savings in energy consumption and runtime. While there exist many methods that allow for such savings, they generally trade computational efficiency for approximations of the exact Jacobian. In this paper, we present a novel method to optimize the number of necessary multiplications for Jacobian computation by leveraging deep reinforcement learning (RL) and a concept called cross-country elimination while still computing the exact Jacobian. Cross-country elimination is a framework for automatic differentiation that phrases Jacobian accumulation as ordered elimination of all vertices on the computational graph where every elimination incurs a certain computational cost. We formulate the search for the optimal elimination order that minimizes the number of necessary multiplications as a single player game which is played by an RL agent. We demonstrate that this method achieves up to 33% improvements over state-of-the-art methods on several relevant tasks taken from diverse domains. Furthermore, we show that these theoretical gains translate into actual runtime improvements by providing a cross-country elimination interpreter in JAX that can efficiently execute the obtained elimination orders.
Authors: David R Wessels, David M Knigge, Samuele Papa, Riccardo Valperga, Sharvaree Vadgama, Efstratios Gavves, Erik J Bekkers
Abstract: Recently, Neural Fields have emerged as a powerful modelling paradigm to represent continuous signals. In a conditional neural field, a field is represented by a latent variable that conditions the NeF, whose parametrisation is otherwise shared over an entire dataset. We propose Equivariant Neural Fields based on cross attention transformers, in which NeFs are conditioned on a geometric conditioning variable, a latent point cloud, that enables an equivariant decoding from latent to field. Our equivariant approach induces a steerability property by which both field and latent are grounded in geometry and amenable to transformation laws if the field transforms, the latent represents transforms accordingly and vice versa. Crucially, the equivariance relation ensures that the latent is capable of (1) representing geometric patterns faitfhully, allowing for geometric reasoning in latent space, (2) weightsharing over spatially similar patterns, allowing for efficient learning of datasets of fields. These main properties are validated using classification experiments and a verification of the capability of fitting entire datasets, in comparison to other non-equivariant NeF approaches. We further validate the potential of ENFs by demonstrate unique local field editing properties.
Authors: Kiseung Kim, Jay-Yoon Lee
Abstract: The Retrieval Augmented Generation (RAG) framework utilizes a combination of parametric knowledge and external knowledge to demonstrate state-of-the-art performance on open-domain question answering tasks. However, the RAG framework suffers from performance degradation when the query is accompanied by irrelevant contexts. In this work, we propose the RE-RAG framework, which introduces a relevance estimator (RE) that not only provides relative relevance between contexts as previous rerankers did, but also provides confidence, which can be used to classify whether given context is useful for answering the given question. We propose a weakly supervised method for training the RE simply utilizing question-answer data without any labels for correct contexts. We show that RE trained with a small generator (sLM) can not only improve the sLM fine-tuned together with RE but also improve previously unreferenced large language models (LLMs). Furthermore, we investigate new decoding strategies that utilize the proposed confidence measured by RE such as choosing to let the user know that it is "unanswerable" to answer the question given the retrieved contexts or choosing to rely on LLM's parametric knowledge rather than unrelated contexts.
Authors: Quandong Wang, Yuxuan Yuan, Xiaoyu Yang, Ruike Zhang, Kang Zhao, Wei Liu, Jian Luan, Daniel Povey, Bin Wang
Abstract: While Large Language Models (LLMs) have achieved remarkable success in various fields, the efficiency of training and inference remains a major challenge. To address this issue, we propose SUBLLM, short for Subsampling-Upsampling-Bypass Large Language Model, an innovative architecture that extends the core decoder-only framework by incorporating subsampling, upsampling, and bypass modules. The subsampling modules are responsible for shortening the sequence, while the upsampling modules restore the sequence length, and the bypass modules enhance convergence. In comparison to LLaMA, the proposed SUBLLM exhibits significant enhancements in both training and inference speeds as well as memory usage, while maintaining competitive few-shot performance. During training, SUBLLM increases speeds by 26% and cuts memory by 10GB per GPU. In inference, it boosts speeds by up to 37% and reduces memory by 1GB per GPU. The training and inference speeds can be enhanced by 34% and 52% respectively when the context window is expanded to 8192. We shall release the source code of the proposed architecture in the published version.
Authors: Sander Schulhoff, Michael Ilie, Nishant Balepur, Konstantine Kahadze, Amanda Liu, Chenglei Si, Yinheng Li, Aayush Gupta, HyoJung Han, Sevien Schulhoff, Pranav Sandeep Dulepet, Saurav Vidyadhara, Dayeon Ki, Sweta Agrawal, Chau Pham, Gerson Kroiz, Feileen Li, Hudson Tao, Ashay Srivastava, Hevander Da Costa, Saloni Gupta, Megan L. Rogers, Inna Goncearenco, Giuseppe Sarli, Igor Galynker, Denis Peskoff, Marine Carpuat, Jules White, Shyamal Anadkat, Alexander Hoyle, Philip Resnik
Abstract: Generative Artificial Intelligence (GenAI) systems are being increasingly deployed across all parts of industry and research settings. Developers and end users interact with these systems through the use of prompting or prompt engineering. While prompting is a widespread and highly researched concept, there exists conflicting terminology and a poor ontological understanding of what constitutes a prompt due to the area's nascency. This paper establishes a structured understanding of prompts, by assembling a taxonomy of prompting techniques and analyzing their use. We present a comprehensive vocabulary of 33 vocabulary terms, a taxonomy of 58 text-only prompting techniques, and 40 techniques for other modalities. We further present a meta-analysis of the entire literature on natural language prefix-prompting.
Authors: Ruizhong Qiu, Weiliang Will Zeng, Hanghang Tong, James Ezick, Christopher Lott
Abstract: The emergence of large language models (LLMs) has significantly pushed the frontiers of program synthesis. Advancement of LLM-based program synthesis calls for a thorough evaluation of LLM-generated code. Most evaluation frameworks focus on the (functional) correctness of generated code; efficiency, as an important measure of code quality, has been overlooked in existing evaluations. In this work, we develop ENAMEL (EfficeNcy AutoMatic EvaLuator), a rigorous and high-standard benchmark for evaluating the capability of LLMs in generating efficient code. Firstly, we propose a new efficiency metric called eff@k, which generalizes the pass@k metric from correctness to efficiency and appropriately handles right-censored execution time. Furthermore, we derive an unbiased and variance-reduced estimator of eff@k via Rao--Blackwellization; we also provide a numerically stable implementation for the new estimator. Secondly, to set a high-standard for efficiency evaluation, we employ a human expert to design best algorithms and implementations as our reference solutions of efficiency, many of which are much more efficient than existing canonical solutions in HumanEval and HumanEval+. Moreover, to ensure a rigorous evaluation, we employ a human expert to curate strong test case generators to filter out wrong code and differentiate suboptimal algorithms. An extensive study across 30 popular LLMs using our benchmark ENAMEL shows that LLMs still fall short of generating expert-level efficient code. Using two subsets of our problem set, we demonstrate that such deficiency is because current LLMs struggle in designing advanced algorithms and are barely aware of implementation optimization. Our benchmark is publicly available at https://github.com/q-rz/enamel .
Authors: Yubin Xiao, Di Wang, Xuan Wu, Yuesong Wu, Boyang Li, Wei Du, Liupu Wang, You Zhou
Abstract: Neural models produce promising results when solving Vehicle Routing Problems (VRPs), but often fall short in generalization. Recent attempts to enhance model generalization often incur unnecessarily large training cost or cannot be directly applied to other models solving different VRP variants. To address these issues, we take a novel perspective on model architecture in this study. Specifically, we propose a plug-and-play Entropy-based Scaling Factor (ESF) and a Distribution-Specific (DS) decoder to enhance the size and distribution generalization, respectively. ESF adjusts the attention weight pattern of the model towards familiar ones discovered during training when solving VRPs of varying sizes. The DS decoder explicitly models VRPs of multiple training distribution patterns through multiple auxiliary light decoders, expanding the model representation space to encompass a broader range of distributional scenarios. We conduct extensive experiments on both synthetic and widely recognized real-world benchmarking datasets and compare the performance with seven baseline models. The results demonstrate the effectiveness of using ESF and DS decoder to obtain a more generalizable model and showcase their applicability to solve different VRP variants, i.e., travelling salesman problem and capacitated VRP. Notably, our proposed generic components require minimal computational resources, and can be effortlessly integrated into conventional generalization strategies to further elevate model generalization.
Authors: Sergey Linok, Tatiana Zemskova, Svetlana Ladanova, Roman Titkov, Dmitry Yudin
Abstract: Locating objects referred to in natural language poses a significant challenge for autonomous agents. Existing CLIP-based open-vocabulary methods successfully perform 3D object retrieval with simple (bare) queries but cannot cope with ambiguous descriptions that demand an understanding of object relations. To tackle this problem, we propose a modular approach called BBQ (Beyond Bare Queries), which constructs 3D scene spatial graph representation with metric edges and utilizes a large language model as a human-to-agent interface through our deductive scene reasoning algorithm. BBQ employs robust DINO-powered associations to form 3D objects, an advanced raycasting algorithm to project them to 2D, and a vision-language model to describe them as graph nodes. On Replica and ScanNet datasets, we show that the designed method accurately constructs 3D object-centric maps. We have demonstrated that their quality takes a leading place for open-vocabulary 3D semantic segmentation against other zero-shot methods. Also, we show that leveraging spatial relations is especially effective for scenes containing multiple entities of the same semantic class. On Sr3D and Nr3D benchmarks, our deductive approach demonstrates a significant improvement, enabling retrieving objects by complex queries compared to other state-of-the-art methods. Considering our design solutions, we achieved a processing speed approximately x3 times faster than the closest analog. This promising performance enables our approach for usage in applied intelligent robotics projects. We make the code publicly available at linukc.github.io/bbq/.
Authors: Nirmalya Thakur, Vanessa Su, Mingchen Shao, Kesha A. Patel, Hongseok Jeong, Victoria Knieling, Andrew Bian
Abstract: The work of this paper presents a dataset that contains the data of 4011 videos about the ongoing outbreak of measles published on 264 websites on the internet between January 1, 2024, and May 31, 2024. The dataset is available at https://dx.doi.org/10.21227/40s8-xf63. These websites primarily include YouTube and TikTok, which account for 48.6% and 15.2% of the videos, respectively. The remainder of the websites include Instagram and Facebook as well as the websites of various global and local news organizations. For each of these videos, the URL of the video, title of the post, description of the post, and the date of publication of the video are presented as separate attributes in the dataset. After developing this dataset, sentiment analysis (using VADER), subjectivity analysis (using TextBlob), and fine-grain sentiment analysis (using DistilRoBERTa-base) of the video titles and video descriptions were performed. This included classifying each video title and video description into (i) one of the sentiment classes i.e. positive, negative, or neutral, (ii) one of the subjectivity classes i.e. highly opinionated, neutral opinionated, or least opinionated, and (iii) one of the fine-grain sentiment classes i.e. fear, surprise, joy, sadness, anger, disgust, or neutral. These results are presented as separate attributes in the dataset for the training and testing of machine learning algorithms for performing sentiment analysis or subjectivity analysis in this field as well as for other applications. Finally, this paper also presents a list of open research questions that may be investigated using this dataset.
Authors: Amogh Mannekote, Jinseok Nam, Ziming Li, Jian Gao, Kristy Elizabeth Boyer, Bonnie J. Dorr
Abstract: Indirect User Requests (IURs), such as "It's cold in here" instead of "Could you please increase the temperature?" are common in human-human task-oriented dialogue and require world knowledge and pragmatic reasoning from the listener. While large language models (LLMs) can handle these requests effectively, smaller models deployed on virtual assistants often struggle due to resource constraints. Moreover, existing task-oriented dialogue benchmarks lack sufficient examples of complex discourse phenomena such as indirectness. To address this, we propose a set of linguistic criteria along with an LLM-based pipeline for generating realistic IURs to test natural language understanding (NLU) and dialogue state tracking (DST) models before deployment in a new domain. We also release IndirectRequests, a dataset of IURs based on the Schema Guided Dialog (SGD) corpus, as a comparative testbed for evaluating the performance of smaller models in handling indirect requests.
Authors: Yida Chen, Aoyu Wu, Trevor DePodesta, Catherine Yeh, Kenneth Li, Nicholas Castillo Marin, Oam Patel, Jan Riecke, Shivam Raval, Olivia Seow, Martin Wattenberg, Fernanda Vi\'egas
Abstract: Conversational LLMs function as black box systems, leaving users guessing about why they see the output they do. This lack of transparency is potentially problematic, especially given concerns around bias and truthfulness. To address this issue, we present an end-to-end prototype-connecting interpretability techniques with user experience design-that seeks to make chatbots more transparent. We begin by showing evidence that a prominent open-source LLM has a "user model": examining the internal state of the system, we can extract data related to a user's age, gender, educational level, and socioeconomic status. Next, we describe the design of a dashboard that accompanies the chatbot interface, displaying this user model in real time. The dashboard can also be used to control the user model and the system's behavior. Finally, we discuss a study in which users conversed with the instrumented system. Our results suggest that users appreciate seeing internal states, which helped them expose biased behavior and increased their sense of control. Participants also made valuable suggestions that point to future directions for both design and machine learning research. The project page and video demo of our TalkTuner system are available at https://bit.ly/talktuner-project-page
Authors: Mat\'ias Carrasco, Franz Mayr, Sergio Yovine, Johny Kidd, Mart\'in Iturbide, Juan Pedro da Silva, Alejo Garat
Abstract: We define a congruence that copes with null next-symbol probabilities that arise when the output of a language model is constrained by some means during text generation. We develop an algorithm for efficiently learning the quotient with respect to this congruence and evaluate it on case studies for analyzing statistical properties of LLM.
Authors: Tianqi Chen, Jun Hou, Yinchi Zhou, Huidong Xie, Xiongchao Chen, Qiong Liu, Xueqi Guo, Menghua Xia, James S. Duncan, Chi Liu, Bo Zhou
Abstract: Positron Emission Tomography (PET) is an important clinical imaging tool but inevitably introduces radiation hazards to patients and healthcare providers. Reducing the tracer injection dose and eliminating the CT acquisition for attenuation correction can reduce the overall radiation dose, but often results in PET with high noise and bias. Thus, it is desirable to develop 3D methods to translate the non-attenuation-corrected low-dose PET (NAC-LDPET) into attenuation-corrected standard-dose PET (AC-SDPET). Recently, diffusion models have emerged as a new state-of-the-art deep learning method for image-to-image translation, better than traditional CNN-based methods. However, due to the high computation cost and memory burden, it is largely limited to 2D applications. To address these challenges, we developed a novel 2.5D Multi-view Averaging Diffusion Model (MADM) for 3D image-to-image translation with application on NAC-LDPET to AC-SDPET translation. Specifically, MADM employs separate diffusion models for axial, coronal, and sagittal views, whose outputs are averaged in each sampling step to ensure the 3D generation quality from multiple views. To accelerate the 3D sampling process, we also proposed a strategy to use the CNN-based 3D generation as a prior for the diffusion model. Our experimental results on human patient studies suggested that MADM can generate high-quality 3D translation images, outperforming previous CNN-based and Diffusion-based baseline methods.
Authors: Da Mu, Zhicheng Zhang, Haobo Yue
Abstract: Sound Event Localization and Detection (SELD) involves detecting and localizing sound events using multichannel sound recordings. Previously proposed Event-Independent Network V2 (EINV2) has achieved outstanding performance on SELD. However, it still faces challenges in effectively extracting features across spectral, spatial, and temporal domains. This paper proposes a three-stage network structure named Multi-scale Feature Fusion (MFF) module to fully extract multi-scale features across spectral, spatial, and temporal domains. The MFF module utilizes parallel subnetworks architecture to generate multi-scale spectral and spatial features. The TF-Convolution Module is employed to provide multi-scale temporal features. We incorporated MFF into EINV2 and term the proposed method as MFF-EINV2. Experimental results in 2022 and 2023 DCASE challenge task3 datasets show the effectiveness of our MFF-EINV2, which achieves state-of-the-art (SOTA) performance compared to published methods.
Authors: Kairui Fu, Shengyu Zhang, Zheqi Lv, Jingyuan Chen, Jiwei Li
Abstract: Due to the continuously improving capabilities of mobile edges, recommender systems start to deploy models on edges to alleviate network congestion caused by frequent mobile requests. Several studies have leveraged the proximity of edge-side to real-time data, fine-tuning them to create edge-specific models. Despite their significant progress, these methods require substantial on-edge computational resources and frequent network transfers to keep the model up to date. The former may disrupt other processes on the edge to acquire computational resources, while the latter consumes network bandwidth, leading to a decrease in user satisfaction. In response to these challenges, we propose a customizeD slImming framework for incompatiblE neTworks(DIET). DIET deploys the same generic backbone (potentially incompatible for a specific edge) to all devices. To minimize frequent bandwidth usage and storage consumption in personalization, DIET tailors specific subnets for each edge based on its past interactions, learning to generate slimming subnets(diets) within incompatible networks for efficient transfer. It also takes the inter-layer relationships into account, empirically reducing inference time while obtaining more suitable diets. We further explore the repeated modules within networks and propose a more storage-efficient framework, DIETING, which utilizes a single layer of parameters to represent the entire network, achieving comparably excellent performance. The experiments across four state-of-the-art datasets and two widely used models demonstrate the superior accuracy in recommendation and efficiency in transmission and storage of our framework.
Authors: Pengyun Wang, Junyu Luo, Yanxin Shen, Siyu Heng, Xiao Luo
Abstract: Graph pooling has gained attention for its ability to obtain effective node and graph representations for various downstream tasks. Despite the recent surge in graph pooling approaches, there is a lack of standardized experimental settings and fair benchmarks to evaluate their performance. To address this issue, we have constructed a comprehensive benchmark that includes 15 graph pooling methods and 21 different graph datasets. This benchmark systematically assesses the performance of graph pooling methods in three dimensions, i.e., effectiveness, robustness, and generalizability. We first evaluate the performance of these graph pooling approaches across different tasks including graph classification, graph regression and node classification. Then, we investigate their performance under potential noise attacks and out-of-distribution shifts in real-world scenarios. We also involve detailed efficiency analysis and parameter analysis. Extensive experiments validate the strong capability and applicability of graph pooling approaches in various scenarios, which can provide valuable insights and guidance for deep geometric learning research. The source code of our benchmark is available at https://github.com/goose315/Graph_Pooling_Benchmark.
Authors: Soumadeep Saha, Sutanoya Chakraborty, Saptarshi Saha, Utpal Garain
Abstract: Crosswords are a form of word puzzle that require a solver to demonstrate a high degree of proficiency in natural language understanding, wordplay, reasoning, and world knowledge, along with adherence to character and length constraints. In this paper we tackle the challenge of solving crosswords with Large Language Models (LLMs). We demonstrate that the current generation of state-of-the art (SoTA) language models show significant competence at deciphering cryptic crossword clues, and outperform previously reported SoTA results by a factor of 2-3 in relevant benchmarks. We also develop a search algorithm that builds off this performance to tackle the problem of solving full crossword grids with LLMs for the very first time, achieving an accuracy of 93\% on New York Times crossword puzzles. Contrary to previous work in this area which concluded that LLMs lag human expert performance significantly, our research suggests this gap is a lot narrower.
Authors: Wenlong Yu, Dongyue Chen, Qilong Wang, Qinghua Hu
Abstract: Fine-grained domain generalization (FGDG) is a more challenging task than traditional DG tasks due to its small inter-class variations and relatively large intra-class disparities. When domain distribution changes, the vulnerability of subtle features leads to a severe deterioration in model performance. Nevertheless, humans inherently demonstrate the capacity for generalizing to out-of-distribution data, leveraging structured multi-granularity knowledge that emerges from discerning the commonality and specificity within categories. Likewise, we propose a Feature Structuralized Domain Generalization (FSDG) model, wherein features experience structuralization into common, specific, and confounding segments, harmoniously aligned with their relevant semantic concepts, to elevate performance in FGDG. Specifically, feature structuralization (FS) is accomplished through joint optimization of five constraints: a decorrelation function applied to disentangled segments, three constraints ensuring common feature consistency and specific feature distinctiveness, and a prediction calibration term. By imposing these stipulations, FSDG is prompted to disentangle and align features based on multi-granularity knowledge, facilitating robust subtle distinctions among categories. Extensive experimentation on three benchmarks consistently validates the superiority of FSDG over state-of-the-art counterparts, with an average improvement of 6.2% in FGDG performance. Beyond that, the explainability analysis on explicit concept matching intensity between the shared concepts among categories and the model channels, along with experiments on various mainstream model architectures, substantiates the validity of FS.
Authors: Hua Shen, Tiffany Knearem, Reshmi Ghosh, Kenan Alkiek, Kundan Krishna, Yachuan Liu, Ziqiao Ma, Savvas Petridis, Yi-Hao Peng, Li Qiwei, Sushrita Rakshit, Chenglei Si, Yutong Xie, Jeffrey P. Bigham, Frank Bentley, Joyce Chai, Zachary Lipton, Qiaozhu Mei, Rada Mihalcea, Michael Terry, Diyi Yang, Meredith Ringel Morris, Paul Resnick, David Jurgens
Abstract: Recent advancements in general-purpose AI have highlighted the importance of guiding AI systems towards the intended goals, ethical principles, and values of individuals and groups, a concept broadly recognized as alignment. However, the lack of clarified definitions and scopes of human-AI alignment poses a significant obstacle, hampering collaborative efforts across research domains to achieve this alignment. In particular, ML- and philosophy-oriented alignment research often views AI alignment as a static, unidirectional process (i.e., aiming to ensure that AI systems' objectives match humans) rather than an ongoing, mutual alignment problem [429]. This perspective largely neglects the long-term interaction and dynamic changes of alignment. To understand these gaps, we introduce a systematic review of over 400 papers published between 2019 and January 2024, spanning multiple domains such as Human-Computer Interaction (HCI), Natural Language Processing (NLP), Machine Learning (ML), and others. We characterize, define and scope human-AI alignment. From this, we present a conceptual framework of "Bidirectional Human-AI Alignment" to organize the literature from a human-centered perspective. This framework encompasses both 1) conventional studies of aligning AI to humans that ensures AI produces the intended outcomes determined by humans, and 2) a proposed concept of aligning humans to AI, which aims to help individuals and society adjust to AI advancements both cognitively and behaviorally. Additionally, we articulate the key findings derived from literature analysis, including discussions about human values, interaction techniques, and evaluations. To pave the way for future studies, we envision three key challenges for future directions and propose examples of potential future solutions.