Authors: Andrew M. Demetriou, Jaehun Kim, Sandy Manolios, Cynthia C. S. Liem
Abstract: Most music widely consumed in Western Countries contains song lyrics, with U.S. samples reporting almost all of their song libraries contain lyrics. In parallel, social science theory suggests that personal values - the abstract goals that guide our decisions and behaviors - play an important role in communication: we share what is important to us to coordinate efforts, solve problems and meet challenges. Thus, the values communicated in song lyrics may be similar or different to those of the listener, and by extension affect the listener's reaction to the song. This suggests that working towards automated estimation of values in lyrics may assist in downstream MIR tasks, in particular, personalization. However, as highly subjective text, song lyrics present a challenge in terms of sampling songs to be annotated, annotation methods, and in choosing a method for aggregation. In this project, we take a perspectivist approach, guided by social science theory, to gathering annotations, estimating their quality, and aggregating them. We then compare aggregated ratings to estimates based on pre-trained sentence/word embedding models by employing a validated value dictionary. We discuss conceptually 'fuzzy' solutions to sampling and annotation challenges, promising initial results in annotation quality and in automated estimations, and future directions.
Authors: Christopher J. Lee, Giorgio Tran, Roderick Tabalba, Jason Leigh, Ryan Longman
Abstract: This paper explores the intersection of data visualization and Large Language Models (LLMs). Driven by the need to make a broader range of data visualization types accessible for novice users, we present a guided LLM-based pipeline designed to transform data, guided by high-level user questions (referred to as macro-queries), into a diverse set of useful visualizations. This approach leverages various prompting techniques, fine-tuning inspired by Abela's Chart Taxonomy, and integrated SQL tool usage.
Authors: Mengya Hu, Rui Xu, Deren Lei, Yaxi Li, Mingyu Wang, Emily Ching, Eslam Kamal, Alex Deng
Abstract: Large language models (LLMs) are highly capable but face latency challenges in real-time applications, such as conducting online hallucination detection. To overcome this issue, we propose a novel framework that leverages a small language model (SLM) classifier for initial detection, followed by a LLM as constrained reasoner to generate detailed explanations for detected hallucinated content. This study optimizes the real-time interpretable hallucination detection by introducing effective prompting techniques that align LLM-generated explanations with SLM decisions. Empirical experiment results demonstrate its effectiveness, thereby enhancing the overall user experience.
Authors: Chester Palen-Michel, Ruixiang Wang, Yipeng Zhang, David Yu, Canran Xu, Zhe Wu
Abstract: The emergence of Large Language Models (LLMs) has revolutionized natural language processing in various applications especially in e-commerce. One crucial step before the application of such LLMs in these fields is to understand and compare the performance in different use cases in such tasks. This paper explored the efficacy of LLMs in the e-commerce domain, focusing on instruction-tuning an open source LLM model with public e-commerce datasets of varying sizes and comparing the performance with the conventional models prevalent in industrial applications. We conducted a comprehensive comparison between LLMs and traditional pre-trained language models across specific tasks intrinsic to the e-commerce domain, namely classification, generation, summarization, and named entity recognition (NER). Furthermore, we examined the effectiveness of the current niche industrial application of very large LLM, using in-context learning, in e-commerce specific tasks. Our findings indicate that few-shot inference with very large LLMs often does not outperform fine-tuning smaller pre-trained models, underscoring the importance of task-specific model optimization.Additionally, we investigated different training methodologies such as single-task training, mixed-task training, and LoRA merging both within domain/tasks and between different tasks. Through rigorous experimentation and analysis, this paper offers valuable insights into the potential effectiveness of LLMs to advance natural language processing capabilities within the e-commerce industry.
Authors: Vivek Iyer, Bhavitvya Malik, Pavel Stepachev, Pinzhen Chen, Barry Haddow, Alexandra Birch
Abstract: Despite the recent popularity of Large Language Models (LLMs) in Machine Translation (MT), their performance in low-resource translation still lags significantly behind Neural Machine Translation (NMT) models. In this paper, we explore what it would take to adapt LLMs for low-resource settings. In particular, we re-examine the role of two factors: a) the importance and application of parallel data, and b) diversity in Supervised Fine-Tuning (SFT). Recently, parallel data has been shown to be less important for MT using LLMs than in previous MT research. Similarly, diversity during SFT has been shown to promote significant transfer in LLMs across languages and tasks. However, for low-resource LLM-MT, we show that the opposite is true for both of these considerations: a) parallel data is critical during both pretraining and SFT, and b) diversity tends to cause interference, not transfer. Our experiments, conducted with 3 LLMs across 2 low-resourced language groups - indigenous American and North-East Indian - reveal consistent patterns in both cases, underscoring the generalizability of our findings. We believe these insights will be valuable for scaling to massively multilingual LLM-MT models that can effectively serve lower-resource languages.
Authors: JoonHo Lee, JuYoun Son, Juree Seok, Wooseok Jang, Yeong-Dae Kwon
Abstract: Ambiguity in language presents challenges in developing more enhanced language models, particularly in preference learning, where variability among annotators results in inconsistently annotated datasets used for model alignment. To address this issue, we introduce a self-curation method that preprocesses annotated datasets by leveraging proxy models trained directly on these datasets. Our method enhances preference learning by automatically detecting and removing ambiguous annotations within the dataset. The proposed approach is validated through extensive experiments, demonstrating a marked improvement in performance across various instruction-following tasks. Our work provides a straightforward and reliable method to overcome annotation inconsistencies, serving as an initial step towards the development of more advanced preference learning techniques.
Authors: Max Glockner, Yufang Hou, Preslav Nakov, Iryna Gurevych
Abstract: Health-related misinformation claims often falsely cite a credible biomedical publication as evidence, which superficially appears to support the false claim. The publication does not really support the claim, but a reader could believe it thanks to the use of logical fallacies. Here, we aim to detect and to highlight such fallacies, which requires carefully assessing the exact content of the misrepresented publications. To achieve this, we introduce MissciPlus, an extension of the fallacy detection dataset Missci. MissciPlus builds on Missci by grounding the applied fallacies in real-world passages from misrepresented studies. This creates a realistic test-bed for detecting and verbalizing these fallacies under real-world input conditions, and enables novel passage-retrieval tasks. MissciPlus is the first logical fallacy dataset which pairs the real-world misrepresented evidence with incorrect claims, identical to the input to evidence-based fact-checking models. With MissciPlus, we i) benchmark retrieval models in identifying passages that support claims only when fallacies are applied, ii) evaluate how well LLMs articulate fallacious reasoning from misrepresented scientific passages, and iii) assess the effectiveness of fact-checking models in refuting claims that misrepresent biomedical research. Our findings show that current fact-checking models struggle to use relevant passages from misrepresented publications to refute misinformation. Moreover, these passages can mislead LLMs into accepting false claims as true.
Authors: Songwei Li, Jie Feng, Jiawei Chi, Xinyuan Hu, Xiaomeng Zhao, Fengli Xu
Abstract: Human mobility prediction is essential for applications like urban planning and transportation management, yet it remains challenging due to the complex, often implicit, intentions behind human behavior. Existing models predominantly focus on spatiotemporal patterns, paying less attention to the underlying intentions that govern movements. Recent advancements in large language models (LLMs) offer a promising alternative research angle for integrating commonsense reasoning into mobility prediction. However, it is a non-trivial problem because LLMs are not natively built for mobility intention inference, and they also face scalability issues and integration difficulties with spatiotemporal models. To address these challenges, we propose a novel LIMP (LLMs for Intent-ware Mobility Prediction) framework. Specifically, LIMP introduces an "Analyze-Abstract-Infer" (A2I) agentic workflow to unleash LLM's commonsense reasoning power for mobility intention inference. Besides, we design an efficient fine-tuning scheme to transfer reasoning power from commercial LLM to smaller-scale, open-source language model, ensuring LIMP's scalability to millions of mobility records. Moreover, we propose a transformer-based intention-aware mobility prediction model to effectively harness the intention inference ability of LLM. Evaluated on two real-world datasets, LIMP significantly outperforms baseline models, demonstrating improved accuracy in next-location prediction and effective intention inference. The interpretability of intention-aware mobility prediction highlights our LIMP framework's potential for real-world applications. Codes and data can be found in https://github.com/tsinghua-fib-lab/LIMP .
Authors: Yafeng Zhang, Zilan Yu, Yuang Huang, Jing Tang
Abstract: Few-shot Named Entity Recognition (NER), the task of identifying named entities with only a limited amount of labeled data, has gained increasing significance in natural language processing. While existing methodologies have shown some effectiveness, such as enriching label semantics through various prompting modes or employing metric learning techniques, their performance exhibits limited robustness across diverse domains due to the lack of rich knowledge in their pre-trained models. To address this issue, we propose CLLMFS, a Contrastive Learning enhanced Large Language Model (LLM) Framework for Few-Shot Named Entity Recognition, achieving promising results with limited training data. Considering the impact of LLM's internal representations on downstream tasks, CLLMFS integrates Low-Rank Adaptation (LoRA) and contrastive learning mechanisms specifically tailored for few-shot NER. By enhancing the model's internal representations, CLLMFS effectively improves both entity boundary awareness ability and entity recognition accuracy. Our method has achieved state-of-the-art performance improvements on F1-score ranging from 2.58\% to 97.74\% over existing best-performing methods across several recognized benchmarks. Furthermore, through cross-domain NER experiments conducted on multiple datasets, we have further validated the robust generalization capability of our method. Our code will be released in the near future.
Authors: Sujay R, Suki Perumal, Yash Nagraj, Anushka Ghei, Srinivas K S
Abstract: Question difficulty estimation remains a multifaceted challenge in educational and assessment settings. Traditional approaches often focus on surface-level linguistic features or learner comprehension levels, neglecting the intricate interplay of factors contributing to question complexity. This paper presents a novel framework for domain-specific question difficulty estimation, leveraging a suite of NLP techniques and knowledge graph analysis. We introduce four key parameters: Topic Retrieval Cost, Topic Salience, Topic Coherence, and Topic Superficiality, each capturing a distinct facet of question complexity within a given subject domain. These parameters are operationalized through topic modelling, knowledge graph analysis, and information retrieval techniques. A model trained on these features demonstrates the efficacy of our approach in predicting question difficulty. By operationalizing these parameters, our framework offers a novel approach to question complexity estimation, paving the way for more effective question generation, assessment design, and adaptive learning systems across diverse academic disciplines.
Authors: Zhouhao Sun, Li Du, Xiao Ding, Yixuan Ma, Kaitao Qiu, Ting Liu, Bing Qin
Abstract: Although achieving promising performance, recent analyses show that current generative large language models (LLMs) may still capture dataset biases and utilize them for generation, leading to poor generalizability and harmfulness of LLMs. However, due to the diversity of dataset biases and the over-optimization problem, previous prior-knowledge-based debiasing methods and fine-tuning-based debiasing methods may not be suitable for current LLMs. To address this issue, we explore combining active learning with the causal mechanisms and propose a casual-guided active learning (CAL) framework, which utilizes LLMs itself to automatically and autonomously identify informative biased samples and induce the bias patterns. Then a cost-effective and efficient in-context learning based method is employed to prevent LLMs from utilizing dataset biases during generation. Experimental results show that CAL can effectively recognize typical biased instances and induce various bias patterns for debiasing LLMs.
Authors: Yosuke Miyanishi, Minh Le Nguyen
Abstract: The rapid growth of Large Language Models (LLMs) usage has highlighted the importance of gradient-free in-context learning (ICL). However, interpreting their inner workings remains challenging. This paper introduces a novel multimodal contrastive in-context learning framework to enhance our understanding of ICL in LLMs. First, we present a contrastive learning-based interpretation of ICL in real-world settings, marking the distance of the key-value representation as the differentiator in ICL. Second, we develop an analytical framework to address biases in multimodal input formatting for real-world datasets. We demonstrate the effectiveness of ICL examples where baseline performance is poor, even when they are represented in unseen formats. Lastly, we propose an on-the-fly approach for ICL (Anchored-by-Text ICL) that demonstrates effectiveness in detecting hateful memes, a task where typical ICL struggles due to resource limitations. Extensive experiments on multimodal datasets reveal that our approach significantly improves ICL performance across various scenarios, such as challenging tasks and resource-constrained environments. Moreover, it provides valuable insights into the mechanisms of in-context learning in LLMs. Our findings have important implications for developing more interpretable, efficient, and robust multimodal AI systems, especially in challenging tasks and resource-constrained environments.
Authors: Art\=uras Nakvosas, Povilas Daniu\v{s}is, Vytas Mulevi\v{c}ius
Abstract: In this paper, we propose and describe the first open Llama2 large language models (LLMs) for the Lithuanian language, including an accompanying question/answer (Q/A) dataset and translations of popular LLM benchmarks. We provide a brief review of open regional LLMs and detailed information on the proposed LLMs and their training process. We also conduct an empirical evaluation, comparing the perplexities of the proposed LLMs with those of other modern open LLMs. In addition, benchmarking the proposed LLMs against language understanding tasks reveals that high-quality pretraining datasets may be essential for achieving models that perform efficiently on these benchmarks. The full realisations of the described LLMs are available in the accompanying open repository~\url{https://huggingface.co/neurotechnology}.
Authors: Haowei Du, Dongyan Zhao
Abstract: Recent works have attempted to integrate external knowledge into LLMs to address the limitations and potential factual errors in LLM-generated content. However, how to retrieve the correct knowledge from the large amount of external knowledge imposes a challenge. To this end, we empirically observe that LLMs have already encoded rich knowledge in their pretrained parameters and utilizing these internal knowledge improves the retrieval of external knowledge when applying them to knowledge-intensive tasks. In this paper, we propose a new internal and external knowledge interactive refinement paradigm dubbed IEKR to utilize internal knowledge in LLM to help retrieve relevant knowledge from the external knowledge base, as well as exploit the external knowledge to refine the hallucination of generated internal knowledge. By simply adding a prompt like 'Tell me something about' to the LLMs, we try to review related explicit knowledge and insert them with the query into the retriever for external retrieval. The external knowledge is utilized to complement the internal knowledge into input of LLM for answers. We conduct experiments on 3 benchmark datasets in knowledge-intensive question answering task with different LLMs and domains, achieving the new state-of-the-art. Further analysis shows the effectiveness of different modules in our approach.
Authors: Mohamed Elgaar, Jiali Cheng, Nidhi Vakil, Hadi Amiri, Leo Anthony Celi
Abstract: Medical decisions directly impact individuals' health and well-being. Extracting decision spans from clinical notes plays a crucial role in understanding medical decision-making processes. In this paper, we develop a new dataset called "MedDec", which contains clinical notes of eleven different phenotypes (diseases) annotated by ten types of medical decisions. We introduce the task of medical decision extraction, aiming to jointly extract and classify different types of medical decisions within clinical notes. We provide a comprehensive analysis of the dataset, develop a span detection model as a baseline for this task, evaluate recent span detection approaches, and employ a few metrics to measure the complexity of data samples. Our findings shed light on the complexities inherent in clinical decision extraction and enable future work in this area of research. The dataset and code are available through https://github.com/CLU-UML/MedDec.
Authors: Hui Wei, Shenghua He, Tian Xia, Andy Wong, Jingyang Lin, Mei Han
Abstract: Alignment approaches such as RLHF and DPO are actively investigated to align large language models (LLMs) with human preferences. Commercial large language models (LLMs) like GPT-4 have been recently employed to evaluate and compare different LLM alignment approaches. These models act as surrogates for human evaluators due to their promising abilities to approximate human preferences with remarkably faster feedback and lower costs. This methodology is referred to as LLM-as-a-judge. However, concerns regarding its reliability have emerged, attributed to LLM judges' biases and inconsistent decision-making. Previous research has sought to develop robust evaluation frameworks for assessing the reliability of LLM judges and their alignment with human preferences. However, the employed evaluation metrics often lack adequate explainability and fail to address the internal inconsistency of LLMs. Additionally, existing studies inadequately explore the impact of various prompt templates when applying LLM-as-a-judge methods, which leads to potentially inconsistent comparisons between different alignment algorithms. In this work, we systematically evaluate LLM judges on alignment tasks (e.g. summarization) by defining evaluation metrics with improved theoretical interpretability and disentangling reliability metrics with LLM internal inconsistency. We develop a framework to evaluate, compare, and visualize the reliability and alignment of LLM judges to provide informative observations that help choose LLM judges for alignment tasks. Our results indicate a significant impact of prompt templates on LLM judge performance, as well as a mediocre alignment level between the tested LLM judges and human evaluators.
Authors: Haowei Du, Dongyan Zhao
Abstract: In-context learning (ICL) of large language models (LLMs) has attracted increasing attention in the community where LLMs make predictions only based on instructions augmented with a few examples. Existing example selection methods for ICL utilize sparse or dense retrievers and derive effective performance. However, these methods do not utilize direct feedback of LLM to train the retriever and the examples selected can not necessarily improve the analogy ability of LLM. To tackle this, we propose our policy-based reinforcement learning framework for example selection (RLS), which consists of a language model (LM) selector and an LLM generator. The LM selector encodes the candidate examples into dense representations and selects the top-k examples into the demonstration for LLM. The outputs of LLM are adopted to compute the reward and policy gradient to optimize the LM selector. We conduct experiments on different datasets and significantly outperform existing example selection methods. Moreover, our approach shows advantages over supervised finetuning (SFT) models in few shot setting. Further experiments show the balance of abundance and the similarity with the test case of examples is important for ICL performance of LLM.
Authors: Mehedi Tajrian, Azizur Rahman, Muhammad Ashad Kabir, Md Rafiqul Islam
Abstract: The rapid dissemination of misinformation on the internet complicates the decision-making process for individuals seeking reliable information, particularly parents researching child development topics. This misinformation can lead to adverse consequences, such as inappropriate treatment of children based on myths. While previous research has utilized text-mining techniques to predict child abuse cases, there has been a gap in the analysis of child development myths and facts. This study addresses this gap by applying text mining techniques and classification models to distinguish between myths and facts about child development, leveraging newly gathered data from publicly available websites. The research methodology involved several stages. First, text mining techniques were employed to pre-process the data, ensuring enhanced accuracy. Subsequently, the structured data was analysed using six robust Machine Learning (ML) classifiers and one Deep Learning (DL) model, with two feature extraction techniques applied to assess their performance across three different training-testing splits. To ensure the reliability of the results, cross-validation was performed using both k-fold and leave-one-out methods. Among the classification models tested, Logistic Regression (LR) demonstrated the highest accuracy, achieving a 90% accuracy with the Bag-of-Words (BoW) feature extraction technique. LR stands out for its exceptional speed and efficiency, maintaining low testing time per statement (0.97 microseconds). These findings suggest that LR, when combined with BoW, is effective in accurately classifying child development information, thus providing a valuable tool for combating misinformation and assisting parents in making informed decisions.
Authors: Lifeng Zhou, Yuke Li
Abstract: In this paper, we propose a novel framework for speech-image retrieval. We utilize speech-image contrastive (SIC) learning tasks to align speech and image representations at a coarse level and speech-image matching (SIM) learning tasks to further refine the fine-grained cross-modal alignment. SIC and SIM learning tasks are jointly trained in a unified manner. To optimize the learning process, we utilize an embedding queue that facilitates efficient sampling of high-quality and diverse negative representations during SIC learning. Additionally, it enhances the learning of SIM tasks by effectively mining hard negatives based on contrastive similarities calculated in SIC tasks. To further optimize learning under noisy supervision, we incorporate momentum distillation into the training process. Experimental results show that our framework outperforms the state-of-the-art method by more than 4% in R@1 on two benchmark datasets for the speech-image retrieval tasks. Moreover, as observed in zero-shot experiments, our framework demonstrates excellent generalization capabilities.
Authors: Maartje De Meulder, Davy Van Landuyt, Rehana Omardeen
Abstract: In the era of AI-driven language technologies, there is a growing demand for the participation and leadership of deaf communities in sign language technology development, often framed as co-creation. This paper, developed through collaborative and iterative dialogue between the authors with data from informal participant observations, examines the involvement of the European Union of the Deaf in two EU Horizon 2020 projects, EASIER and SignON. These projects aimed to develop mobile translation applications between signed and spoken languages, bringing together predominantly hearing, non-signing technology experts with predominantly hearing sign language academics and organizations representing deaf end users in large multi-partner consortia. While co-creation is sometimes presented as the best or required way to do research or even as emancipatory, it frequently masks systemic issues of power imbalances and tokenism. Drawing from EUD's experiences of these projects, we highlight several inconvenient truths of co-creation, and propose seven lessons for future initiatives: recognizing deaf partners' invisible labour as work, managing expectations about technologies, cripping co-creation processes, exploring alternative methods to mitigate co-creation fatigue, seeking intersectional feedback, ensuring co-creation is not just virtue signalling, and fostering deaf leadership in AI sign language research. We argue for co-creation as a transformative activity that fundamentally alters the status quo and levels the playing field. This necessitates increasing the number of deaf researchers and enhancing AI literacy among deaf communities. Without these critical transformative actions, co-creation risks merely paying lip service to deaf communities.
Authors: Hourui Deng, Hongjie Zhang, Jie Ou, Chaosheng Feng
Abstract: Spatial reasoning in Large Language Models (LLMs) is the foundation for embodied intelligence. However, even in simple maze environments, LLMs still encounter challenges in long-term path-planning, primarily influenced by their spatial hallucination and context inconsistency hallucination by long-term reasoning. To address this challenge, this study proposes an innovative model, Spatial-to-Relational Transformation and Curriculum Q-Learning (S2RCQL). To address the spatial hallucination of LLMs, we propose the Spatial-to-Relational approach, which transforms spatial prompts into entity relations and paths representing entity relation chains. This approach fully taps the potential of LLMs in terms of sequential thinking. As a result, we design a path-planning algorithm based on Q-learning to mitigate the context inconsistency hallucination, which enhances the reasoning ability of LLMs. Using the Q-value of state-action as auxiliary information for prompts, we correct the hallucinations of LLMs, thereby guiding LLMs to learn the optimal path. Finally, we propose a reverse curriculum learning technique based on LLMs to further mitigate the context inconsistency hallucination. LLMs can rapidly accumulate successful experiences by reducing task difficulty and leveraging them to tackle more complex tasks. We performed comprehensive experiments based on Baidu's self-developed LLM: ERNIE-Bot 4.0. The results showed that our S2RCQL achieved a 23%--40% improvement in both success and optimality rates compared with advanced prompt engineering.
Authors: Dineth Jayakody, A V A Malkith, Koshila Isuranda, Vishal Thenuwara, Nisansa de Silva, Sachintha Rajith Ponnamperuma, G G N Sandamali, K L K Sudheera
Abstract: Aspect-based Sentiment Analysis (ABSA) is a critical task in Natural Language Processing (NLP) that focuses on extracting sentiments related to specific aspects within a text, offering deep insights into customer opinions. Traditional sentiment analysis methods, while useful for determining overall sentiment, often miss the implicit opinions about particular product or service features. This paper presents a comprehensive review of the evolution of ABSA methodologies, from lexicon-based approaches to machine learning and deep learning techniques. We emphasize the recent advancements in Transformer-based models, particularly Bidirectional Encoder Representations from Transformers (BERT) and its variants, which have set new benchmarks in ABSA tasks. We focused on finetuning Llama and Mistral models, building hybrid models using the SetFit framework, and developing our own model by exploiting the strengths of state-of-the-art (SOTA) Transformer-based models for aspect term extraction (ATE) and aspect sentiment classification (ASC). Our hybrid model Instruct - DeBERTa uses SOTA InstructABSA for aspect extraction and DeBERTa-V3-baseabsa-V1 for aspect sentiment classification. We utilize datasets from different domains to evaluate our model's performance. Our experiments indicate that the proposed hybrid model significantly improves the accuracy and reliability of sentiment analysis across all experimented domains. As per our findings, our hybrid model Instruct - DeBERTa is the best-performing model for the joint task of ATE and ASC for both SemEval restaurant 2014 and SemEval laptop 2014 datasets separately. By addressing the limitations of existing methodologies, our approach provides a robust solution for understanding detailed consumer feedback, thus offering valuable insights for businesses aiming to enhance customer satisfaction and product development.
Authors: Nigel G. Ward, Divette Marco, Olac Fuentes
Abstract: We investigate which prosodic features matter most in conveying prosodic functions. We use the problem of predicting human perceptions of pragmatic similarity among utterance pairs to evaluate the utility of prosodic features of different types. We find, for example, that duration-related features are more important than pitch-related features, and that utterance-initial features are more important than utterance-final features. Further, failure analysis indicates that modeling using pitch features only often fails to handle important pragmatic functions, and suggests that several generally-neglected acoustic and prosodic features are pragmatically significant, including nasality and vibrato. These findings can guide future basic research in prosody, and suggest how to improve speech synthesis evaluation, among other applications.
Authors: C\'elia D'Cruz, Jean-Marc Bereder, Fr\'ed\'eric Precioso, Michel Riveill
Abstract: Large Language Models have undoubtedly revolutionized the Natural Language Processing field, the current trend being to promote one-model-for-all tasks (sentiment analysis, translation, etc.). However, the statistical mechanisms at work in the larger language models struggle to exploit the relevant information when it is very sparse, when it is a weak signal. This is the case, for example, for the classification of long domain-specific documents, when the relevance relies on a single relevant word or on very few relevant words from technical jargon. In the medical domain, it is essential to determine whether a given report contains critical information about a patient's condition. This critical information is often based on one or few specific isolated terms. In this paper, we propose a hierarchical model which exploits a short list of potential target terms to retrieve candidate sentences and represent them into the contextualized embedding of the target term(s) they contain. A pooling of the term(s) embedding(s) entails the document representation to be classified. We evaluate our model on one public medical document benchmark in English and on one private French medical dataset. We show that our narrower hierarchical model is better than larger language models for retrieving relevant long documents in a domain-specific context.
Authors: Miroslaw Staron, Jonathan Strom, Albin Karlsson, Wilhelm Meding
Abstract: Standardization processes build upon consensus between partners, which depends on their ability to identify points of disagreement and resolving them. Large standardization organizations, like the 3GPP or ISO, rely on leaders of work packages who can correctly, and efficiently, identify disagreements, discuss them and reach a consensus. This task, however, is effort-, labor-intensive and costly. In this paper, we address the problem of identifying similarities, dissimilarities and discussion points using large language models. In a design science research study, we work with one of the organizations which leads several workgroups in the 3GPP standard. Our goal is to understand how well the language models can support the standardization process in becoming more cost-efficient, faster and more reliable. Our results show that generic models for text summarization correlate well with domain expert's and delegate's assessments (Pearson correlation between 0.66 and 0.98), but that there is a need for domain-specific models to provide better discussion materials for the standardization groups.
Authors: Shentong Mo, Paul Pu Liang
Abstract: Biomedical data is inherently multimodal, consisting of electronic health records, medical imaging, digital pathology, genome sequencing, wearable sensors, and more. The application of artificial intelligence tools to these multifaceted sensing technologies has the potential to revolutionize the prognosis, diagnosis, and management of human health and disease. However, current approaches to biomedical AI typically only train and evaluate with one or a small set of medical modalities and tasks. This limitation hampers the development of comprehensive tools that can leverage the rich interconnected information across many heterogeneous biomedical sensors. To address this challenge, we present MultiMed, a benchmark designed to evaluate and enable large-scale learning across a wide spectrum of medical modalities and tasks. MultiMed consists of 2.56 million samples across ten medical modalities such as medical reports, pathology, genomics, and protein data, and is structured into eleven challenging tasks, including disease prognosis, protein structure prediction, and medical question answering. Using MultiMed, we conduct comprehensive experiments benchmarking state-of-the-art unimodal, multimodal, and multitask models. Our analysis highlights the advantages of training large-scale medical models across many related modalities and tasks. Moreover, MultiMed enables studies of generalization across related medical concepts, robustness to real-world noisy data and distribution shifts, and novel modality combinations to improve prediction performance. MultiMed will be publicly available and regularly updated and welcomes inputs from the community.
Authors: Mohammadreza Pourreza, Ruoxi Sun, Hailong Li, Lesly Miculicich, Tomas Pfister, Sercan O. Arik
Abstract: Text-to-SQL systems, which convert natural language queries into SQL commands, have seen significant progress primarily for the SQLite dialect. However, adapting these systems to other SQL dialects like BigQuery and PostgreSQL remains a challenge due to the diversity in SQL syntax and functions. We introduce SQL-GEN, a framework for generating high-quality dialect-specific synthetic data guided by dialect-specific tutorials, and demonstrate its effectiveness in creating training datasets for multiple dialects. Our approach significantly improves performance, by up to 20\%, over previous methods and reduces the gap with large-scale human-annotated datasets. Moreover, combining our synthetic data with human-annotated data provides additional performance boosts of 3.3\% to 5.6\%. We also introduce a novel Mixture of Experts (MoE) initialization method that integrates dialect-specific models into a unified system by merging self-attention layers and initializing the gates with dialect-specific keywords, further enhancing performance across different SQL dialects.
Authors: Jean Park, Kuk Jin Jang, Basam Alasaly, Sriharsha Mopidevi, Andrew Zolensky, Eric Eaton, Insup Lee, Kevin Johnson
Abstract: Multimodal large language models (MLLMs) can simultaneously process visual, textual, and auditory data, capturing insights that complement human analysis. However, existing video question-answering (VidQA) benchmarks and datasets often exhibit a bias toward a single modality, despite the goal of requiring advanced reasoning skills that integrate diverse modalities to answer the queries. In this work, we introduce the modality importance score (MIS) to identify such bias. It is designed to assess which modality embeds the necessary information to answer the question. Additionally, we propose an innovative method using state-of-the-art MLLMs to estimate the modality importance, which can serve as a proxy for human judgments of modality perception. With this MIS, we demonstrate the presence of unimodal bias and the scarcity of genuinely multimodal questions in existing datasets. We further validate the modality importance score with multiple ablation studies to evaluate the performance of MLLMs on permuted feature sets. Our results indicate that current models do not effectively integrate information due to modality imbalance in existing datasets. Our proposed MLLM-derived MIS can guide the curation of modality-balanced datasets that advance multimodal learning and enhance MLLMs' capabilities to understand and utilize synergistic relations across modalities.
Authors: Purushothaman Natarajan, Athira Nambiar
Abstract: Deep Neural Networks (DNNs) have revolutionized various fields by enabling task automation and reducing human error. However, their internal workings and decision-making processes remain obscure due to their black box nature. Consequently, the lack of interpretability limits the application of these models in high-risk scenarios. To address this issue, the emerging field of eXplainable Artificial Intelligence (XAI) aims to explain and interpret the inner workings of DNNs. Despite advancements, XAI faces challenges such as the semantic gap between machine and human understanding, the trade-off between interpretability and performance, and the need for context-specific explanations. To overcome these limitations, we propose a novel multimodal framework named VALE Visual and Language Explanation. VALE integrates explainable AI techniques with advanced language models to provide comprehensive explanations. This framework utilizes visual explanations from XAI tools, an advanced zero-shot image segmentation model, and a visual language model to generate corresponding textual explanations. By combining visual and textual explanations, VALE bridges the semantic gap between machine outputs and human interpretation, delivering results that are more comprehensible to users. In this paper, we conduct a pilot study of the VALE framework for image classification tasks. Specifically, Shapley Additive Explanations (SHAP) are used to identify the most influential regions in classified images. The object of interest is then extracted using the Segment Anything Model (SAM), and explanations are generated using state-of-the-art pre-trained Vision-Language Models (VLMs). Extensive experimental studies are performed on two datasets: the ImageNet dataset and a custom underwater SONAR image dataset, demonstrating VALEs real-world applicability in underwater image classification.
Authors: Kaizhao Liang, Bo Liu, Lizhang Chen, Qiang Liu
Abstract: Recently, a wide range of memory-efficient LLM training algorithms have gained substantial popularity. These methods leverage the low-rank structure of gradients to project optimizer states into a subspace using projection matrix found by singular value decomposition (SVD). However, convergence of these algorithms is highly dependent on the update rules of their projection matrix. In this work, we provide the \emph{first} convergence guarantee for arbitrary update rules of projection matrix. This guarantee is generally applicable to optimizers that can be analyzed with Hamiltonian Descent, including most common ones, such as LION, Adam. Inspired by our theoretical understanding, we propose Online Subspace Descent, a new family of subspace descent optimizer without SVD. Instead of updating the projection matrix with eigenvectors, Online Subspace Descent updates the projection matrix with online PCA. Online Subspace Descent is flexible and introduces only minimum overhead to training. We show that for the task of pretraining LLaMA models ranging from 60M to 7B parameters on the C4 dataset, Online Subspace Descent achieves lower perplexity and better downstream tasks performance than state-of-the-art low-rank training methods across different settings and narrows the gap with full-rank baselines.
Authors: Bin Wang, Chunyu Xie, Dawei Leng, Yuhui Yin
Abstract: In the field of multimodal large language models (MLLMs), common methods typically involve unfreezing the language model during training to foster profound visual understanding. However, the fine-tuning of such models with vision-language data often leads to a diminution of their natural language processing (NLP) capabilities. To avoid this performance degradation, a straightforward solution is to freeze the language model while developing multimodal competencies. Unfortunately, previous works have not attained satisfactory outcomes. Building on the strategy of freezing the language model, we conduct thorough structural exploration and introduce the Inner-Adaptor Architecture (IAA). Specifically, the architecture incorporates multiple multimodal adaptors at varying depths within the large language model to facilitate direct interaction with the inherently text-oriented transformer layers, thereby enabling the frozen language model to acquire multimodal capabilities. Unlike previous approaches of freezing language models that require large-scale aligned data, our proposed architecture is able to achieve superior performance on small-scale datasets. We conduct extensive experiments to improve the general multimodal capabilities and visual grounding abilities of the MLLM. Our approach remarkably outperforms previous state-of-the-art methods across various vision-language benchmarks without sacrificing performance on NLP tasks. Code and models are available at https://github.com/360CVGroup/Inner-Adaptor-Architecture.
URLs: https://github.com/360CVGroup/Inner-Adaptor-Architecture.
Authors: Kai-Wei Chang, Haibin Wu, Yu-Kai Wang, Yuan-Kuei Wu, Hua Shen, Wei-Cheng Tseng, Iu-thing Kang, Shang-Wen Li, Hung-yi Lee
Abstract: Prompting has become a practical method for utilizing pre-trained language models (LMs). This approach offers several advantages. It allows an LM to adapt to new tasks with minimal training and parameter updates, thus achieving efficiency in both storage and computation. Additionally, prompting modifies only the LM's inputs and harnesses the generative capabilities of language models to address various downstream tasks in a unified manner. This significantly reduces the need for human labor in designing task-specific models. These advantages become even more evident as the number of tasks served by the LM scales up. Motivated by the strengths of prompting, we are the first to explore the potential of prompting speech LMs in the domain of speech processing. Recently, there has been a growing interest in converting speech into discrete units for language modeling. Our pioneer research demonstrates that these quantized speech units are highly versatile within our unified prompting framework. Not only can they serve as class labels, but they also contain rich phonetic information that can be re-synthesized back into speech signals for speech generation tasks. Specifically, we reformulate speech processing tasks into speech-to-unit generation tasks. As a result, we can seamlessly integrate tasks such as speech classification, sequence generation, and speech generation within a single, unified prompting framework. The experiment results show that the prompting method can achieve competitive performance compared to the strong fine-tuning method based on self-supervised learning models with a similar number of trainable parameters. The prompting method also shows promising results in the few-shot setting. Moreover, with the advanced speech LMs coming into the stage, the proposed prompting framework attains great potential.
Authors: Hongcheng Ding, Xuanze Zhao, Zixiao Jiang, Shamsul Nahar Abdullah, Deshinta Arrova Dewi
Abstract: Accurate forecasting of the EUR/USD exchange rate is crucial for investors, businesses, and policymakers. This paper proposes a novel framework, IUS, that integrates unstructured textual data from news and analysis with structured data on exchange rates and financial indicators to enhance exchange rate prediction. The IUS framework employs large language models for sentiment polarity scoring and exchange rate movement classification of texts. These textual features are combined with quantitative features and input into a Causality-Driven Feature Generator. An Optuna-optimized Bi-LSTM model is then used to forecast the EUR/USD exchange rate. Experiments demonstrate that the proposed method outperforms benchmark models, reducing MAE by 10.69% and RMSE by 9.56% compared to the best performing baseline. Results also show the benefits of data fusion, with the combination of unstructured and structured data yielding higher accuracy than structured data alone. Furthermore, feature selection using the top 12 important quantitative features combined with the textual features proves most effective. The proposed IUS framework and Optuna-Bi-LSTM model provide a powerful new approach for exchange rate forecasting through multi-source data integration.
Authors: Ahmad Pouramini, Hesham Faili
Abstract: In recent years, multi-task prompt tuning has garnered considerable attention for its inherent modularity and potential to enhance parameter-efficient transfer learning across diverse tasks. This paper aims to analyze and improve the performance of multiple tasks by facilitating the transfer of knowledge between their corresponding prompts in a multi-task setting. Our proposed approach decomposes the prompt for each target task into a combination of shared prompts (source prompts) and a task-specific prompt (private prompt). During training, the source prompts undergo fine-tuning and are integrated with the private prompt to drive the target prompt for each task. We present and compare multiple methods for combining source prompts to construct the target prompt, analyzing the roles of both source and private prompts within each method. We investigate their contributions to task performance and offer flexible, adjustable configurations based on these insights to optimize performance. Our empirical findings clearly showcase improvements in accuracy and robustness compared to the conventional practice of prompt tuning and related works. Notably, our results substantially outperform other methods in the field in few-shot settings, demonstrating superior performance in various tasks across GLUE benchmark, among other tasks. This achievement is attained with a significantly reduced amount of training data, making our method a promising one for few-shot settings.
Authors: Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Yufa Zhou
Abstract: The quadratic computational complexity in the self-attention mechanism of popular transformer architectures poses significant challenges for training and inference, particularly in terms of efficiency and memory requirements. Towards addressing these challenges, this paper introduces a novel fast computation method for gradient calculation in multi-layer transformer models. Our approach enables the computation of gradients for the entire multi-layer transformer model in almost linear time $n^{1+o(1)}$, where $n$ is the input sequence length. This breakthrough significantly reduces the computational bottleneck associated with the traditional quadratic time complexity. Our theory holds for any loss function and maintains a bounded approximation error across the entire model. Furthermore, our analysis can hold when the multi-layer transformer model contains many practical sub-modules, such as residual connection, casual mask, and multi-head attention. By improving the efficiency of gradient computation in large language models, we hope that our work will facilitate the more effective training and deployment of long-context language models based on our theoretical results.
Authors: Evin Jaff, Yuhao Wu, Ning Zhang, Umar Iqbal
Abstract: LLM app ecosystems are quickly maturing and supporting a wide range of use cases, which requires them to collect excessive user data. Given that the LLM apps are developed by third-parties and that anecdotal evidence suggests LLM platforms currently do not strictly enforce their policies, user data shared with arbitrary third-parties poses a significant privacy risk. In this paper we aim to bring transparency in data practices of LLM apps. As a case study, we study OpenAI's GPT app ecosystem. We develop an LLM-based framework to conduct the static analysis of natural language-based source code of GPTs and their Actions (external services) to characterize their data collection practices. Our findings indicate that Actions collect expansive data about users, including sensitive information prohibited by OpenAI, such as passwords. We find that some Actions, including related to advertising and analytics, are embedded in multiple GPTs, which allow them to track user activities across GPTs. Additionally, co-occurrence of Actions exposes as much as 9.5x more data to them, than it is exposed to individual Actions. Lastly, we develop an LLM-based privacy policy analysis framework to automatically check the consistency of data collection by Actions with disclosures in their privacy policies. Our measurements indicate that the disclosures for most of the collected data types are omitted in privacy policies, with only 5.8% of Actions clearly disclosing their data collection practices.
Authors: Murtadha Ahmed, Bo Wen, Shengfeng Pan, Jianlin Su, Luo Ao, Yunfeng Liu
Abstract: Aspect-based sentiment analysis (ABSA) aims to associate a text with a set of aspects and infer their respective sentimental polarities. State-of-the-art approaches are built on fine-tuning pre-trained language models, focusing on learning aspect-specific representations from the corpus. However, aspects are often expressed implicitly, making implicit mapping challenging without sufficient labeled examples, which may be scarce in real-world scenarios. This paper proposes a unified framework to address aspect categorization and aspect-based sentiment subtasks. We introduce a mechanism to construct an auxiliary-sentence for the implicit aspect using the corpus's semantic information. We then encourage BERT to learn aspect-specific representation in response to this auxiliary-sentence, not the aspect itself. We evaluate our approach on real benchmark datasets for both ABSA and Targeted-ABSA tasks. Our experiments show that it consistently achieves state-of-the-art performance in aspect categorization and aspect-based sentiment across all datasets, with considerable improvement margins. The BERT-ASC code is available at https://github.com/amurtadha/BERT-ASC.
Authors: Manuel V. Loureiro, Steven Derby, Tri Kurniawan Wijaya
Abstract: Topic models aim to reveal latent structures within a corpus of text, typically through the use of term-frequency statistics over bag-of-words representations from documents. In recent years, conceptual entities -- interpretable, language-independent features linked to external knowledge resources -- have been used in place of word-level tokens, as words typically require extensive language processing with a minimal assurance of interpretability. However, current literature is limited when it comes to exploring purely entity-driven neural topic modeling. For instance, despite the advantages of using entities for eliciting thematic structure, it is unclear whether current techniques are compatible with these sparsely organised, information-dense conceptual units. In this work, we explore entity-based neural topic modeling and propose a novel topic clustering approach using bimodal vector representations of entities. Concretely, we extract these latent representations from large language models and graph neural networks trained on a knowledge base of symbolic relations, in order to derive the most salient aspects of these conceptual units. Analysis of coherency metrics confirms that our approach is better suited to working with entities in comparison to state-of-the-art models, particularly when using graph-based embeddings trained on a knowledge base.
Authors: Alberto Mu\~noz-Ortiz, Carlos G\'omez-Rodr\'iguez, David Vilares
Abstract: We conduct a quantitative analysis contrasting human-written English news text with comparable large language model (LLM) output from six different LLMs that cover three different families and four sizes in total. Our analysis spans several measurable linguistic dimensions, including morphological, syntactic, psychometric, and sociolinguistic aspects. The results reveal various measurable differences between human and AI-generated texts. Human texts exhibit more scattered sentence length distributions, more variety of vocabulary, a distinct use of dependency and constituent types, shorter constituents, and more optimized dependency distances. Humans tend to exhibit stronger negative emotions (such as fear and disgust) and less joy compared to text generated by LLMs, with the toxicity of these models increasing as their size grows. LLM outputs use more numbers, symbols and auxiliaries (suggesting objective language) than human texts, as well as more pronouns. The sexist bias prevalent in human text is also expressed by LLMs, and even magnified in all of them but one. Differences between LLMs and humans are larger than between LLMs.
Authors: Elena Shushkevich, Long Mai, Manuel V. Loureiro, Steven Derby, Tri Kurniawan Wijaya
Abstract: The proliferation of news media outlets has increased the demand for intelligent systems capable of detecting redundant information in news articles in order to enhance user experience. However, the heterogeneous nature of news can lead to spurious findings in these systems: Simple heuristics such as whether a pair of news are both about politics can provide strong but deceptive downstream performance. Segmenting news similarity datasets into topics improves the training of these models by forcing them to learn how to distinguish salient characteristics under more narrow domains. However, this requires the existence of topic-specific datasets, which are currently lacking. In this article, we propose a novel dataset of similar news, SPICED, which includes seven topics: Crime & Law, Culture & Entertainment, Disasters & Accidents, Economy & Business, Politics & Conflicts, Science & Technology, and Sports. Futhermore, we present four different levels of complexity, specifically designed for news similarity detection task. We benchmarked the created datasets using MinHash, BERT, SBERT, and SimCSE models.
Authors: Alisa Liu, Xiaochuang Han, Yizhong Wang, Yulia Tsvetkov, Yejin Choi, Noah A. Smith
Abstract: Despite the general capabilities of large pretrained language models, they consistently benefit from further adaptation to better achieve desired behaviors. However, tuning these models has become increasingly resource-intensive, or impossible when model weights are private. We introduce proxy-tuning, a lightweight decoding-time algorithm that operates on top of black-box LMs to achieve the same end as direct tuning, but by accessing only its predictions over the output vocabulary, not its parameters. Our method tunes a smaller LM, then applies the difference between the predictions of the small tuned and untuned LMs to shift the original predictions of the larger untuned model in the direction of tuning, while retaining the benefits of larger-scale pretraining. In experiments, when we apply proxy-tuning to Llama2-70B using proxies of only 7B size, we can close 88% of the gap between Llama2-70B and its truly-tuned chat version, when evaluated across knowledge, reasoning, and safety benchmarks. We then demonstrate the generality of proxy-tuning by applying it to domain adaptation on code, and task-specific finetuning on question-answering and math problems. Finally, we show how to proxy-tune a truly black-box LM, GPT-3.5, for temporal adaptation, increasing its knowledge about recent events. Our work demonstrates the promise of using small tuned LMs to efficiently customize large, potentially proprietary LMs through decoding-time guidance.
Authors: Phuc Phan, Hieu Tran, Long Phan
Abstract: We propose a straightforward approach called Distillation Contrastive Decoding (DCD) to enhance the reasoning capabilities of Large Language Models (LLMs) during inference. In contrast to previous approaches that relied on smaller amateur models or analysis of hidden state differences, DCD employs Contrastive Chain-of-thought Prompting and advanced distillation techniques, including Dropout and Quantization. This approach effectively addresses the limitations of Contrastive Decoding (CD), which typically requires both an expert and an amateur model, thus increasing computational resource demands. By integrating contrastive prompts with distillation, DCD obviates the need for an amateur model and reduces memory usage. Our evaluations demonstrate that DCD significantly enhances LLM performance across a range of reasoning benchmarks, surpassing both CD and existing methods in the GSM8K and StrategyQA datasets.
Authors: Simeon Junker, Sina Zarrie{\ss}
Abstract: Scene context is well known to facilitate humans' perception of visible objects. In this paper, we investigate the role of context in Referring Expression Generation (REG) for objects in images, where existing research has often focused on distractor contexts that exert pressure on the generator. We take a new perspective on scene context in REG and hypothesize that contextual information can be conceived of as a resource that makes REG models more resilient and facilitates the generation of object descriptions, and object types in particular. We train and test Transformer-based REG models with target representations that have been artificially obscured with noise to varying degrees. We evaluate how properties of the models' visual context affect their processing and performance. Our results show that even simple scene contexts make models surprisingly resilient to perturbations, to the extent that they can identify referent types even when visual information about the target is completely missing.
Authors: Chujie Gao, Qihui Zhang, Dongping Chen, Yue Huang, Siyuan Wu, Zhengyan Fu, Yao Wan, Xiangliang Zhang, Lichao Sun
Abstract: Large Language Models (LLMs) have achieved remarkable success across various industries due to their exceptional generative capabilities. However, for safe and effective real-world deployments, ensuring honesty and helpfulness is critical. This paper addresses the question: Can we prioritize the helpfulness of LLMs while preserving their honesty? To begin with, we establish exhaustive principles aimed at guaranteeing the honesty of LLM. Additionally, we introduce a novel dataset, referred to as HoneSet, comprising 930 queries spanning six categories meticulously crafted to assess an LLM's capacity for maintaining honesty. Subsequently, we present two approaches to augmenting honesty and helpfulness in LLMs: a training-free enhancement and a fine-tuning-based improvement. The training-free approach, which is based on curiosity-driven prompting, empowers LLMs to articulate internal confusion and uncertainty regarding queries, thereby optimizing their responses. Conversely, the fine-tuning-based method employs a two-stage process inspired by curriculum learning: initially instructing LLMs to discern between honest and dishonest responses, then refining their training to enhance helpfulness. Experiments conducted on nine prominent LLMs demonstrate a significant improvement in alignment with honesty across all models through the implementation of our proposed enhancements. Particularly noteworthy is the 65.3% enhancement observed in Llama3-8b and the remarkable 124.7% improvement in Mistral-7b, as measured by the H$^{2}$ (honest and helpful) assessment. We believe that our work can pave the way for developing more trustworthy LLMs for real-world applications.
Authors: Marcely Zanon Boito, Vivek Iyer, Nikolaos Lagos, Laurent Besacier, Ioan Calapodescu
Abstract: We present mHuBERT-147, the first general-purpose massively multilingual HuBERT speech representation model trained on 90K hours of clean, open-license data. To scale up the multi-iteration HuBERT approach, we use faiss-based clustering, achieving 5.2x faster label assignment than the original method. We also apply a new multilingual batching up-sampling strategy, leveraging both language and dataset diversity. After 3 training iterations, our compact 95M parameter mHuBERT-147 outperforms larger models trained on substantially more data. We rank second and first on the ML-SUPERB 10min and 1h leaderboards, with SOTA scores for 3 tasks. Across ASR/LID tasks, our model consistently surpasses XLS-R (300M params; 436K hours) and demonstrates strong competitiveness against the much larger MMS (1B params; 491K hours). Our findings indicate that mHuBERT-147 is a promising model for multilingual speech tasks, offering an unprecedented balance between high performance and parameter efficiency.
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. Our code is available at https://github.com/XiaoMi/subllm.
Authors: Garima Chhikara, Anurag Sharma, V. Gurucharan, Kripabandhu Ghosh, Abhijnan Chakraborty
Abstract: Large Language Models (LLMs) have demonstrated impressive performance across a wide range of NLP tasks, including summarization. LLMs inherently produce abstractive summaries by paraphrasing the original text, while the generation of extractive summaries - selecting specific subsets from the original text - remains largely unexplored. LLMs have a limited context window size, restricting the amount of data that can be processed at once. We tackle this challenge by introducing LaMSUM, a novel multi-level framework designed to generate extractive summaries from large collections of user-generated text using LLMs. LaMSUM integrates summarization with different voting methods to achieve robust summaries. Extensive evaluation using four popular LLMs (Llama 3, Mixtral, Gemini, GPT-4o) demonstrates that LaMSUM outperforms state-of-the-art extractive summarization methods. Overall, this work represents one of the first attempts to achieve extractive summarization by leveraging the power of LLMs, and is likely to spark further interest within the research community.
Authors: Siyuan Wu, Yue Huang, Chujie Gao, Dongping Chen, Qihui Zhang, Yao Wan, Tianyi Zhou, Xiangliang Zhang, Jianfeng Gao, Chaowei Xiao, Lichao Sun
Abstract: Large Language Models (LLMs) such as GPT-4 and Llama3 have significantly impacted various fields by enabling high-quality synthetic data generation and reducing dependence on expensive human-generated datasets. Despite this, challenges remain in the areas of generalization, controllability, diversity, and truthfulness within the existing generative frameworks. To address these challenges, this paper presents UniGen, a comprehensive LLM-powered framework designed to produce diverse, accurate, and highly controllable datasets. UniGen is adaptable, supporting all types of text datasets and enhancing the generative process through innovative mechanisms. To augment data diversity, UniGen incorporates an attribute-guided generation module and a group checking feature. For accuracy, it employs a code-based mathematical assessment for label verification alongside a retrieval-augmented generation technique for factual validation. The framework also allows for user-specified constraints, enabling customization of the data generation process to suit particular requirements. Extensive experiments demonstrate the superior quality of data generated by UniGen, and each module within UniGen plays a critical role in this enhancement. Additionally, UniGen is applied in two practical scenarios: benchmarking LLMs and data augmentation. The results indicate that UniGen effectively supports dynamic and evolving benchmarking, and that data augmentation improves LLM capabilities in various domains, including agent-oriented abilities and reasoning skills.
Authors: Emman Haider, Daniel Perez-Becker, Thomas Portet, Piyush Madan, Amit Garg, Atabak Ashfaq, David Majercak, Wen Wen, Dongwoo Kim, Ziyi Yang, Jianwen Zhang, Hiteshi Sharma, Blake Bullwinkel, Martin Pouliot, Amanda Minnich, Shiven Chawla, Solianna Herrera, Shahed Warreth, Maggie Engler, Gary Lopez, Nina Chikanov, Raja Sekhar Rao Dheekonda, Bolor-Erdene Jagdagdorj, Roman Lutz, Richard Lundeen, Tori Westerhoff, Pete Bryan, Christian Seifert, Ram Shankar Siva Kumar, Andrew Berkley, Alex Kessler
Abstract: Recent innovations in language model training have demonstrated that it is possible to create highly performant models that are small enough to run on a smartphone. As these models are deployed in an increasing number of domains, it is critical to ensure that they are aligned with human preferences and safety considerations. In this report, we present our methodology for safety aligning the Phi-3 series of language models. We utilized a "break-fix" cycle, performing multiple rounds of dataset curation, safety post-training, benchmarking, red teaming, and vulnerability identification to cover a variety of harm areas in both single and multi-turn scenarios. Our results indicate that this approach iteratively improved the performance of the Phi-3 models across a wide range of responsible AI benchmarks. Finally, we include additional red teaming strategies and evaluations that were used to test the safety behavior of Phi-3.5-mini and Phi-3.5-MoE, which were optimized for multilingual capabilities.
Authors: Desta Haileselassie Hagos, Rick Battle, Danda B. Rawat
Abstract: The emergence of Generative Artificial Intelligence (AI) and Large Language Models (LLMs) has marked a new era of Natural Language Processing (NLP), introducing unprecedented capabilities that are revolutionizing various domains. This paper explores the current state of these cutting-edge technologies, demonstrating their remarkable advancements and wide-ranging applications. Our paper contributes to providing a holistic perspective on the technical foundations, practical applications, and emerging challenges within the evolving landscape of Generative AI and LLMs. We believe that understanding the generative capabilities of AI systems and the specific context of LLMs is crucial for researchers, practitioners, and policymakers to collaboratively shape the responsible and ethical integration of these technologies into various domains. Furthermore, we identify and address main research gaps, providing valuable insights to guide future research endeavors within the AI research community.
Authors: Yuanwei Wu, Yue Huang, Yixin Liu, Xiang Li, Pan Zhou, Lichao Sun
Abstract: GPT-4V has attracted considerable attention due to its extraordinary capacity for integrating and processing multimodal information. At the same time, its ability of face recognition raises new safety concerns of privacy leakage. Despite researchers' efforts in safety alignment through RLHF or preprocessing filters, vulnerabilities might still be exploited. In our study, we introduce AutoJailbreak, an innovative automatic jailbreak technique inspired by prompt optimization. We leverage Large Language Models (LLMs) for red-teaming to refine the jailbreak prompt and employ weak-to-strong in-context learning prompts to boost efficiency. Furthermore, we present an effective search method that incorporates early stopping to minimize optimization time and token expenditure. Our experiments demonstrate that AutoJailbreak significantly surpasses conventional methods, achieving an Attack Success Rate (ASR) exceeding 95.3\%. This research sheds light on strengthening GPT-4V security, underscoring the potential for LLMs to be exploited in compromising GPT-4V integrity.
Authors: Chuhan Wu, Ruiming Tang
Abstract: Guided by the belief of the scaling law, large language models (LLMs) have achieved impressive performance in recent years. However, scaling law only gives a qualitative estimation of loss, which is influenced by various factors such as model architectures, data distributions, tokenizers, and computation precision. Thus, estimating the real performance of LLMs with different training settings rather than loss may be quite useful in practical development. In this article, we present an empirical equation named "Performance Law" to directly predict the MMLU score of an LLM, which is a widely used metric to indicate the general capability of LLMs in real-world conversations and applications. Based on only a few key hyperparameters of the LLM architecture and the size of training data, we obtain a quite accurate MMLU prediction of various LLMs with diverse sizes and architectures developed by different organizations in different years. Performance law can be used to guide the choice of LLM architecture and the effective allocation of computational resources without extensive experiments.
Authors: Jian Chen, Vashisth Tiwari, Ranajoy Sadhukhan, Zhuoming Chen, Jinyuan Shi, Ian En-Hsu Yen, Beidi Chen
Abstract: Large Language Models (LLMs) have become more prevalent in long-context applications such as interactive chatbots, document analysis, and agent workflows, but it is challenging to serve long-context requests with low latency and high throughput. Speculative decoding (SD) is a widely used technique to reduce latency without sacrificing performance but the conventional wisdom suggests that its efficacy is limited to small batch sizes. In MagicDec, we show that surprisingly SD can achieve speedup even for a high throughput inference regime for moderate to long sequences. More interestingly, an intelligent drafting strategy can achieve better speedup with increasing batch size based on our rigorous analysis. MagicDec first identifies the bottleneck shifts with increasing batch size and sequence length, and uses these insights to deploy speculative decoding more effectively for high throughput inference. Then, it leverages draft models with sparse KV cache to address the KV bottleneck that scales with both sequence length and batch size. This finding underscores the broad applicability of speculative decoding in long-context serving, as it can enhance throughput and reduce latency without compromising accuracy. For moderate to long sequences, we demonstrate up to 2x speedup for LLaMA-2-7B-32K and 1.84x speedup for LLaMA-3.1-8B when serving batch sizes ranging from 32 to 256 on 8 NVIDIA A100 GPUs. The code is available at https://github.com/Infini-AI-Lab/MagicDec/.
Authors: Yiquan Wu, Bo Tang, Chenyang Xi, Yu Yu, Pengyu Wang, Yifei Liu, Kun Kuang, Haiying Deng, Zhiyu Li, Feiyu Xiong, Jie Hu, Peng Cheng, Zhonghao Wang, Yi Wang, Yi Luo, Mingchuan Yang
Abstract: Commentary provides readers with a deep understanding of events by presenting diverse arguments and evidence. However, creating commentary is a time-consuming task, even for skilled commentators. Large language models (LLMs) have simplified the process of natural language generation, but their direct application in commentary creation still faces challenges due to unique task requirements. These requirements can be categorized into two levels: 1) fundamental requirements, which include creating well-structured and logically consistent narratives, and 2) advanced requirements, which involve generating quality arguments and providing convincing evidence. In this paper, we introduce Xinyu, an efficient LLM-based system designed to assist commentators in generating Chinese commentaries. To meet the fundamental requirements, we deconstruct the generation process into sequential steps, proposing targeted strategies and supervised fine-tuning (SFT) for each step. To address the advanced requirements, we present an argument ranking model for arguments and establish a comprehensive evidence database that includes up-to-date events and classic books, thereby strengthening the substantiation of the evidence with retrieval augmented generation (RAG) technology. To evaluate the generated commentaries more fairly, corresponding to the two-level requirements, we introduce a comprehensive evaluation metric that considers five distinct perspectives in commentary generation. Our experiments confirm the effectiveness of our proposed system. We also observe a significant increase in the efficiency of commentators in real-world scenarios, with the average time spent on creating a commentary dropping from 4 hours to 20 minutes. Importantly, such an increase in efficiency does not compromise the quality of the commentaries.
Authors: Priyanka Mandikal
Abstract: LLMs have revolutionized the landscape of information retrieval and knowledge dissemination. However, their application in specialized areas is often hindered by factual inaccuracies and hallucinations, especially in long-tail knowledge distributions. We explore the potential of retrieval-augmented generation (RAG) models for long-form question answering (LFQA) in a specialized knowledge domain. We present VedantaNY-10M, a dataset curated from extensive public discourses on the ancient Indian philosophy of Advaita Vedanta. We develop and benchmark a RAG model against a standard, non-RAG LLM, focusing on transcription, retrieval, and generation performance. Human evaluations by computational linguists and domain experts show that the RAG model significantly outperforms the standard model in producing factual and comprehensive responses having fewer hallucinations. In addition, a keyword-based hybrid retriever that emphasizes unique low-frequency terms further improves results. Our study provides insights into effectively integrating modern large language models with ancient knowledge systems. Project page with dataset and code: https://sites.google.com/view/vedantany-10m
Authors: Kun Luo, Minghao Qin, Zheng Liu, Shitao Xiao, Jun Zhao, Kang Liu
Abstract: Pretrained language models like BERT and T5 serve as crucial backbone encoders for dense retrieval. However, these models often exhibit limited generalization capabilities and face challenges in improving in domain accuracy. Recent research has explored using large language models (LLMs) as retrievers, achieving SOTA performance across various tasks. Despite these advancements, the specific benefits of LLMs over traditional retrievers and the impact of different LLM configurations, such as parameter sizes, pretraining duration, and alignment processes on retrieval tasks remain unclear. In this work, we conduct a comprehensive empirical study on a wide range of retrieval tasks, including in domain accuracy, data efficiency, zero shot generalization, lengthy retrieval, instruction based retrieval, and multi task learning. We evaluate over 15 different backbone LLMs and non LLMs. Our findings reveal that larger models and extensive pretraining consistently enhance in domain accuracy and data efficiency. Additionally, larger models demonstrate significant potential in zero shot generalization, lengthy retrieval, instruction based retrieval, and multi task learning. These results underscore the advantages of LLMs as versatile and effective backbone encoders in dense retrieval, providing valuable insights for future research and development in this field.
Authors: Nico Daheim, Thomas M\"ollenhoff, Edoardo Maria Ponti, Iryna Gurevych, Mohammad Emtiyaz Khan
Abstract: Models trained on different datasets can be merged by a weighted-averaging of their parameters, but why does it work and when can it fail? Here, we connect the inaccuracy of weighted-averaging to mismatches in the gradients and propose a new uncertainty-based scheme to improve the performance by reducing the mismatch. The connection also reveals implicit assumptions in other schemes such as averaging, task arithmetic, and Fisher-weighted averaging. Our new method gives consistent improvements for large language models and vision transformers, both in terms of performance and robustness to hyperparameters. Code available here.
Authors: Jake Chanenson, Madison Pickering, Noah Apthorpe
Abstract: Identifying contextual integrity (CI) and governing knowledge commons (GKC) parameters in privacy policy texts can facilitate normative privacy analysis. However, GKC-CI annotation has heretofore required manual or crowdsourced effort. This paper demonstrates that high-accuracy GKC-CI parameter annotation of privacy policies can be performed automatically using large language models. We fine-tune 50 open-source and proprietary models on 21,588 GKC-CI annotations from 16 ground truth privacy policies. Our best performing model has an accuracy of 90.65%, which is comparable to the accuracy of experts on the same task. We apply our best performing model to 456 privacy policies from a variety of online services, demonstrating the effectiveness of scaling GKC-CI annotation for privacy policy exploration and analysis. We publicly release our model training code, training and testing data, an annotation visualizer, and all annotated policies for future GKC-CI research.
Authors: Anna C. Doris, Daniele Grandi, Ryan Tomich, Md Ferdous Alam, Mohammadmehdi Ataei, Hyunmin Cheong, Faez Ahmed
Abstract: This research introduces DesignQA, a novel benchmark aimed at evaluating the proficiency of multimodal large language models (MLLMs) in comprehending and applying engineering requirements in technical documentation. Developed with a focus on real-world engineering challenges, DesignQA uniquely combines multimodal data-including textual design requirements, CAD images, and engineering drawings-derived from the Formula SAE student competition. Different from many existing MLLM benchmarks, DesignQA contains document-grounded visual questions where the input image and input document come from different sources. The benchmark features automatic evaluation metrics and is divided into segments-Rule Comprehension, Rule Compliance, and Rule Extraction-based on tasks that engineers perform when designing according to requirements. We evaluate state-of-the-art models (at the time of writing) like GPT-4o, GPT-4, Claude-Opus, Gemini-1.0, and LLaVA-1.5 against the benchmark, and our study uncovers the existing gaps in MLLMs' abilities to interpret complex engineering documentation. The MLLMs tested, while promising, struggle to reliably retrieve relevant rules from the Formula SAE documentation, face challenges in recognizing technical components in CAD images, and encounter difficulty in analyzing engineering drawings. These findings underscore the need for multimodal models that can better handle the multifaceted questions characteristic of design according to technical documentation. This benchmark sets a foundation for future advancements in AI-supported engineering design processes. DesignQA is publicly available at: https://github.com/anniedoris/design_qa/.
Authors: Yizheng Huang, Jimmy Huang
Abstract: Retrieval-Augmented Generation (RAG) merges retrieval methods with deep learning advancements to address the static limitations of large language models (LLMs) by enabling the dynamic integration of up-to-date external information. This methodology, focusing primarily on the text domain, provides a cost-effective solution to the generation of plausible but possibly incorrect responses by LLMs, thereby enhancing the accuracy and reliability of their outputs through the use of real-world data. As RAG grows in complexity and incorporates multiple concepts that can influence its performance, this paper organizes the RAG paradigm into four categories: pre-retrieval, retrieval, post-retrieval, and generation, offering a detailed perspective from the retrieval viewpoint. It outlines RAG's evolution and discusses the field's progression through the analysis of significant studies. Additionally, the paper introduces evaluation methods for RAG, addressing the challenges faced and proposing future research directions. By offering an organized framework and categorization, the study aims to consolidate existing research on RAG, clarify its technological underpinnings, and highlight its potential to broaden the adaptability and applications of LLMs.
Authors: Ciro Beneduce, Bruno Lepri, Massimiliano Luca
Abstract: Predicting the locations an individual will visit in the future is crucial for solving many societal issues like disease diffusion and reduction of pollution. However, next-location predictors require a significant amount of individual-level information that may be scarce or unavailable in some scenarios (e.g., cold-start). Large Language Models (LLMs) have shown good generalization and reasoning capabilities and are rich in geographical knowledge, allowing us to believe that these models can act as zero-shot next-location predictors. We tested more than 15 LLMs on three real-world mobility datasets and we found that LLMs can obtain accuracies up to 36.2%, a significant relative improvement of almost 640% when compared to other models specifically designed for human mobility. We also test for data contamination and explored the possibility of using LLMs as text-based explainers for next-location prediction, showing that, regardless of the model size, LLMs can explain their decision.
Authors: Weijia Zhang, Mohammad Aliannejadi, Yifei Yuan, Jiahuan Pei, Jia-Hong Huang, Evangelos Kanoulas
Abstract: Large language models (LLMs) often produce unsupported or unverifiable content, known as "hallucinations." To mitigate this, retrieval-augmented LLMs incorporate citations, grounding the content in verifiable sources. Despite such developments, manually assessing how well a citation supports the associated statement remains a major challenge. Previous studies use faithfulness metrics to estimate citation support automatically but are limited to binary classification, overlooking fine-grained citation support in practical scenarios. To investigate the effectiveness of faithfulness metrics in fine-grained scenarios, we propose a comparative evaluation framework that assesses the metric effectiveness in distinguishing citations between three-category support levels: full, partial, and no support. Our framework employs correlation analysis, classification evaluation, and retrieval evaluation to measure the alignment between metric scores and human judgments comprehensively. Our results show no single metric consistently excels across all evaluations, revealing the complexity of assessing fine-grained support. Based on the findings, we provide practical recommendations for developing more effective metrics.
Authors: Nikita Dhawan, Leonardo Cotta, Karen Ullrich, Rahul G. Krishnan, Chris J. Maddison
Abstract: Knowing the effect of an intervention is critical for human decision-making, but current approaches for causal effect estimation rely on manual data collection and structuring, regardless of the causal assumptions. This increases both the cost and time-to-completion for studies. We show how large, diverse observational text data can be mined with large language models (LLMs) to produce inexpensive causal effect estimates under appropriate causal assumptions. We introduce NATURAL, a novel family of causal effect estimators built with LLMs that operate over datasets of unstructured text. Our estimators use LLM conditional distributions (over variables of interest, given the text data) to assist in the computation of classical estimators of causal effect. We overcome a number of technical challenges to realize this idea, such as automating data curation and using LLMs to impute missing information. We prepare six (two synthetic and four real) observational datasets, paired with corresponding ground truth in the form of randomized trials, which we used to systematically evaluate each step of our pipeline. NATURAL estimators demonstrate remarkable performance, yielding causal effect estimates that fall within 3 percentage points of their ground truth counterparts, including on real-world Phase 3/4 clinical trials. Our results suggest that unstructured text data is a rich source of causal effect information, and NATURAL is a first step towards an automated pipeline to tap this resource.
Authors: Flora B\"owing, Patrick Gildersleve
Abstract: The disparity between news stories valued by journalists and those preferred by readers, known as the "News Gap", is well-documented. However, the difference in expectations regarding news related user-generated content is less studied. Comment sections, hosted by news websites, are popular venues for reader engagement, yet still subject to editorial decisions. It is thus important to understand journalist vs reader comment preferences and how these are served by various comment ranking algorithms that represent discussions differently. We analyse 1.2 million comments from Austrian newspaper Der Standard to understand the "News Comment Gap" and the effects of different ranking algorithms. We find that journalists prefer positive, timely, complex, direct responses, while readers favour comments similar to article content from elite authors. We introduce the versatile Feature-Oriented Ranking Utility Metric (FORUM) to assess the impact of different ranking algorithms and find dramatic differences in how they prioritise the display of comments by sentiment, topical relevance, lexical diversity, and readability. Journalists can exert substantial influence over the discourse through both curatorial and algorithmic means. Understanding these choices' implications is vital in fostering engaging and civil discussions while aligning with journalistic objectives, especially given the increasing legal scrutiny and societal importance of online discourse.
Authors: Minxuan Zhou, Hao Liang, Tianpeng Li, Zhiyu Wu, Mingan Lin, Linzhuang Sun, Yaqi Zhou, Yan Zhang, Xiaoqin Huang, Yicong Chen, Yujing Qiao, Weipeng Chen, Bin Cui, Wentao Zhang, Zenan Zhou
Abstract: With the development of Multimodal Large Language Models (MLLMs), the evaluation of multimodal models in the context of mathematical problems has become a valuable research field. Multimodal visual-textual mathematical reasoning serves as a critical indicator for evaluating the comprehension and complex multi-step quantitative reasoning abilities of MLLMs. However, previous multimodal math benchmarks have not sufficiently integrated visual and textual information. To address this gap, we proposed MathScape, a new benchmark that emphasizes the understanding and application of combined visual and textual information. MathScape is designed to evaluate photo-based math problem scenarios, assessing the theoretical understanding and application ability of MLLMs through a categorical hierarchical approach. We conduct a multi-dimensional evaluation on 11 advanced MLLMs, revealing that our benchmark is challenging even for the most sophisticated models. By analyzing the evaluation results, we identify the limitations of MLLMs, offering valuable insights for enhancing model performance.
Authors: Khang T. Doan, Bao G. Huynh, Dung T. Hoang, Thuc D. Pham, Nhat H. Pham, Quan T. M. Nguyen, Bang Q. Vo, Suong N. Hoang
Abstract: In this report, we introduce Vintern-1B, a reliable 1-billion-parameters multimodal large language model (MLLM) for Vietnamese language tasks. By integrating the Qwen2-0.5B-Instruct language model with the InternViT-300M-448px visual model, Vintern-1B is optimized for a range of applications, including optical character recognition (OCR), document extraction, and general question-answering in Vietnamese context. The model is fine-tuned on an extensive dataset of over 3 million image-question-answer pairs, achieving robust performance and reliable results across multiple Vietnamese language benchmarks like OpenViVQA and ViTextVQA. Vintern-1B is small enough to fit into various on-device applications easily. Additionally, we have open-sourced several Vietnamese vision question answering (VQA) datasets for text and diagrams, created with Gemini 1.5 Flash. Our models are available at: https://huggingface.co/5CD-AI/Vintern-1B-v2.