Authors: Todd Morrill, Zhaoyuan Deng, Yanda Chen, Amith Ananthram, Colin Wayne Leach, Kathleen McKeown
Abstract: There are many settings where it is useful to predict and explain the success or failure of a dialogue. Circumplex theory from psychology models the social orientations (e.g., Warm-Agreeable, Arrogant-Calculating) of conversation participants and can be used to predict and explain the outcome of social interactions. Our work is novel in its systematic application of social orientation tags to modeling conversation outcomes. In this paper, we introduce a new data set of dialogue utterances machine-labeled with social orientation tags. We show that social orientation tags improve task performance, especially in low-resource settings, on both English and Chinese language benchmarks. We also demonstrate how social orientation tags help explain the outcomes of social interactions when used in neural models. Based on these results showing the utility of social orientation tags for dialogue outcome prediction tasks, we release our data sets, code, and models that are fine-tuned to predict social orientation tags on dialogue utterances.
Authors: Lin Ai, Zheng Hui, Zizhou Liu, Julia Hirschberg
Abstract: To address the challenges of out-of-control generation in generative models for machine reading comprehension (MRC), we introduce the Question-Attended Span Extraction (QASE) module. Integrated during the fine-tuning of pre-trained generative language models (PLMs), QASE enables these PLMs to match SOTA extractive methods and outperform leading LLMs like GPT-4 in MRC tasks, without significant increases in computational costs.
Authors: Yanchao Tan, Hang Lv, Xinyi Huang, Jiawei Zhang, Shiping Wang, Carl Yang
Abstract: Graphs with abundant attributes are essential in modeling interconnected entities and improving predictions in various real-world applications. Traditional Graph Neural Networks (GNNs), which are commonly used for modeling attributed graphs, need to be re-trained every time when applied to different graph tasks and datasets. Although the emergence of Large Language Models (LLMs) has introduced a new paradigm in natural language processing, the generative potential of LLMs in graph mining remains largely under-explored. To this end, we propose a novel framework MuseGraph, which seamlessly integrates the strengths of GNNs and LLMs and facilitates a more effective and generic approach for graph mining across different tasks and datasets. Specifically, we first introduce a compact graph description via the proposed adaptive input generation to encapsulate key information from the graph under the constraints of language token limitations. Then, we propose a diverse instruction generation mechanism, which distills the reasoning capabilities from LLMs (e.g., GPT-4) to create task-specific Chain-of-Thought-based instruction packages for different graph tasks. Finally, we propose a graph-aware instruction tuning with a dynamic instruction package allocation strategy across tasks and datasets, ensuring the effectiveness and generalization of the training process. Our experimental results demonstrate significant improvements in different graph tasks, showcasing the potential of our MuseGraph in enhancing the accuracy of graph-oriented downstream tasks while keeping the generation powers of LLMs.
Authors: Li Cai, Xin Mao, Yuhao Zhou, Zhaoguang Long, Changxu Wu, Man Lan
Abstract: Knowledge graphs have garnered significant research attention and are widely used to enhance downstream applications. However, most current studies mainly focus on static knowledge graphs, whose facts do not change with time, and disregard their dynamic evolution over time. As a result, temporal knowledge graphs have attracted more attention because a large amount of structured knowledge exists only within a specific period. Knowledge graph representation learning aims to learn low-dimensional vector embeddings for entities and relations in a knowledge graph. The representation learning of temporal knowledge graphs incorporates time information into the standard knowledge graph framework and can model the dynamics of entities and relations over time. In this paper, we conduct a comprehensive survey of temporal knowledge graph representation learning and its applications. We begin with an introduction to the definitions, datasets, and evaluation metrics for temporal knowledge graph representation learning. Next, we propose a taxonomy based on the core technologies of temporal knowledge graph representation learning methods, and provide an in-depth analysis of different methods in each category. Finally, we present various downstream applications related to the temporal knowledge graphs. In the end, we conclude the paper and have an outlook on the future research directions in this area.
Authors: Jun-En Ding, Phan Nguyen Minh Thao, Wen-Chih Peng, Jian-Zhe Wang, Chun-Cheng Chug, Min-Chen Hsieh, Yun-Chien Tseng, Ling Chen, Dongsheng Luo, Chi-Te Wang, Pei-fu Chen, Feng Liu, Fang-Ming Hung
Abstract: Chronic diseases such as diabetes are the leading causes of morbidity and mortality worldwide. Numerous research studies have been attempted with various deep learning models in diagnosis. However, most previous studies had certain limitations, including using publicly available datasets (e.g. MIMIC), and imbalanced data. In this study, we collected five-year electronic health records (EHRs) from the Taiwan hospital database, including 1,420,596 clinical notes, 387,392 laboratory test results, and more than 1,505 laboratory test items, focusing on research pre-training large language models. We proposed a novel Large Language Multimodal Models (LLMMs) framework incorporating multimodal data from clinical notes and laboratory test results for the prediction of chronic disease risk. Our method combined a text embedding encoder and multi-head attention layer to learn laboratory test values, utilizing a deep neural network (DNN) module to merge blood features with chronic disease semantics into a latent space. In our experiments, we observe that clinicalBERT and PubMed-BERT, when combined with attention fusion, can achieve an accuracy of 73% in multiclass chronic diseases and diabetes prediction. By transforming laboratory test values into textual descriptions and employing the Flan T-5 model, we achieved a 76% Area Under the ROC Curve (AUROC), demonstrating the effectiveness of leveraging numerical text data for training and inference in language models. This approach significantly improves the accuracy of early-stage diabetes prediction.
Authors: Seo Hyun Kim, Keummin Ka, Yohan Jo, Seung-won Hwang, Dongha Lee, Jinyoung Yeo
Abstract: For a human-like chatbot, constructing a long-term memory is crucial. A naive approach for making a memory could be simply listing the summarized dialogue. However, this can lead to problems when the speaker's status change over time and contradictory information gets accumulated. It is important that the memory stays organized to lower the confusion for the response generator. In this paper, we propose a novel memory scheme for long-term conversation, CREEM. Unlike existing approaches that construct memory based solely on current sessions, our proposed model blending past memories during memory formation. Additionally, we introduce refining process to handle redundant or outdated information. This innovative approach seeks for overall improvement and coherence of chatbot responses by ensuring a more informed and dynamically evolving long-term memory.
Authors: Aziida Nanyonga, Hassan Wasswa, Graham Wild
Abstract: Aviation safety is paramount in the modern world, with a continuous commitment to reducing accidents and improving safety standards. Central to this endeavor is the analysis of aviation accident reports, rich textual resources that hold insights into the causes and contributing factors behind aviation mishaps. This paper compares two prominent topic modeling techniques, Latent Dirichlet Allocation (LDA) and Non-negative Matrix Factorization (NMF), in the context of aviation accident report analysis. The study leverages the National Transportation Safety Board (NTSB) Dataset with the primary objective of automating and streamlining the process of identifying latent themes and patterns within accident reports. The Coherence Value (C_v) metric was used to evaluate the quality of generated topics. LDA demonstrates higher topic coherence, indicating stronger semantic relevance among words within topics. At the same time, NMF excelled in producing distinct and granular topics, enabling a more focused analysis of specific aspects of aviation accidents.
Authors: Jiamin Luo, Jingjing Wang, Guodong Zhou
Abstract: Multimodal Conversational Emotion (MCE) detection, generally spanning across the acoustic, vision and language modalities, has attracted increasing interest in the multimedia community. Previous studies predominantly focus on learning contextual information in conversations with only a few considering the topic information in single language modality, while always neglecting the acoustic and vision topic information. On this basis, we propose a model-agnostic Topic-enriched Diffusion (TopicDiff) approach for capturing multimodal topic information in MCE tasks. Particularly, we integrate the diffusion model into neural topic model to alleviate the diversity deficiency problem of neural topic model in capturing topic information. Detailed evaluations demonstrate the significant improvements of TopicDiff over the state-of-the-art MCE baselines, justifying the importance of multimodal topic information to MCE and the effectiveness of TopicDiff in capturing such information. Furthermore, we observe an interesting finding that the topic information in acoustic and vision is more discriminative and robust compared to the language.
Authors: Juhao Liang, Ziwei Wang, Zhuoheng Ma, Jianquan Li, Zhiyi Zhang, Xiangbo Wu, Benyou Wang
Abstract: Large Language Models(LLMs) have dramatically revolutionized the field of Natural Language Processing(NLP), offering remarkable capabilities that have garnered widespread usage. However, existing interaction paradigms between LLMs and users are constrained by either inflexibility, limitations in customization, or a lack of persistent learning. This inflexibility is particularly evident as users, especially those without programming skills, have restricted avenues to enhance or personalize the model. Existing frameworks further complicate the model training and deployment process due to their computational inefficiencies and lack of user-friendly interfaces. To overcome these challenges, this paper introduces a novel interaction paradigm-'Online Training using External Interactions'-that merges the benefits of persistent, real-time model updates with the flexibility for individual customization through external interactions such as AI agents or online/offline knowledge bases.
Authors: Ahmed Izzidien, Holli Sargeant, Felix Steffek
Abstract: To undertake computational research of the law, efficiently identifying datasets of court decisions that relate to a specific legal issue is a crucial yet challenging endeavour. This study addresses the gap in the literature working with large legal corpora about how to isolate cases, in our case summary judgments, from a large corpus of UK court decisions. We introduce a comparative analysis of two computational methods: (1) a traditional natural language processing-based approach leveraging expert-generated keywords and logical operators and (2) an innovative application of the Claude 2 large language model to classify cases based on content-specific prompts. We use the Cambridge Law Corpus of 356,011 UK court decisions and determine that the large language model achieves a weighted F1 score of 0.94 versus 0.78 for keywords. Despite iterative refinement, the search logic based on keywords fails to capture nuances in legal language. We identify and extract 3,102 summary judgment cases, enabling us to map their distribution across various UK courts over a temporal span. The paper marks a pioneering step in employing advanced natural language processing to tackle core legal research tasks, demonstrating how these technologies can bridge systemic gaps and enhance the accessibility of legal information. We share the extracted dataset metrics to support further research on summary judgments.
Authors: Yotam Intrator, Matan Halfon, Roman Goldenberg, Reut Tsarfaty, Matan Eyal, Ehud Rivlin, Yossi Matias, Natalia Aizenberg
Abstract: Large language models hold significant promise in multilingual applications. However, inherent biases stemming from predominantly English-centric pre-training have led to the widespread practice of pre-translation, i.e., translating non-English inputs to English before inference, leading to complexity and information loss. This study re-evaluates the need for pre-translation in the context of PaLM2 models (Anil et al., 2023), which have been established as highly performant in multilingual tasks. We offer a comprehensive investigation across 108 languages and 6 diverse benchmarks, including open-end generative tasks, which were excluded from previous similar studies. Our findings challenge the pre-translation paradigm established in prior research, highlighting the advantages of direct inference in PaLM2. Specifically, PaLM2-L consistently outperforms pre-translation in 94 out of 108 languages. These findings pave the way for more efficient and effective multilingual applications, alleviating the limitations associated with pre-translation and unlocking linguistic authenticity.
Authors: Haley Hostetter, M. Z. Naser, Xinyan Huang, John Gales
Abstract: This communication presents preliminary findings from comparing two recent chatbots, OpenAI's ChatGPT and Google's Bard, in the context of fire engineering by evaluating their responses in handling fire safety related queries. A diverse range of fire engineering questions and scenarios were created and examined, including structural fire design, fire prevention strategies, evacuation, building code compliance, and fire suppression systems (some of which resemble those commonly present in the Fire Protection exam (FPE)). The results reveal some key differences in the performance of the chatbots, with ChatGPT demonstrating a relatively superior performance. Then, this communication highlights the potential for chatbot technology to revolutionize fire engineering practices by providing instant access to critical information while outlining areas for further improvement and research. Evidently, and when it matures, this technology will likely be elemental to our engineers' practice and education.
Authors: Zhenyu Zhang, Runjin Chen, Shiwei Liu, Zhewei Yao, Olatunji Ruwase, Beidi Chen, Xiaoxia Wu, Zhangyang Wang
Abstract: This paper aims to overcome the "lost-in-the-middle" challenge of large language models (LLMs). While recent advancements have successfully enabled LLMs to perform stable language modeling with up to 4 million tokens, the persistent difficulty faced by most LLMs in identifying relevant information situated in the middle of the context has not been adequately tackled. To address this problem, this paper introduces Multi-scale Positional Encoding (Ms-PoE) which is a simple yet effective plug-and-play approach to enhance the capacity of LLMs to handle the relevant information located in the middle of the context, without fine-tuning or introducing any additional overhead. Ms-PoE leverages the position indice rescaling to relieve the long-term decay effect introduced by RoPE, while meticulously assigning distinct scaling ratios to different attention heads to preserve essential knowledge learned during the pre-training step, forming a multi-scale context fusion from short to long distance. Extensive experiments with a wide range of LLMs demonstrate the efficacy of our approach. Notably, Ms-PoE achieves an average accuracy gain of up to 3.8 on the Zero-SCROLLS benchmark over the original LLMs. Code are available at https://github.com/VITA-Group/Ms-PoE.
Authors: Arefa, Mohammed Abbas Ansari, Chandni Saxena, Tanvir Ahmad
Abstract: This paper presents our system development for SemEval-2024 Task 3: "The Competition of Multimodal Emotion Cause Analysis in Conversations". Effectively capturing emotions in human conversations requires integrating multiple modalities such as text, audio, and video. However, the complexities of these diverse modalities pose challenges for developing an efficient multimodal emotion cause analysis (ECA) system. Our proposed approach addresses these challenges by a two-step framework. We adopt two different approaches in our implementation. In Approach 1, we employ instruction-tuning with two separate Llama 2 models for emotion and cause prediction. In Approach 2, we use GPT-4V for conversation-level video description and employ in-context learning with annotated conversation using GPT 3.5. Our system wins rank 4, and system ablation experiments demonstrate that our proposed solutions achieve significant performance gains. All the experimental codes are available on Github.
Authors: Wuraola Oyewusi
Abstract: To effectively navigate the AI revolution, AI literacy is crucial. However, content predominantly exists in dominant languages, creating a gap for low-resource languages like Yoruba (41 million native speakers). This case study explores bridging this gap by creating and distributing AI videos in Yoruba.The project developed 26 videos covering foundational, intermediate, and advanced AI concepts, leveraging storytelling and accessible explanations. These videos were created using a cost-effective methodology and distributed across YouTube, LinkedIn, and Twitter, reaching an estimated global audience of 22 countries. Analysis of YouTube reveals insights into viewing patterns, with the 25-44 age group contributing the most views. Notably, over half of the traffic originated from external sources, highlighting the potential of cross-platform promotion.This study demonstrates the feasibility and impact of creating AI literacy content in low-resource languages. It emphasizes that accurate interpretation requires both technical expertise in AI and fluency in the target language. This work contributes a replicable methodology, a 22-word Yoruba AI vocabulary, and data-driven insights into audience demographics and acquisition channel
Authors: Aly M. Kassem, Omar Mahmoud, Niloofar Mireshghallah, Hyunwoo Kim, Yulia Tsvetkov, Yejin Choi, Sherif Saad, Santu Rana
Abstract: In this paper, we introduce a black-box prompt optimization method that uses an attacker LLM agent to uncover higher levels of memorization in a victim agent, compared to what is revealed by prompting the target model with the training data directly, which is the dominant approach of quantifying memorization in LLMs. We use an iterative rejection-sampling optimization process to find instruction-based prompts with two main characteristics: (1) minimal overlap with the training data to avoid presenting the solution directly to the model, and (2) maximal overlap between the victim model's output and the training data, aiming to induce the victim to spit out training data. We observe that our instruction-based prompts generate outputs with 23.7% higher overlap with training data compared to the baseline prefix-suffix measurements. Our findings show that (1) instruction-tuned models can expose pre-training data as much as their base-models, if not more so, (2) contexts other than the original training data can lead to leakage, and (3) using instructions proposed by other LLMs can open a new avenue of automated attacks that we should further study and explore. The code can be found at https://github.com/Alymostafa/Instruction_based_attack .
URLs: https://github.com/Alymostafa/Instruction_based_attack
Authors: Linyuan Gong, Sida Wang, Mostafa Elhoushi, Alvin Cheung
Abstract: We introduce Syntax-Aware Fill-In-the-Middle (SAFIM), a new benchmark for evaluating Large Language Models (LLMs) on the code Fill-in-the-Middle (FIM) task. This benchmark focuses on syntax-aware completions of program structures such as code blocks and conditional expressions, and includes 17,720 examples from multiple programming languages, sourced from recent code submissions after April 2022 to minimize data contamination. SAFIM provides a robust framework with various prompt designs and novel syntax-aware post-processing techniques, facilitating accurate and fair comparisons across LLMs. Our comprehensive evaluation of 15 LLMs shows that FIM pretraining not only enhances FIM proficiency but also improves Left-to-Right (L2R) inference using LLMs. Our findings challenge conventional beliefs and suggest that pretraining methods and data quality have more impact than model size. SAFIM thus serves as a foundational platform for future research in effective pretraining strategies for code LLMs. The evaluation toolkit and dataset are available at https://github.com/gonglinyuan/safim, and the leaderboard is available at https://safimbenchmark.com.
URLs: https://github.com/gonglinyuan/safim,, https://safimbenchmark.com.
Authors: Angelina Parfenova
Abstract: This paper explores the development and application of an automated system designed to extract information from semi-structured interview transcripts. Given the labor-intensive nature of traditional qualitative analysis methods, such as coding, there exists a significant demand for tools that can facilitate the analysis process. Our research investigates various topic modeling techniques and concludes that the best model for analyzing interview texts is a combination of BERT embeddings and HDBSCAN clustering. We present a user-friendly software prototype that enables researchers, including those without programming skills, to efficiently process and visualize the thematic structure of interview data. This tool not only facilitates the initial stages of qualitative analysis but also offers insights into the interconnectedness of topics revealed, thereby enhancing the depth of qualitative analysis.
Authors: Sharon Levy, Tahilin Sanchez Karver, William D. Adler, Michelle R. Kaufman, Mark Dredze
Abstract: Chat-based large language models have the opportunity to empower individuals lacking high-quality healthcare access to receive personalized information across a variety of topics. However, users may ask underspecified questions that require additional context for a model to correctly answer. We study how large language model biases are exhibited through these contextual questions in the healthcare domain. To accomplish this, we curate a dataset of sexual and reproductive healthcare questions that are dependent on age, sex, and location attributes. We compare models' outputs with and without demographic context to determine group alignment among our contextual questions. Our experiments reveal biases in each of these attributes, where young adult female users are favored.
Authors: Frances A. Laureano De Leon, Harish Tayyar Madabushi, Mark Lee
Abstract: Code-switching is a prevalent linguistic phenomenon in which multilingual individuals seamlessly alternate between languages. Despite its widespread use online and recent research trends in this area, research in code-switching presents unique challenges, primarily stemming from the scarcity of labelled data and available resources. In this study we investigate how pre-trained Language Models handle code-switched text in three dimensions: a) the ability of PLMs to detect code-switched text, b) variations in the structural information that PLMs utilise to capture code-switched text, and c) the consistency of semantic information representation in code-switched text. To conduct a systematic and controlled evaluation of the language models in question, we create a novel dataset of well-formed naturalistic code-switched text along with parallel translations into the source languages. Our findings reveal that pre-trained language models are effective in generalising to code-switched text, shedding light on the abilities of these models to generalise representations to CS corpora. We release all our code and data including the novel corpus at https://github.com/francesita/code-mixed-probes.
Authors: Ojas Gramopadhye, Saeel Sandeep Nachane, Prateek Chanda, Ganesh Ramakrishnan, Kshitij Sharad Jadhav, Yatin Nandwani, Dinesh Raghu, Sachindra Joshi
Abstract: Large Language models (LLMs) have demonstrated significant potential in transforming healthcare by automating tasks such as clinical documentation, information retrieval, and decision support. In this aspect, carefully engineered prompts have emerged as a powerful tool for using LLMs for medical scenarios, e.g., patient clinical scenarios. In this paper, we propose a modified version of the MedQA-USMLE dataset, which is subjective, to mimic real-life clinical scenarios. We explore the Chain of Thought (CoT) reasoning based on subjective response generation for the modified MedQA-USMLE dataset with appropriate LM-driven forward reasoning for correct responses to the medical questions. Keeping in mind the importance of response verification in the medical setting, we utilize a reward training mechanism whereby the language model also provides an appropriate verified response for a particular response to a clinical question. In this regard, we also include human-in-the-loop for different evaluation aspects. We develop better in-contrast learning strategies by modifying the 5-shot-codex-CoT-prompt from arXiv:2207.08143 for the subjective MedQA dataset and developing our incremental-reasoning prompt. Our evaluations show that the incremental reasoning prompt performs better than the modified codex prompt in certain scenarios. We also show that greedy decoding with the incremental reasoning method performs better than other strategies, such as prompt chaining and eliminative reasoning.
Authors: Savvas Petridis, Ben Wedin, Ann Yuan, James Wexler, Nithum Thain
Abstract: Large language models (LLMs) are highly capable at a variety of tasks given the right prompt, but writing one is still a difficult and tedious process. In this work, we introduce ConstitutionalExperts, a method for learning a prompt consisting of constitutional principles (i.e. rules), given a training dataset. Unlike prior methods that optimize the prompt as a single entity, our method incrementally improves the prompt by surgically editing individual principles. We also show that we can improve overall performance by learning unique prompts for different semantic regions of the training data and using a mixture-of-experts (MoE) architecture to route inputs at inference time. We compare our method to other state of the art prompt-optimization techniques across six benchmark datasets. We also investigate whether MoE improves these other techniques. Our results suggest that ConstitutionalExperts outperforms other prompt optimization techniques by 10.9% (F1) and that mixture-of-experts improves all techniques, suggesting its broad applicability.
Authors: Zhongwei Wan, Che Liu, Xin Wang, Chaofan Tao, Hui Shen, Zhenwu Peng, Jie Fu, Rossella Arcucci, Huaxiu Yao, Mi Zhang
Abstract: Electrocardiogram (ECG) serves as the primary non-invasive diagnostic tool for cardiac conditions monitoring, are crucial in assisting clinicians. Recent studies have concentrated on classifying cardiac conditions using ECG data but have overlooked ECG report generation, which is not only time-consuming but also requires clinical expertise. To automate ECG report generation and ensure its versatility, we propose the Multimodal ECG Instruction Tuning (MEIT) framework, the \textit{first} attempt to tackle ECG report generation with LLMs and multimodal instructions. To facilitate future research, we establish a benchmark to evaluate MEIT with various LLMs backbones across two large-scale ECG datasets. Our approach uniquely aligns the representations of the ECG signal and the report, and we conduct extensive experiments to benchmark MEIT with nine open source LLMs, using more than 800,000 ECG reports. MEIT's results underscore the superior performance of instruction-tuned LLMs, showcasing their proficiency in quality report generation, zero-shot capabilities, and resilience to signal perturbation. These findings emphasize the efficacy of our MEIT framework and its potential for real-world clinical application.
Authors: Xuanxin Wu, Yuki Arase
Abstract: Sentence simplification, which rewrites a sentence to be easier to read and understand, is a promising technique to help people with various reading difficulties. With the rise of advanced large language models (LLMs), evaluating their performance in sentence simplification has become imperative. Recent studies have used both automatic metrics and human evaluations to assess the simplification abilities of LLMs. However, the suitability of existing evaluation methodologies for LLMs remains in question. First, the suitability of current automatic metrics on LLMs' simplification evaluation is still uncertain. Second, current human evaluation approaches in sentence simplification often fall into two extremes: they are either too superficial, failing to offer a clear understanding of the models' performance, or overly detailed, making the annotation process complex and prone to inconsistency, which in turn affects the evaluation's reliability. To address these problems, this study provides in-depth insights into LLMs' performance while ensuring the reliability of the evaluation. We design an error-based human annotation framework to assess the GPT-4's simplification capabilities. Results show that GPT-4 generally generates fewer erroneous simplification outputs compared to the current state-of-the-art. However, LLMs have their limitations, as seen in GPT-4's struggles with lexical paraphrasing. Furthermore, we conduct meta-evaluations on widely used automatic metrics using our human annotations. We find that while these metrics are effective for significant quality differences, they lack sufficient sensitivity to assess the overall high-quality simplification by GPT-4.
Authors: Jiapeng Wang, Chengyu Wang, Tingfeng Cao, Jun Huang, Lianwen Jin
Abstract: We present DiffChat, a novel method to align Large Language Models (LLMs) to "chat" with prompt-as-input Text-to-Image Synthesis (TIS) models (e.g., Stable Diffusion) for interactive image creation. Given a raw prompt/image and a user-specified instruction, DiffChat can effectively make appropriate modifications and generate the target prompt, which can be leveraged to create the target image of high quality. To achieve this, we first collect an instruction-following prompt engineering dataset named InstructPE for the supervised training of DiffChat. Next, we propose a reinforcement learning framework with the feedback of three core criteria for image creation, i.e., aesthetics, user preference, and content integrity. It involves an action-space dynamic modification technique to obtain more relevant positive samples and harder negative samples during the off-policy sampling. Content integrity is also introduced into the value estimation function for further improvement of produced images. Our method can exhibit superior performance than baseline models and strong competitors based on both automatic and human evaluations, which fully demonstrates its effectiveness.
Authors: Devanshu Agrawal, Shang Gao, Martin Gajek
Abstract: Long-context large language models (LLMs) hold promise for tasks such as question-answering (QA) over long documents, but they tend to miss important information in the middle of context documents (arXiv:2307.03172v3). Here, we introduce $\textit{R&R}$ -- a combination of two novel prompt-based methods called $\textit{reprompting}$ and $\textit{in-context retrieval}$ (ICR) -- to alleviate this effect in document-based QA. In reprompting, we repeat the prompt instructions periodically throughout the context document to remind the LLM of its original task. In ICR, rather than instructing the LLM to answer the question directly, we instruct it to retrieve the top $k$ passage numbers most relevant to the given question, which are then used as an abbreviated context in a second QA prompt. We test R&R with GPT-4 Turbo and Claude-2.1 on documents up to 80k tokens in length and observe a 16-point boost in QA accuracy on average. Our further analysis suggests that R&R improves performance on long document-based QA because it reduces the distance between relevant context and the instructions. Finally, we show that compared to short-context chunkwise methods, R&R enables the use of larger chunks that cost fewer LLM calls and output tokens, while minimizing the drop in accuracy.
Authors: Xuhui Zhou, Zhe Su, Tiwalayo Eisape, Hyunwoo Kim, Maarten Sap
Abstract: Recent advances in large language models (LLM) have enabled richer social simulations, allowing for the study of various social phenomena with LLM-based agents. However, most work has used an omniscient perspective on these simulations (e.g., single LLM to generate all interlocutors), which is fundamentally at odds with the non-omniscient, information asymmetric interactions that humans have. To examine these differences, we develop an evaluation framework to simulate social interactions with LLMs in various settings (omniscient, non-omniscient). Our experiments show that interlocutors simulated omnisciently are much more successful at accomplishing social goals compared to non-omniscient agents, despite the latter being the more realistic setting. Furthermore, we demonstrate that learning from omniscient simulations improves the apparent naturalness of interactions but scarcely enhances goal achievement in cooperative scenarios. Our findings indicate that addressing information asymmetry remains a fundamental challenge for LLM-based agents.
Authors: Dingkang Yang, Mingcheng Li, Dongling Xiao, Yang Liu, Kun Yang, Zhaoyu Chen, Yuzheng Wang, Peng Zhai, Ke Li, Lihua Zhang
Abstract: Multimodal Sentiment Analysis (MSA) aims to understand human intentions by integrating emotion-related clues from diverse modalities, such as visual, language, and audio. Unfortunately, the current MSA task invariably suffers from unplanned dataset biases, particularly multimodal utterance-level label bias and word-level context bias. These harmful biases potentially mislead models to focus on statistical shortcuts and spurious correlations, causing severe performance bottlenecks. To alleviate these issues, we present a Multimodal Counterfactual Inference Sentiment (MCIS) analysis framework based on causality rather than conventional likelihood. Concretely, we first formulate a causal graph to discover harmful biases from already-trained vanilla models. In the inference phase, given a factual multimodal input, MCIS imagines two counterfactual scenarios to purify and mitigate these biases. Then, MCIS can make unbiased decisions from biased observations by comparing factual and counterfactual outcomes. We conduct extensive experiments on several standard MSA benchmarks. Qualitative and quantitative results show the effectiveness of the proposed framework.
Authors: Toshish Jawale, Chaitanya Animesh, Sekhar Vallath, Kartik Talamadupula, Larry Heck
Abstract: This study analyzes changes in the attention mechanisms of large language models (LLMs) when used to understand natural conversations between humans (human-human). We analyze three use cases of LLMs: interactions over web content, code, and mathematical texts. By analyzing attention distance, dispersion, and interdependency across these domains, we highlight the unique challenges posed by conversational data. Notably, conversations require nuanced handling of long-term contextual relationships and exhibit higher complexity through their attention patterns. Our findings reveal that while language models exhibit domain-specific attention behaviors, there is a significant gap in their ability to specialize in human conversations. Through detailed attention entropy analysis and t-SNE visualizations, we demonstrate the need for models trained with a diverse array of high-quality conversational data to enhance understanding and generation of human-like dialogue. This research highlights the importance of domain specialization in language models and suggests pathways for future advancement in modeling human conversational nuances.
Authors: Aru Maekawa, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura
Abstract: Recently, decoder-only pre-trained large language models (LLMs), with several tens of billion parameters, have significantly impacted a wide range of natural language processing (NLP) tasks. While encoder-only or encoder-decoder pre-trained language models have already proved to be effective in discourse parsing, the extent to which LLMs can perform this task remains an open research question. Therefore, this paper explores how beneficial such LLMs are for Rhetorical Structure Theory (RST) discourse parsing. Here, the parsing process for both fundamental top-down and bottom-up strategies is converted into prompts, which LLMs can work with. We employ Llama 2 and fine-tune it with QLoRA, which has fewer parameters that can be tuned. Experimental results on three benchmark datasets, RST-DT, Instr-DT, and the GUM corpus, demonstrate that Llama 2 with 70 billion parameters in the bottom-up strategy obtained state-of-the-art (SOTA) results with significant differences. Furthermore, our parsers demonstrated generalizability when evaluated on RST-DT, showing that, in spite of being trained with the GUM corpus, it obtained similar performances to those of existing parsers trained with RST-DT.
Authors: Ning Xu, Tingting Zhang, Hongshuo Tian, Yongdong Zhang, An-An Liu
Abstract: News captioning task aims to generate sentences by describing named entities or concrete events for an image with its news article. Existing methods have achieved remarkable results by relying on the large-scale pre-trained models, which primarily focus on the correlations between the input news content and the output predictions. However, the news captioning requires adhering to some fundamental rules of news reporting, such as accurately describing the individuals and actions associated with the event. In this paper, we propose the rule-driven news captioning method, which can generate image descriptions following designated rule signal. Specifically, we first design the news-aware semantic rule for the descriptions. This rule incorporates the primary action depicted in the image (e.g., "performing") and the roles played by named entities involved in the action (e.g., "Agent" and "Place"). Second, we inject this semantic rule into the large-scale pre-trained model, BART, with the prefix-tuning strategy, where multiple encoder layers are embedded with news-aware semantic rule. Finally, we can effectively guide BART to generate news sentences that comply with the designated rule. Extensive experiments on two widely used datasets (i.e., GoodNews and NYTimes800k) demonstrate the effectiveness of our method.
Authors: Jun Xu, Mengshu Sun, Zhiqiang Zhang, Jun Zhou
Abstract: Recent advancements in large language models have shown impressive performance in general chat. However, their domain-specific capabilities, particularly in information extraction, have certain limitations. Extracting structured information from natural language that deviates from known schemas or instructions has proven challenging for previous prompt-based methods. This motivated us to explore domain-specific modeling in chat-based language models as a solution for extracting structured information from natural language. In this paper, we present ChatUIE, an innovative unified information extraction framework built upon ChatGLM. Simultaneously, reinforcement learning is employed to improve and align various tasks that involve confusing and limited samples. Furthermore, we integrate generation constraints to address the issue of generating elements that are not present in the input. Our experimental results demonstrate that ChatUIE can significantly improve the performance of information extraction with a slight decrease in chatting ability.
Authors: Markus Huff, Elanur Ulak\c{c}{\i}
Abstract: Large language models (LLMs) are demonstrating remarkable capabilities across various tasks despite lacking a foundation in human cognition. This raises the question: can these models, beyond simply mimicking human language patterns, offer insights into the mechanisms underlying human cognition? This study explores the ability of ChatGPT to predict human performance in a language-based memory task. Building upon theories of text comprehension, we hypothesize that recognizing ambiguous sentences (e.g., "Because Bill drinks wine is never kept in the house") is facilitated by preceding them with contextually relevant information. Participants, both human and ChatGPT, were presented with pairs of sentences. The second sentence was always a garden-path sentence designed to be inherently ambiguous, while the first sentence either provided a fitting (e.g., "Bill has chronic alcoholism") or an unfitting context (e.g., "Bill likes to play golf"). We measured both human's and ChatGPT's ratings of sentence relatedness, ChatGPT's memorability ratings for the garden-path sentences, and humans' spontaneous memory for the garden-path sentences. The results revealed a striking alignment between ChatGPT's assessments and human performance. Sentences deemed more related and assessed as being more memorable by ChatGPT were indeed better remembered by humans, even though ChatGPT's internal mechanisms likely differ significantly from human cognition. This finding, which was confirmed with a robustness check employing synonyms, underscores the potential of generative AI models to predict human performance accurately. We discuss the broader implications of these findings for leveraging LLMs in the development of psychological theories and for gaining a deeper understanding of human cognition.
Authors: Sotaro Takeshita, Simone Paolo Ponzetto, Kai Eckert
Abstract: Keywords, that is, content-relevant words in summaries play an important role in efficient information conveyance, making it critical to assess if system-generated summaries contain such informative words during evaluation. However, existing evaluation metrics for extreme summarization models do not pay explicit attention to keywords in summaries, leaving developers ignorant of their presence. To address this issue, we present a keyword-oriented evaluation metric, dubbed ROUGE-K, which provides a quantitative answer to the question of -- \textit{How well do summaries include keywords?} Through the lens of this keyword-aware metric, we surprisingly find that a current strong baseline model often misses essential information in their summaries. Our analysis reveals that human annotators indeed find the summaries with more keywords to be more relevant to the source documents. This is an important yet previously overlooked aspect in evaluating summarization systems. Finally, to enhance keyword inclusion, we propose four approaches for incorporating word importance into a transformer-based model and experimentally show that it enables guiding models to include more keywords while keeping the overall quality. Our code is released at https://github.com/sobamchan/rougek.
Authors: Maximilian Schall, Tamara Czinczoll, Gerard de Melo
Abstract: Writing commit messages is a tedious daily task for many software developers, and often remains neglected. Automating this task has the potential to save time while ensuring that messages are informative. A high-quality dataset and an objective benchmark are vital preconditions for solid research and evaluation towards this goal. We show that existing datasets exhibit various problems, such as the quality of the commit selection, small sample sizes, duplicates, privacy issues, and missing licenses for redistribution. This can lead to unusable models and skewed evaluations, where inferior models achieve higher evaluation scores due to biases in the data. We compile a new large-scale dataset, CommitBench, adopting best practices for dataset creation. We sample commits from diverse projects with licenses that permit redistribution and apply our filtering and dataset enhancements to improve the quality of generated commit messages. We use CommitBench to compare existing models and show that other approaches are outperformed by a Transformer model pretrained on source code. We hope to accelerate future research by publishing the source code( https://github.com/Maxscha/commitbench ).
Authors: Xin Zhao, Naoki Yoshinaga, Daisuke Oba
Abstract: Acquiring factual knowledge for language models (LMs) in low-resource languages poses a serious challenge, thus resorting to cross-lingual transfer in multilingual LMs (ML-LMs). In this study, we ask how ML-LMs acquire and represent factual knowledge. Using the multilingual factual knowledge probing dataset, mLAMA, we first conducted a neuron investigation of ML-LMs (specifically, multilingual BERT). We then traced the roots of facts back to the knowledge source (Wikipedia) to identify the ways in which ML-LMs acquire specific facts. We finally identified three patterns of acquiring and representing facts in ML-LMs: language-independent, cross-lingual shared and transferred, and devised methods for differentiating them. Our findings highlight the challenge of maintaining consistent factual knowledge across languages, underscoring the need for better fact representation learning in ML-LMs.
Authors: Parisa Jamadi Khiabani, Arkaitz Zubiaga
Abstract: Stance detection, as the task of determining the viewpoint of a social media post towards a target as 'favor' or 'against', has been understudied in the challenging yet realistic scenario where there is limited labeled data for a certain target. Our work advances research in few-shot stance detection by introducing SocialPET, a socially informed approach to leveraging language models for the task. Our proposed approach builds on the Pattern Exploiting Training (PET) technique, which addresses classification tasks as cloze questions through the use of language models. To enhance the approach with social awareness, we exploit the social network structure surrounding social media posts. We prove the effectiveness of SocialPET on two stance datasets, Multi-target and P-Stance, outperforming competitive stance detection models as well as the base model, PET, where the labeled instances for the target under study is as few as 100. When we delve into the results, we observe that SocialPET is comparatively strong in identifying instances of the `against' class, where baseline models underperform.
Authors: Hongda Sun, Yuxuan Liu, Chengwei Wu, Haiyu Yan, Cheng Tai, Xin Gao, Shuo Shang, Rui Yan
Abstract: Open-domain question answering (ODQA) has emerged as a pivotal research spotlight in information systems. Existing methods follow two main paradigms to collect evidence: (1) The \textit{retrieve-then-read} paradigm retrieves pertinent documents from an external corpus; and (2) the \textit{generate-then-read} paradigm employs large language models (LLMs) to generate relevant documents. However, neither can fully address multifaceted requirements for evidence. To this end, we propose LLMQA, a generalized framework that formulates the ODQA process into three basic steps: query expansion, document selection, and answer generation, combining the superiority of both retrieval-based and generation-based evidence. Since LLMs exhibit their excellent capabilities to accomplish various tasks, we instruct LLMs to play multiple roles as generators, rerankers, and evaluators within our framework, integrating them to collaborate in the ODQA process. Furthermore, we introduce a novel prompt optimization algorithm to refine role-playing prompts and steer LLMs to produce higher-quality evidence and answers. Extensive experimental results on widely used benchmarks (NQ, WebQ, and TriviaQA) demonstrate that LLMQA achieves the best performance in terms of both answer accuracy and evidence quality, showcasing its potential for advancing ODQA research and applications.
Authors: Sho Hoshino, Akihiko Kato, Soichiro Murakami, Peinan Zhang
Abstract: Learning better sentence embeddings leads to improved performance for natural language understanding tasks including semantic textual similarity (STS) and natural language inference (NLI). As prior studies leverage large-scale labeled NLI datasets for fine-tuning masked language models to yield sentence embeddings, task performance for languages other than English is often left behind. In this study, we directly compared two data augmentation techniques as potential solutions for monolingual STS: (a) cross-lingual transfer that exploits English resources alone as training data to yield non-English sentence embeddings as zero-shot inference, and (b) machine translation that coverts English data into pseudo non-English training data in advance. In our experiments on monolingual STS in Japanese and Korean, we find that the two data techniques yield performance on par. Rather, we find a superiority of the Wikipedia domain over the NLI domain for these languages, in contrast to prior studies that focused on NLI as training data. Combining our findings, we demonstrate that the cross-lingual transfer of Wikipedia data exhibits improved performance, and that native Wikipedia data can further improve performance for monolingual STS.
Authors: Jio Oh, Soyeon Kim, Junseok Seo, Jindong Wang, Ruochen Xu, Xing Xie, Steven Euijong Whang
Abstract: Large language models (LLMs) have achieved unprecedented performance in various applications, yet their evaluation remains a critical issue. Existing hallucination benchmarks are either static or lack adjustable complexity for thorough analysis. We contend that utilizing existing relational databases is a promising approach for constructing benchmarks due to their accurate knowledge description via functional dependencies. We propose ERBench to automatically convert any relational database into a benchmark based on the entity-relationship (ER) model. Our key idea is to construct questions using the database schema, records, and functional dependencies such that they can be automatically verified. In addition, we use foreign key constraints to join relations and construct multihop questions, which can be arbitrarily complex and used to debug the intermediate answers of LLMs. Finally, ERBench supports continuous evaluation, multimodal questions, and various prompt engineering techniques. In our experiments, we construct an LLM benchmark using databases of multiple domains and make an extensive comparison of contemporary LLMs. We observe that better LLMs like GPT-4 can handle a larger variety of question types, but are by no means perfect. Also, correct answers do not necessarily imply correct rationales, which is an important evaluation that ERBench does better than other benchmarks for various question types. Code is available at https: //github.com/DILAB-KAIST/ERBench.
Authors: Jian Zhu, Yuping Ruan, Jingfei Chang, Cheng Luo
Abstract: The detection of abusive language remains a long-standing challenge with the extensive use of social networks. The detection task of abusive language suffers from limited accuracy. We argue that the existing detection methods utilize the fine-tuning technique of the pre-trained language models (PLMs) to handle downstream tasks. Hence, these methods fail to stimulate the general knowledge of the PLMs. To address the problem, we propose a novel Deep Prompt Multi-task Network (DPMN) for abuse language detection. Specifically, DPMN first attempts to design two forms of deep prompt tuning and light prompt tuning for the PLMs. The effects of different prompt lengths, tuning strategies, and prompt initialization methods on detecting abusive language are studied. In addition, we propose a Task Head based on Bi-LSTM and FFN, which can be used as a short text classifier. Eventually, DPMN utilizes multi-task learning to improve detection metrics further. The multi-task network has the function of transferring effective knowledge. The proposed DPMN is evaluated against eight typical methods on three public datasets: OLID, SOLID, and AbuseAnalyzer. The experimental results show that our DPMN outperforms the state-of-the-art methods.
Authors: Sotaro Takeshita, Tommaso Green, Ines Reinig, Kai Eckert, Simone Paolo Ponzetto
Abstract: Extensive efforts in the past have been directed toward the development of summarization datasets. However, a predominant number of these resources have been (semi)-automatically generated, typically through web data crawling, resulting in subpar resources for training and evaluating summarization systems, a quality compromise that is arguably due to the substantial costs associated with generating ground-truth summaries, particularly for diverse languages and specialized domains. To address this issue, we present ACLSum, a novel summarization dataset carefully crafted and evaluated by domain experts. In contrast to previous datasets, ACLSum facilitates multi-aspect summarization of scientific papers, covering challenges, approaches, and outcomes in depth. Through extensive experiments, we evaluate the quality of our resource and the performance of models based on pretrained language models and state-of-the-art large language models (LLMs). Additionally, we explore the effectiveness of extractive versus abstractive summarization within the scholarly domain on the basis of automatically discovered aspects. Our results corroborate previous findings in the general domain and indicate the general superiority of end-to-end aspect-based summarization. Our data is released at https://github.com/sobamchan/aclsum.
Authors: Zihao Wang, Anji Liu, Haowei Lin, Jiaqi Li, Xiaojian Ma, Yitao Liang
Abstract: We explore how iterative revising a chain of thoughts with the help of information retrieval significantly improves large language models' reasoning and generation ability in long-horizon generation tasks, while hugely mitigating hallucination. In particular, the proposed method -- *retrieval-augmented thoughts* (RAT) -- revises each thought step one by one with retrieved information relevant to the task query, the current and the past thought steps, after the initial zero-shot CoT is generated. Applying RAT to GPT-3.5, GPT-4, and CodeLLaMA-7b substantially improves their performances on various long-horizon generation tasks; on average of relatively increasing rating scores by 13.63% on code generation, 16.96% on mathematical reasoning, 19.2% on creative writing, and 42.78% on embodied task planning. The demo page can be found at https://craftjarvis.github.io/RAT
Authors: Yiding Liu, Jingjing Wang, Jiaming Luo, Tao Zeng, Guodong Zhou
Abstract: Aspect Sentiment Understanding (ASU) in interactive scenarios (e.g., Question-Answering and Dialogue) has attracted ever-more interest in recent years and achieved important progresses. However, existing studies on interactive ASU largely ignore the coreference issue for opinion targets (i.e., aspects), while this phenomenon is ubiquitous in interactive scenarios especially dialogues, limiting the ASU performance. Recently, large language models (LLMs) shows the powerful ability to integrate various NLP tasks with the chat paradigm. In this way, this paper proposes a new Chat-based Aspect Sentiment Understanding (ChatASU) task, aiming to explore LLMs' ability in understanding aspect sentiments in dialogue scenarios. Particularly, this ChatASU task introduces a sub-task, i.e., Aspect Chain Reasoning (ACR) task, to address the aspect coreference issue. On this basis, we propose a Trusted Self-reflexion Approach (TSA) with ChatGLM as backbone to ChatASU. Specifically, this TSA treats the ACR task as an auxiliary task to boost the performance of the primary ASU task, and further integrates trusted learning into reflexion mechanisms to alleviate the LLMs-intrinsic factual hallucination problem in TSA. Furthermore, a high-quality ChatASU dataset is annotated to evaluate TSA, and extensive experiments show that our proposed TSA can significantly outperform several state-of-the-art baselines, justifying the effectiveness of TSA to ChatASU and the importance of considering the coreference and hallucination issues in ChatASU.
Authors: Shuaiyi Li, Yang Deng, Deng Cai, Hongyuan Lu, Liang Chen, Wai Lam
Abstract: As the typical retraining paradigm is unacceptably time- and resource-consuming, researchers are turning to model editing in order to seek an effective, consecutive, and batch-supportive way to edit the model behavior directly. Despite all these practical expectations, existing model editing methods fail to realize all of them. Furthermore, the memory demands for such succession-supportive model editing approaches tend to be prohibitive, frequently necessitating an external memory that grows incrementally over time. To cope with these challenges, we propose COMEBA-HK, a model editing method that is both consecutive and batch-supportive. COMEBA-HK is memory-friendly as it only needs a small amount of it to store several hook layers with updated weights. Experimental results demonstrate the superiority of our method over other batch-supportive model editing methods under both single-round and consecutive batch editing scenarios. Extensive analyses of COMEBA-HK have been conducted to verify the stability of our method over 1) the number of consecutive steps and 2) the number of editing instance.
Authors: Wei Zhou, Heike Adel, Hendrik Schuff, Ngoc Thang Vu
Abstract: Attribution scores indicate the importance of different input parts and can, thus, explain model behaviour. Currently, prompt-based models are gaining popularity, i.a., due to their easier adaptability in low-resource settings. However, the quality of attribution scores extracted from prompt-based models has not been investigated yet. In this work, we address this topic by analyzing attribution scores extracted from prompt-based models w.r.t. plausibility and faithfulness and comparing them with attribution scores extracted from fine-tuned models and large language models. In contrast to previous work, we introduce training size as another dimension into the analysis. We find that using the prompting paradigm (with either encoder-based or decoder-based models) yields more plausible explanations than fine-tuning the models in low-resource settings and Shapley Value Sampling consistently outperforms attention and Integrated Gradients in terms of leading to more plausible and faithful explanations.
Authors: Seyed Parsa Neshaei, Yasaman Boreshban, Gholamreza Ghassem-Sani, Seyed Abolghasem Mirroshandel
Abstract: Transformer-based models have made remarkable advancements in various NLP areas. Nevertheless, these models often exhibit vulnerabilities when confronted with adversarial attacks. In this paper, we explore the effect of quantization on the robustness of Transformer-based models. Quantization usually involves mapping a high-precision real number to a lower-precision value, aiming at reducing the size of the model at hand. To the best of our knowledge, this work is the first application of quantization on the robustness of NLP models. In our experiments, we evaluate the impact of quantization on BERT and DistilBERT models in text classification using SST-2, Emotion, and MR datasets. We also evaluate the performance of these models against TextFooler, PWWS, and PSO adversarial attacks. Our findings show that quantization significantly improves (by an average of 18.68%) the adversarial accuracy of the models. Furthermore, we compare the effect of quantization versus that of the adversarial training approach on robustness. Our experiments indicate that quantization increases the robustness of the model by 18.80% on average compared to adversarial training without imposing any extra computational overhead during training. Therefore, our results highlight the effectiveness of quantization in improving the robustness of NLP models.
Authors: Arijit Nag, Animesh Mukherjee, Niloy Ganguly, Soumen Chakrabarti
Abstract: Large Language Models (LLMs) exhibit impressive zero/few-shot inference and generation quality for high-resource languages(HRLs). A few of them have been trained in low-resource languages (LRLs) and give decent performance. Owing to the prohibitive costs of training LLMs, they are usually used as a network service, with the client charged by the count of input and output tokens. The number of tokens strongly depends on the script and language, as well as the LLM's sub-word vocabulary. We show that LRLs are at a pricing disadvantage, because the well-known LLMs produce more tokens for LRLs than HRLs. This is because most currently popular LLMs are optimized for HRL vocabularies. Our objective is to level the playing field: reduce the cost of processing LRLs in contemporary LLMs while ensuring that predictive and generative qualities are not compromised. As means to reduce the number of tokens processed by the LLM, we consider code-mixing, translation, and transliteration of LRLs to HRLs. We perform an extensive study using the IndicXTREME dataset, covering 15 Indian languages, while using GPT-4 (one of the costliest LLM services released so far) as a commercial LLM. We observe and analyze interesting patterns involving token count, cost,and quality across a multitude of languages and tasks. We show that choosing the best policy to interact with the LLM can reduce cost by 90% while giving better or comparable performance, compared to communicating with the LLM in the original LRL.
Authors: Adrian de Wynter
Abstract: We show that GPT-4's reasoning and planning capabilities extend to the 1993 first-person shooter Doom. This large language model (LLM) is able to run and play the game with only a few instructions, plus a textual description--generated by the model itself from screenshots--about the state of the game being observed. We find that GPT-4 can play the game to a passable degree: it is able to manipulate doors, combat enemies, and perform pathing. More complex prompting strategies involving multiple model calls provide better results. While further work is required to enable the LLM to play the game as well as its classical, reinforcement learning-based counterparts, we note that GPT-4 required no training, leaning instead on its own reasoning and observational capabilities. We hope our work pushes the boundaries on intelligent, LLM-based agents in video games. We conclude by discussing the ethical implications of our work.
Authors: D. Fortune Kponou, Frejus A. A. Laleye, Eugene C. Ezin
Abstract: In this paper, we introduce the Fongbe to French Speech Translation Corpus (FFSTC) for the first time. This corpus encompasses approximately 31 hours of collected Fongbe language content, featuring both French transcriptions and corresponding Fongbe voice recordings. FFSTC represents a comprehensive dataset compiled through various collection methods and the efforts of dedicated individuals. Furthermore, we conduct baseline experiments using Fairseq's transformer_s and conformer models to evaluate data quality and validity. Our results indicate a score of 8.96 for the transformer_s model and 8.14 for the conformer model, establishing a baseline for the FFSTC corpus.
Authors: Agnes Luhtaru, Taido Purason, Martin Vainikko, Maksym Del, Mark Fishel
Abstract: This study explores enhancing grammatical error correction (GEC) through artificial error generation (AEG) using language models (LMs). Specifically, we fine-tune Llama 2-based LMs for error generation and find that this approach yields synthetic errors akin to human errors. Next, we train GEC Llama models with the help of these artificial errors and outperform previous state-of-the-art error correction models, with gains ranging between 0.8 and 6 F0.5 points across all tested languages (German, Ukrainian, and Estonian). Moreover, we demonstrate that generating errors by fine-tuning smaller sequence-to-sequence models and prompting large commercial LMs (GPT-3.5 and GPT-4) also results in synthetic errors beneficially affecting error generation models.
Authors: James Chua, Edward Rees, Hunar Batra, Samuel R. Bowman, Julian Michael, Ethan Perez, Miles Turpin
Abstract: While chain-of-thought prompting (CoT) has the potential to improve the explainability of language model reasoning, it can systematically misrepresent the factors influencing models' behavior--for example, rationalizing answers in line with a user's opinion without mentioning this bias. To mitigate this biased reasoning problem, we introduce bias-augmented consistency training (BCT), an unsupervised fine-tuning scheme that trains models to give consistent reasoning across prompts with and without biasing features. We construct a suite testing nine forms of biased reasoning on seven question-answering tasks, and find that applying BCT to GPT-3.5-Turbo with one bias reduces the rate of biased reasoning by 86% on held-out tasks. Moreover, this model generalizes to other forms of bias, reducing biased reasoning on held-out biases by an average of 37%. As BCT generalizes to held-out biases and does not require gold labels, this method may hold promise for reducing biased reasoning from as-of-yet unknown biases and on tasks where supervision for ground truth reasoning is unavailable.
Authors: Aisha Khatun, Anisur Rahman, Md Saiful Islam, Hemayet Ahmed Chowdhury, Ayesha Tasnim
Abstract: Authorship Attribution is the task of creating an appropriate characterization of text that captures the authors' writing style to identify the original author of a given piece of text. With increased anonymity on the internet, this task has become increasingly crucial in various security and plagiarism detection fields. Despite significant advancements in other languages such as English, Spanish, and Chinese, Bangla lacks comprehensive research in this field due to its complex linguistic feature and sentence structure. Moreover, existing systems are not scalable when the number of author increases, and the performance drops for small number of samples per author. In this paper, we propose the use of Average-Stochastic Gradient Descent Weight-Dropped Long Short-Term Memory (AWD-LSTM) architecture and an effective transfer learning approach that addresses the problem of complex linguistic features extraction and scalability for authorship attribution in Bangla Literature (AABL). We analyze the effect of different tokenization, such as word, sub-word, and character level tokenization, and demonstrate the effectiveness of these tokenizations in the proposed model. Moreover, we introduce the publicly available Bangla Authorship Attribution Dataset of 16 authors (BAAD16) containing 17,966 sample texts and 13.4+ million words to solve the standard dataset scarcity problem and release six variations of pre-trained language models for use in any Bangla NLP downstream task. For evaluation, we used our developed BAAD16 dataset as well as other publicly available datasets. Empirically, our proposed model outperformed state-of-the-art models and achieved 99.8% accuracy in the BAAD16 dataset. Furthermore, we showed that the proposed system scales much better even with an increasing number of authors, and performance remains steady despite few training samples.
Authors: Machel Reid, Nikolay Savinov, Denis Teplyashin, Dmitry Lepikhin, Timothy Lillicrap, Jean-baptiste Alayrac, Radu Soricut, Angeliki Lazaridou, Orhan Firat, Julian Schrittwieser, Ioannis Antonoglou, Rohan Anil, Sebastian Borgeaud, Andrew Dai, Katie Millican, Ethan Dyer, Mia Glaese, Thibault Sottiaux, Benjamin Lee, Fabio Viola, Malcolm Reynolds, Yuanzhong Xu, James Molloy, Jilin Chen, Michael Isard, Paul Barham, Tom Hennigan, Ross McIlroy, Melvin Johnson, Johan Schalkwyk, Eli Collins, Eliza Rutherford, Erica Moreira, Kareem Ayoub, Megha Goel, Clemens Meyer, Gregory Thornton, Zhen Yang, Henryk Michalewski, Zaheer Abbas, Nathan Schucher, Ankesh Anand, Richard Ives, James Keeling, Karel Lenc, Salem Haykal, Siamak Shakeri, Pranav Shyam, Aakanksha Chowdhery, Roman Ring, Stephen Spencer, Eren Sezener, Luke Vilnis, Oscar Chang, Nobuyuki Morioka, George Tucker, Ce Zheng, Oliver Woodman, Nithya Attaluri, Tomas Kocisky, Evgenii Eltyshev, Xi Chen, Timothy Chung, Vittorio Selo, Siddhartha Brahma, Petko Georgiev, Ambrose Slone, Zhenkai Zhu, James Lottes, Siyuan Qiao, Ben Caine, Sebastian Riedel, Alex Tomala, Martin Chadwick, Juliette Love, Peter Choy, Sid Mittal, Neil Houlsby, Yunhao Tang, Matthew Lamm, Libin Bai, Qiao Zhang, Luheng He, Yong Cheng, Peter Humphreys, Yujia Li, Sergey Brin, Albin Cassirer, Yingjie Miao, Lukas Zilka, Taylor Tobin, Kelvin Xu, Lev Proleev, Daniel Sohn, Alberto Magni, Lisa Anne Hendricks, Isabel Gao, Santiago Onta\~n\'on, Oskar Bunyan, Nathan Byrd, Abhanshu Sharma, Biao Zhang, Mario Pinto, Rishika Sinha, Harsh Mehta, Dawei Jia, Sergi Caelles, Albert Webson, Alex Morris, Becca Roelofs, Yifan Ding, Robin Strudel, Xuehan Xiong, Marvin Ritter, Mostafa Dehghani, Rahma Chaabouni, Abhijit Karmarkar, Guangda Lai, Fabian Mentzer, Bibo Xu, YaGuang Li, Yujing Zhang, Tom Le Paine, Alex Goldin, Behnam Neyshabur, Kate Baumli, Anselm Levskaya, Michael Laskin, Wenhao Jia, Jack W. Rae, Kefan Xiao, Antoine He, Skye Giordano, Lakshman Yagati, Jean-Baptiste Lespiau, Paul Natsev, Sanjay Ganapathy, Fangyu Liu, Danilo Martins, Nanxin Chen, Yunhan Xu, Megan Barnes, Rhys May, Arpi Vezer, Junhyuk Oh, Ken Franko, Sophie Bridgers, Ruizhe Zhao, Boxi Wu, Basil Mustafa, Sean Sechrist, Emilio Parisotto, Thanumalayan Sankaranarayana Pillai, Chris Larkin, Chenjie Gu, Christina Sorokin, Maxim Krikun, Alexey Guseynov, Jessica Landon, Romina Datta, Alexander Pritzel, Phoebe Thacker, Fan Yang, Kevin Hui, Anja Hauth, Chih-Kuan Yeh, David Barker, Justin Mao-Jones, Sophia Austin, Hannah Sheahan, Parker Schuh, James Svensson, Rohan Jain, Vinay Ramasesh, Anton Briukhov, Da-Woon Chung, Tamara von Glehn, Christina Butterfield, Priya Jhakra, Matthew Wiethoff, Justin Frye, Jordan Grimstad, Beer Changpinyo, Charline Le Lan, Anna Bortsova, Yonghui Wu, Paul Voigtlaender, Tara Sainath, Charlotte Smith, Will Hawkins, Kris Cao, James Besley, Srivatsan Srinivasan, Mark Omernick, Colin Gaffney, Gabriela Surita, Ryan Burnell, Bogdan Damoc, Junwhan Ahn, Andrew Brock, Mantas Pajarskas, Anastasia Petrushkina, Seb Noury, Lorenzo Blanco, Kevin Swersky, Arun Ahuja, Thi Avrahami, Vedant Misra, Raoul de Liedekerke, Mariko Iinuma, Alex Polozov, Sarah York, George van den Driessche, Paul Michel, Justin Chiu, Rory Blevins, Zach Gleicher, Adri\`a Recasens, Alban Rrustemi, Elena Gribovskaya, Aurko Roy, Wiktor Gworek, S\'eb Arnold, Lisa Lee, James Lee-Thorp, Marcello Maggioni, Enrique Piqueras, Kartikeya Badola, Sharad Vikram, Lucas Gonzalez, Anirudh Baddepudi, Evan Senter, Jacob Devlin, James Qin, Michael Azzam, Maja Trebacz, Martin Polacek, Kashyap Krishnakumar, Shuo-yiin Chang, Matthew Tung, Ivo Penchev, Rishabh Joshi, Kate Olszewska, Carrie Muir, Mateo Wirth, Ale Jakse Hartman, Josh Newlan, Sheleem Kashem, Vijay Bolina, Elahe Dabir, Joost van Amersfoort, Zafarali Ahmed, James Cobon-Kerr, Aishwarya Kamath, Arnar Mar Hrafnkelsson, Le Hou, Ian Mackinnon, Alexandre Frechette, Eric Noland, Xiance Si, Emanuel Taropa, Dong Li, Phil Crone, Anmol Gulati, S\'ebastien Cevey, Jonas Adler, Ada Ma, David Silver, Simon Tokumine, Richard Powell, Stephan Lee, Michael Chang, Samer Hassan, Diana Mincu, Antoine Yang, Nir Levine, Jenny Brennan, Mingqiu Wang, Sarah Hodkinson, Jeffrey Zhao, Josh Lipschultz, Aedan Pope, Michael B. Chang, Cheng Li, Laurent El Shafey, Michela Paganini, Sholto Douglas, Bernd Bohnet, Fabio Pardo, Seth Odoom, Mihaela Rosca, Cicero Nogueira dos Santos, Kedar Soparkar, Arthur Guez, Tom Hudson, Steven Hansen, Chulayuth Asawaroengchai, Ravi Addanki, Tianhe Yu, Wojciech Stokowiec, Mina Khan, Justin Gilmer, Jaehoon Lee, Carrie Grimes Bostock, Keran Rong, Jonathan Caton, Pedram Pejman, Filip Pavetic, Geoff Brown, Vivek Sharma, Mario Lu\v{c}i\'c, Rajkumar Samuel, Josip Djolonga, Amol Mandhane, Lars Lowe Sj\"osund, Elena Buchatskaya, Elspeth White, Natalie Clay, Jiepu Jiang, Hyeontaek Lim, Ross Hemsley, Jane Labanowski, Nicola De Cao, David Steiner, Sayed Hadi Hashemi, Jacob Austin, Anita Gergely, Tim Blyth, Joe Stanton, Kaushik Shivakumar, Aditya Siddhant, Anders Andreassen, Carlos Araya, Nikhil Sethi, Rakesh Shivanna, Steven Hand, Ankur Bapna, Ali Khodaei, Antoine Miech, Garrett Tanzer, Andy Swing, Shantanu Thakoor, Zhufeng Pan, Zachary Nado, Stephanie Winkler, Dian Yu, Mohammad Saleh, Loren Maggiore, Iain Barr, Minh Giang, Thais Kagohara, Ivo Danihelka, Amit Marathe, Vladimir Feinberg, Mohamed Elhawaty, Nimesh Ghelani, Dan Horgan, Helen Miller, Lexi Walker, Richard Tanburn, Mukarram Tariq, Disha Shrivastava, Fei Xia, Chung-Cheng Chiu, Zoe Ashwood, Khuslen Baatarsukh, Sina Samangooei, Fred Alcober, Axel Stjerngren, Paul Komarek, Katerina Tsihlas, Anudhyan Boral, Ramona Comanescu, Jeremy Chen, Ruibo Liu, Dawn Bloxwich, Charlie Chen, Yanhua Sun, Fangxiaoyu Feng, Matthew Mauger, Xerxes Dotiwalla, Vincent Hellendoorn, Michael Sharman, Ivy Zheng, Krishna Haridasan, Gabe Barth-Maron, Craig Swanson, Dominika Rogozi\'nska, Alek Andreev, Paul Kishan Rubenstein, Ruoxin Sang, Dan Hurt, Gamaleldin Elsayed, Renshen Wang, Dave Lacey, Anastasija Ili\'c, Yao Zhao, Lora Aroyo, Chimezie Iwuanyanwu, Vitaly Nikolaev, Balaji Lakshminarayanan, Sadegh Jazayeri, Rapha\"el Lopez Kaufman, Mani Varadarajan, Chetan Tekur, Doug Fritz, Misha Khalman, David Reitter, Kingshuk Dasgupta, Shourya Sarcar, Tina Ornduff, Javier Snaider, Fantine Huot, Johnson Jia, Rupert Kemp, Nejc Trdin, Anitha Vijayakumar, Lucy Kim, Christof Angermueller, Li Lao, Tianqi Liu, Haibin Zhang, David Engel, Somer Greene, Ana\"is White, Jessica Austin, Lilly Taylor, Shereen Ashraf, Dangyi Liu, Maria Georgaki, Irene Cai, Yana Kulizhskaya, Sonam Goenka, Brennan Saeta, Kiran Vodrahalli, Christian Frank, Dario de Cesare, Brona Robenek, Harry Richardson, Mahmoud Alnahlawi, Christopher Yew, Priya Ponnapalli, Marco Tagliasacchi, Alex Korchemniy, Yelin Kim, Dinghua Li, Bill Rosgen, Zoe Ashwood, Kyle Levin, Jeremy Wiesner, Praseem Banzal, Praveen Srinivasan, Hongkun Yu, \c{C}a\u{g}lar \"Unl\"u, David Reid, Zora Tung, Daniel Finchelstein, Ravin Kumar, Andre Elisseeff, Jin Huang, Ming Zhang, Rui Zhu, Ricardo Aguilar, Mai Gim\'enez, Jiawei Xia, Olivier Dousse, Willi Gierke, Soheil Hassas Yeganeh, Damion Yates, Komal Jalan, Lu Li, Eri Latorre-Chimoto, Duc Dung Nguyen, Ken Durden, Praveen Kallakuri, Yaxin Liu, Matthew Johnson, Tomy Tsai, Alice Talbert, Jasmine Liu, Alexander Neitz, Chen Elkind, Marco Selvi, Mimi Jasarevic, Livio Baldini Soares, Albert Cui, Pidong Wang, Alek Wenjiao Wang, Xinyu Ye, Krystal Kallarackal, Lucia Loher, Hoi Lam, Josef Broder, Dan Holtmann-Rice, Nina Martin, Bramandia Ramadhana, Daniel Toyama, Mrinal Shukla, Sujoy Basu, Abhi Mohan, Nick Fernando, Noah Fiedel, Kim Paterson, Hui Li, Ankush Garg, Jane Park, DongHyun Choi, Diane Wu, Sankalp Singh, Zhishuai Zhang, Amir Globerson, Lily Yu, John Carpenter, F\'elix de Chaumont Quitry, Carey Radebaugh, Chu-Cheng Lin, Alex Tudor, Prakash Shroff, Drew Garmon, Dayou Du, Neera Vats, Han Lu, Shariq Iqbal, Alex Yakubovich, Nilesh Tripuraneni, James Manyika, Haroon Qureshi, Nan Hua, Christel Ngani, Maria Abi Raad, Hannah Forbes, Anna Bulanova, Jeff Stanway, Mukund Sundararajan, Victor Ungureanu, Colton Bishop, Yunjie Li, Balaji Venkatraman, Bo Li, Chloe Thornton, Salvatore Scellato, Nishesh Gupta, Yicheng Wang, Ian Tenney, Xihui Wu, Ashish Shenoy, Gabriel Carvajal, Diana Gage Wright, Ben Bariach, Zhuyun Xiao, Peter Hawkins, Sid Dalmia, Clement Farabet, Pedro Valenzuela, Quan Yuan, Chris Welty, Ananth Agarwal, Mia Chen, Wooyeol Kim, Brice Hulse, Nandita Dukkipati, Adam Paszke, Andrew Bolt, Elnaz Davoodi, Kiam Choo, Jennifer Beattie, Jennifer Prendki, Harsha Vashisht, Rebeca Santamaria-Fernandez, Luis C. Cobo, Jarek Wilkiewicz, David Madras, Ali Elqursh, Grant Uy, Kevin Ramirez, Matt Harvey, Tyler Liechty, Heiga Zen, Jeff Seibert, Clara Huiyi Hu, Mohamed Elhawaty, Andrey Khorlin, Maigo Le, Asaf Aharoni, Megan Li, Lily Wang, Sandeep Kumar, Alejandro Lince, Norman Casagrande, Jay Hoover, Dalia El Badawy, David Soergel, Denis Vnukov, Matt Miecnikowski, Jiri Simsa, Anna Koop, Praveen Kumar, Thibault Sellam, Daniel Vlasic, Samira Daruki, Nir Shabat, John Zhang, Guolong Su, Jiageng Zhang, Jeremiah Liu, Yi Sun, Evan Palmer, Alireza Ghaffarkhah, Xi Xiong, Victor Cotruta, Michael Fink, Lucas Dixon, Ashwin Sreevatsa, Adrian Goedeckemeyer, Alek Dimitriev, Mohsen Jafari, Remi Crocker, Nicholas FitzGerald, Aviral Kumar, Sanjay Ghemawat, Ivan Philips, Frederick Liu, Yannie Liang, Rachel Sterneck, Alena Repina, Marcus Wu, Laura Knight, Marin Georgiev, Hyo Lee, Harry Askham, Abhishek Chakladar, Annie Louis, Carl Crous, Hardie Cate, Dessie Petrova, Michael Quinn, Denese Owusu-Afriyie, Achintya Singhal, Nan Wei, Solomon Kim, Damien Vincent, Milad Nasr, Christopher A. Choquette-Choo, Reiko Tojo, Shawn Lu, Diego de Las Casas, Yuchung Cheng, Tolga Bolukbasi, Katherine Lee, Saaber Fatehi, Rajagopal Ananthanarayanan, Miteyan Patel, Charbel Kaed, Jing Li, Jakub Sygnowski, Shreyas Rammohan Belle, Zhe Chen, Jaclyn Konzelmann, Siim P\~oder, Roopal Garg, Vinod Koverkathu, Adam Brown, Chris Dyer, Rosanne Liu, Azade Nova, Jun Xu, Slav Petrov, Demis Hassabis, Koray Kavukcuoglu, Jeffrey Dean, Oriol Vinyals
Abstract: In this report, we present the latest model of the Gemini family, Gemini 1.5 Pro, a highly compute-efficient multimodal mixture-of-experts model capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. Gemini 1.5 Pro achieves near-perfect recall on long-context retrieval tasks across modalities, improves the state-of-the-art in long-document QA, long-video QA and long-context ASR, and matches or surpasses Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5 Pro's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 2.1 (200k) and GPT-4 Turbo (128k). Finally, we highlight surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.
Authors: Kunal Handa, Yarin Gal, Ellie Pavlick, Noah Goodman, Jacob Andreas, Alex Tamkin, Belinda Z. Li
Abstract: Aligning AI systems to users' interests requires understanding and incorporating humans' complex values and preferences. Recently, language models (LMs) have been used to gather information about the preferences of human users. This preference data can be used to fine-tune or guide other LMs and/or AI systems. However, LMs have been shown to struggle with crucial aspects of preference learning: quantifying uncertainty, modeling human mental states, and asking informative questions. These challenges have been addressed in other areas of machine learning, such as Bayesian Optimal Experimental Design (BOED), which focus on designing informative queries within a well-defined feature space. But these methods, in turn, are difficult to scale and apply to real-world problems where simply identifying the relevant features can be difficult. We introduce OPEN (Optimal Preference Elicitation with Natural language) a framework that uses BOED to guide the choice of informative questions and an LM to extract features and translate abstract BOED queries into natural language questions. By combining the flexibility of LMs with the rigor of BOED, OPEN can optimize the informativity of queries while remaining adaptable to real-world domains. In user studies, we find that OPEN outperforms existing LM- and BOED-based methods for preference elicitation.
Authors: Benjamin Lemkin
Abstract: GPT4 was initially trained on large amounts of data, and then fine-tuned using Reinforcement learning from Human Feedback (RLHF), which is when volunteers give feedback in order to teach GPT4 not to create inappropriate content. In this paper, we present a method to manipulate the fine-tuned version into reverting to pre-RLHF behavior, effectively removing all safety mechanisms that the model learned during RLHF. In particular, when GPT4 acts without RLHF, it loses all inhibition, and can complete very inappropriate content given only the first few words.
Authors: Yifan Zeng, Yiran Wu, Xiao Zhang, Huazheng Wang, Qingyun Wu
Abstract: Despite extensive pre-training and fine-tuning in moral alignment to prevent generating harmful information at user request, large language models (LLMs) remain vulnerable to jailbreak attacks. In this paper, we propose AutoDefense, a response-filtering based multi-agent defense framework that filters harmful responses from LLMs. This framework assigns different roles to LLM agents and employs them to complete the defense task collaboratively. The division in tasks enhances the overall instruction-following of LLMs and enables the integration of other defense components as tools. AutoDefense can adapt to various sizes and kinds of open-source LLMs that serve as agents. Through conducting extensive experiments on a large scale of harmful and safe prompts, we validate the effectiveness of the proposed AutoDefense in improving the robustness against jailbreak attacks, while maintaining the performance at normal user request. Our code and data are publicly available at https://github.com/XHMY/AutoDefense.
Authors: Arijit Ghosh Chowdhury, Md Mofijul Islam, Vaibhav Kumar, Faysal Hossain Shezan, Vaibhav Kumar, Vinija Jain, Aman Chadha
Abstract: Large Language Models (LLMs) have become a cornerstone in the field of Natural Language Processing (NLP), offering transformative capabilities in understanding and generating human-like text. However, with their rising prominence, the security and vulnerability aspects of these models have garnered significant attention. This paper presents a comprehensive survey of the various forms of attacks targeting LLMs, discussing the nature and mechanisms of these attacks, their potential impacts, and current defense strategies. We delve into topics such as adversarial attacks that aim to manipulate model outputs, data poisoning that affects model training, and privacy concerns related to training data exploitation. The paper also explores the effectiveness of different attack methodologies, the resilience of LLMs against these attacks, and the implications for model integrity and user trust. By examining the latest research, we provide insights into the current landscape of LLM vulnerabilities and defense mechanisms. Our objective is to offer a nuanced understanding of LLM attacks, foster awareness within the AI community, and inspire robust solutions to mitigate these risks in future developments.
Authors: Antonios Alexos, Pierre Baldi
Abstract: The generation of natural and high-quality speech from text is a challenging problem in the field of natural language processing. In addition to speech generation, speech editing is also a crucial task, which requires the seamless and unnoticeable integration of edited speech into synthesized speech. We propose a novel approach to speech editing by leveraging a pre-trained text-to-speech (TTS) model, such as FastSpeech 2, and incorporating a double attention block network on top of it to automatically merge the synthesized mel-spectrogram with the mel-spectrogram of the edited text. We refer to this model as AttentionStitch, as it harnesses attention to stitch audio samples together. We evaluate the proposed AttentionStitch model against state-of-the-art baselines on both single and multi-speaker datasets, namely LJSpeech and VCTK. We demonstrate its superior performance through an objective and a subjective evaluation test involving 15 human participants. AttentionStitch is capable of producing high-quality speech, even for words not seen during training, while operating automatically without the need for human intervention. Moreover, AttentionStitch is fast during both training and inference and is able to generate human-sounding edited speech.
Authors: Eva Giboulot, Furon Teddy
Abstract: Watermarking is a technical means to dissuade malfeasant usage of Large Language Models. This paper proposes a novel watermarking scheme, so-called WaterMax, that enjoys high detectability while sustaining the quality of the generated text of the original LLM. Its new design leaves the LLM untouched (no modification of the weights, logits, temperature, or sampling technique). WaterMax balances robustness and complexity contrary to the watermarking techniques of the literature inherently provoking a trade-off between quality and robustness. Its performance is both theoretically proven and experimentally validated. It outperforms all the SotA techniques under the most complete benchmark suite.
Authors: Martin Riddell, Ansong Ni, Arman Cohan
Abstract: While large language models have achieved remarkable performance on various code generation benchmarks, there have been growing concerns regarding potential contamination of these benchmarks as they may be leaked into pretraining and finetuning data. While recent work has investigated contamination in natural language generation and understanding tasks, there has been less extensive research into how data contamination impacts the evaluation of code generation, which is critical for understanding the robustness and reliability of LLMs in programming contexts. In this work, we perform a comprehensive study of data contamination of popular code generation benchmarks, and precisely quantify their overlap with pretraining corpus through both surface-level and semantic-level matching. In our experiments, we show that there are substantial overlap between popular code generation benchmarks and open training corpus, and models perform significantly better on the subset of the benchmarks where similar solutions are seen during training. We also conduct extensive analysis on the factors that affects model memorization and generalization, such as model size, problem difficulty, and question length. We release all resulting files from our matching pipeline for future research.
Authors: Vanshika Vats, Marzia Binta Nizam, Minghao Liu, Ziyuan Wang, Richard Ho, Mohnish Sai Prasad, Vincent Titterton, Sai Venkat Malreddy, Riya Aggarwal, Yanwen Xu, Lei Ding, Jay Mehta, Nathan Grinnell, Li Liu, Sijia Zhong, Devanathan Nallur Gandamani, Xinyi Tang, Rohan Ghosalkar, Celeste Shen, Rachel Shen, Nafisa Hussain, Kesav Ravichandran, James Davis
Abstract: In the rapidly evolving landscape of artificial intelligence (AI), the collaboration between human intelligence and AI systems, known as Human-AI (HAI) Teaming, has emerged as a cornerstone for advancing problem-solving and decision-making processes. The advent of Large Pre-trained Models (LPtM) has significantly transformed this landscape, offering unprecedented capabilities by leveraging vast amounts of data to understand and predict complex patterns. This paper surveys the pivotal integration of LPtMs with HAI, emphasizing how these models enhance collaborative intelligence beyond traditional approaches. It examines the synergistic potential of LPtMs in augmenting human capabilities, discussing this collaboration for AI model improvements, effective teaming, ethical considerations, and their broad applied implications in various sectors. Through this exploration, the study sheds light on the transformative impact of LPtM-enhanced HAI Teaming, providing insights for future research, policy development, and strategic implementations aimed at harnessing the full potential of this collaboration for research and societal benefit.
Authors: Yuhao Wu, Franziska Roesner, Tadayoshi Kohno, Ning Zhang, Umar Iqbal
Abstract: Large language models (LLMs) extended as systems, such as ChatGPT, have begun supporting third-party applications. These LLM apps leverage the de facto natural language-based automated execution paradigm of LLMs: that is, apps and their interactions are defined in natural language, provided access to user data, and allowed to freely interact with each other and the system. These LLM app ecosystems resemble the settings of earlier computing platforms, where there was insufficient isolation between apps and the system. Because third-party apps may not be trustworthy, and exacerbated by the imprecision of the natural language interfaces, the current designs pose security and privacy risks for users. In this paper, we propose SecGPT, an architecture for LLM-based systems that aims to mitigate the security and privacy issues that arise with the execution of third-party apps. SecGPT's key idea is to isolate the execution of apps and more precisely mediate their interactions outside of their isolated environments. We evaluate SecGPT against a number of case study attacks and demonstrate that it protects against many security, privacy, and safety issues that exist in non-isolated LLM-based systems. The performance overhead incurred by SecGPT to improve security is under 0.3x for three-quarters of the tested queries. To foster follow-up research, we release SecGPT's source code at https://github.com/llm-platform-security/SecGPT.
Authors: Carlo Lipizzi
Abstract: Large Language Models (LLM) have taken the front seat in most of the news since November 2023, when ChatGPT was introduced. After more than one year, one of the major reasons companies are resistant to adopting them is the limited confidence they have in the trustworthiness of those systems. In a study by (Baymard, 2023), ChatGPT-4 showed an 80.1% false-positive error rate in identifying usability issues on websites. A Jan. '24 study by JAMA Pediatrics found that ChatGPT has an accuracy rate of 17% percent when diagnosing pediatric medical cases (Barile et al., 2024). But then, what is "trust"? Trust is a relative, subject condition that can change based on culture, domain, individuals. And then, given a domain, how can the trustworthiness of a system be measured? In this paper, I present a systematic approach to measure trustworthiness based on a predefined ground truth, represented as a knowledge graph of the domain. The approach is a process with humans in the loop to validate the representation of the domain and to fine-tune the system. Measuring the trustworthiness would be essential for all the entities operating in critical environments, such as healthcare, defense, finance, but it would be very relevant for all the users of LLMs.
Authors: Hanzhuo Tan, Qi Luo, Jing Li, Yuqun Zhang
Abstract: Decompilation aims to restore compiled code to human-readable source code, but struggles with details like names and structure. Large language models (LLMs) show promise for programming tasks, motivating their application to decompilation. However, there does not exist any open-source LLM for decompilation. Moreover, existing decompilation evaluation systems mainly consider token-level accuracy and largely ignore code executability, which is the most important feature of any program. Therefore, we release the first open-access decompilation LLMs ranging from 1B to 33B pre-trained on 4 billion tokens of C source code and the corresponding assembly code. The open-source LLMs can serve as baselines for further development in the field. To ensure practical program evaluation, we introduce Decompile-Eval, the first dataset that considers re-compilability and re-executability for decompilation. The benchmark emphasizes the importance of evaluating the decompilation model from the perspective of program semantics. Experiments indicate that our LLM4Decompile has demonstrated the capability to accurately decompile 21% of the assembly code, which achieves a 50% improvement over GPT-4. Our code, dataset, and models are released at https://github.com/albertan017/LLM4Decompile
Authors: Thang M. Pham, Peijie Chen, Tin Nguyen, Seunghyun Yoon, Trung Bui, Anh Nguyen
Abstract: CLIP-based classifiers rely on the prompt containing a {class name} that is known to the text encoder. That is, CLIP performs poorly on new classes or the classes whose names rarely appear on the Internet (e.g., scientific names of birds). For fine-grained classification, we propose PEEB - an explainable and editable classifier to (1) express the class name into a set of pre-defined text descriptors that describe the visual parts of that class; and (2) match the embeddings of the detected parts to their textual descriptors in each class to compute a logit score for classification. In a zero-shot setting where the class names are unknown, PEEB outperforms CLIP by a large margin (~10x in accuracy). Compared to part-based classifiers, PEEB is not only the state-of-the-art on the supervised-learning setting (88.80% accuracy) but also the first to enable users to edit the class definitions to form a new classifier without retraining. Compared to concept bottleneck models, PEEB is also the state-of-the-art in both zero-shot and supervised learning settings.
Authors: Zhengrui Guo, Jiabo Ma, Yingxue Xu, Yihui Wang, Liansheng Wang, Hao Chen
Abstract: Histopathology serves as the gold standard in cancer diagnosis, with clinical reports being vital in interpreting and understanding this process, guiding cancer treatment and patient care. The automation of histopathology report generation with deep learning stands to significantly enhance clinical efficiency and lessen the labor-intensive, time-consuming burden on pathologists in report writing. In pursuit of this advancement, we introduce HistGen, a multiple instance learning-empowered framework for histopathology report generation together with the first benchmark dataset for evaluation. Inspired by diagnostic and report-writing workflows, HistGen features two delicately designed modules, aiming to boost report generation by aligning whole slide images (WSIs) and diagnostic reports from local and global granularity. To achieve this, a local-global hierarchical encoder is developed for efficient visual feature aggregation from a region-to-slide perspective. Meanwhile, a cross-modal context module is proposed to explicitly facilitate alignment and interaction between distinct modalities, effectively bridging the gap between the extensive visual sequences of WSIs and corresponding highly summarized reports. Experimental results on WSI report generation show the proposed model outperforms state-of-the-art (SOTA) models by a large margin. Moreover, the results of fine-tuning our model on cancer subtyping and survival analysis tasks further demonstrate superior performance compared to SOTA methods, showcasing strong transfer learning capability. Dataset, model weights, and source code are available in https://github.com/dddavid4real/HistGen.
Authors: Hao Kang, Qingru Zhang, Souvik Kundu, Geonhwa Jeong, Zaoxing Liu, Tushar Krishna, Tuo Zhao
Abstract: Key-value (KV) caching has become the de-facto to accelerate generation speed for large language models (LLMs) inference. However, the growing cache demand with increasing sequence length has transformed LLM inference to be a memory bound problem, significantly constraining the system throughput. Existing methods rely on dropping unimportant tokens or quantizing all entries uniformly. Such methods, however, often incur high approximation errors to represent the compressed matrices. The autoregressive decoding process further compounds the error of each step, resulting in critical deviation in model generation and deterioration of performance. To tackle this challenge, we propose GEAR, an efficient KV cache compression framework that achieves near-lossless high-ratio compression. GEAR first applies quantization to majority of entries of similar magnitudes to ultra-low precision. It then employs a low rank matrix to approximate the quantization error, and a sparse matrix to remedy individual errors from outlier entries. By adeptly integrating three techniques, GEAR is able to fully exploit their synergistic potentials. Our experiments demonstrate that compared to alternatives, GEAR achieves near-lossless 4-bit KV cache compression with up to 2.38x throughput improvement, while reducing peak-memory size up to 2.29x. Our code is publicly available at https://github.com/HaoKang-Timmy/GEAR.
Authors: Tarun Kalluri, Bodhisattwa Prasad Majumder, Manmohan Chandraker
Abstract: We introduce LaGTran, a novel framework that utilizes readily available or easily acquired text descriptions to guide robust transfer of discriminative knowledge from labeled source to unlabeled target data with domain shifts. While unsupervised adaptation methods have been established to address this problem, they show limitations in handling challenging domain shifts due to their exclusive operation within the pixel-space. Motivated by our observation that semantically richer text modality has more favorable transfer properties, we devise a transfer mechanism to use a source-trained text-classifier to generate predictions on the target text descriptions, and utilize these predictions as supervision for the corresponding images. Our approach driven by language guidance is surprisingly easy and simple, yet significantly outperforms all prior approaches on challenging datasets like GeoNet and DomainNet, validating its extreme effectiveness. To further extend the scope of our study beyond images, we introduce a new benchmark to study ego-exo transfer in videos and find that our language-aided LaGTran yields significant gains in this highly challenging and non-trivial transfer setting. Code, models, and proposed datasets are publicly available at https://tarun005.github.io/lagtran/.
Authors: Yiqun Yao, Zheng Zhang, Jing Li, Yequan Wang
Abstract: Accelerating large language model pre-training is a critical issue in present research. In this paper, we focus on speeding up pre-training by progressively growing from a small Transformer structure to a large one. There are two main research problems associated with progressive growth: determining the optimal growth schedule, and designing efficient growth operators. In terms of growth schedule, the impact of each single dimension on a schedule's efficiency is under-explored by existing work. Regarding the growth operators, existing methods rely on the initialization of new weights to inherit knowledge, and achieve only non-strict function preservation, limiting further improvements on training dynamics. To address these issues, we propose Masked Structural Growth (MSG), including (i) growth schedules involving all possible dimensions and (ii) strictly function-preserving growth operators that is independent of the initialization of new weights. Experiments show that MSG is significantly faster than related work: we achieve up to 2.2x speedup in pre-training different types of language models while maintaining comparable or better downstream performances. Code is publicly available at https://github.com/cofe-ai/MSG.
Authors: Sohee Yang, Jonghyeon Kim, Joel Jang, Seonghyeon Ye, Hyunji Lee, Minjoon Seo
Abstract: Previous works in prompt engineering for large language models have introduced different gradient-free probability-based prompt selection methods that aim to choose the optimal prompt among the candidates for a given task but have failed to provide a comprehensive and fair comparison between each other. In this paper, we propose a unified framework to interpret and evaluate the existing probability-based prompt selection methods by performing extensive experiments on 13 common and diverse NLP tasks. We find that each of the existing methods can be interpreted as some variant of the method that maximizes mutual information between the input and the predicted output (MI). Utilizing this finding, we develop several other combinatorial variants of MI and increase the effectiveness of the oracle prompt selection method from 87.79% to 94.98%, measured as the ratio of the performance of the selected prompt to that of the optimal oracle prompt. Furthermore, considering that all the methods rely on the output probability distribution of the model that might be biased, we propose a novel calibration method called Calibration by Marginalization (CBM) that is orthogonal to the existing methods and helps increase the prompt selection effectiveness of the best method to 96.85%, achieving 99.44% of the oracle prompt F1 without calibration.
Authors: Yukang Chen, Shengju Qian, Haotian Tang, Xin Lai, Zhijian Liu, Song Han, Jiaya Jia
Abstract: We present LongLoRA, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost. Typically, training LLMs with long context sizes is computationally expensive, requiring extensive training hours and GPU resources. For example, training on the context length of 8192 needs 16x computational costs in self-attention layers as that of 2048. In this paper, we speed up the context extension of LLMs in two aspects. On the one hand, although dense global attention is needed during inference, fine-tuning the model can be effectively and efficiently done by sparse local attention. The proposed shifted sparse attention effectively enables context extension, leading to non-trivial computation saving with similar performance to fine-tuning with vanilla attention. Particularly, it can be implemented with only two lines of code in training, while being optional in inference. On the other hand, we revisit the parameter-efficient fine-tuning regime for context expansion. Notably, we find that LoRA for context extension works well under the premise of trainable embedding and normalization. LongLoRA combines this improved LoRA with S^2-Attn. LongLoRA demonstrates strong empirical results on various tasks on Llama2 models from 7B/13B to 70B. LongLoRA extends Llama2 7B from 4k context to 100k, or Llama2 70B to 32k on a single 8x A100 machine. LongLoRA extends models' context while retaining their original architectures, and is compatible with most existing techniques, like Flash-Attention2. In addition, we further conduct supervised fine-tuning with LongLoRA and our long instruction-following LongAlpaca dataset.
Authors: Tuhin Chakrabarty, Philippe Laban, Divyansh Agarwal, Smaranda Muresan, Chien-Sheng Wu
Abstract: Researchers have argued that large language models (LLMs) exhibit high-quality writing capabilities from blogs to stories. However, evaluating objectively the creativity of a piece of writing is challenging. Inspired by the Torrance Test of Creative Thinking (TTCT), which measures creativity as a process, we use the Consensual Assessment Technique [3] and propose the Torrance Test of Creative Writing (TTCW) to evaluate creativity as a product. TTCW consists of 14 binary tests organized into the original dimensions of Fluency, Flexibility, Originality, and Elaboration. We recruit 10 creative writers and implement a human assessment of 48 stories written either by professional authors or LLMs using TTCW. Our analysis shows that LLM-generated stories pass 3-10X less TTCW tests than stories written by professionals. In addition, we explore the use of LLMs as assessors to automate the TTCW evaluation, revealing that none of the LLMs positively correlate with the expert assessments.
Authors: Hang Shao, Bei Liu, Bo Xiao, Ke Zeng, Guanglu Wan, Yanmin Qian
Abstract: Various Large Language Models(LLMs) from the Generative Pretrained Transformer(GPT) family have achieved outstanding performances in a wide range of text generation tasks. However, the enormous model sizes have hindered their practical use in real-world applications due to high inference latency. Therefore, improving the efficiencies of LLMs through quantization, pruning, and other means has been a key issue in LLM studies. In this work, we propose a method based on Hessian sensitivity-aware mixed sparsity pruning to prune LLMs to at least 50% sparsity without the need of any retraining. It allocates sparsity adaptively based on sensitivity, allowing us to reduce pruning-induced error while maintaining the overall sparsity level. The advantages of the proposed method exhibit even more when the sparsity is extremely high. Furthermore, our method is compatible with quantization, enabling further compression of LLMs.
Authors: Shuaiyi Li, Yang Deng, Wai Lam
Abstract: Spatial reasoning in text plays a crucial role in various real-world applications. Existing approaches for spatial reasoning typically infer spatial relations from pure text, which overlooks the gap between natural language and symbolic structures. Graph neural networks (GNNs) have showcased exceptional proficiency in inducing and aggregating symbolic structures. However, classical GNNs face challenges in handling multi-hop spatial reasoning due to the over-smoothing issue, i.e., the performance decreases substantially as the number of graph layers increases. To cope with these challenges, we propose a novel Depth-Wise Graph Neural Network (DepWiGNN). Specifically, we design a novel node memory scheme and aggregate the information over the depth dimension instead of the breadth dimension of the graph, which empowers the ability to collect long dependencies without stacking multiple layers. Experimental results on two challenging multi-hop spatial reasoning datasets show that DepWiGNN outperforms existing spatial reasoning methods. The comparisons with the other three GNNs further demonstrate its superiority in capturing long dependency in the graph.
Authors: Xilai Ma, Jing Li, Min Zhang
Abstract: Few-shot relation extraction involves identifying the type of relationship between two specific entities within a text, using a limited number of annotated samples. A variety of solutions to this problem have emerged by applying meta-learning and neural graph techniques which typically necessitate a training process for adaptation. Recently, the strategy of in-context learning has been demonstrating notable results without the need of training. Few studies have already utilized in-context learning for zero-shot information extraction. Unfortunately, the evidence for inference is either not considered or implicitly modeled during the construction of chain-of-thought prompts. In this paper, we propose a novel approach for few-shot relation extraction using large language models, named CoT-ER, chain-of-thought with explicit evidence reasoning. In particular, CoT-ER first induces large language models to generate evidences using task-specific and concept-level knowledge. Then these evidences are explicitly incorporated into chain-of-thought prompting for relation extraction. Experimental results demonstrate that our CoT-ER approach (with 0% training data) achieves competitive performance compared to the fully-supervised (with 100% training data) state-of-the-art approach on the FewRel1.0 and FewRel2.0 datasets.
Authors: Ziyi Ye, Qingyao Ai, Yiqun Liu, Maarten de Rijke, Min Zhang, Christina Lioma, Tuukka Ruotsalo
Abstract: Generating human language through non-invasive brain-computer interfaces (BCIs) has the potential to unlock many applications, such as serving disabled patients and improving communication. Currently, however, generating language via BCIs has been previously successful only within a classification setup for selecting pre-generated sentence continuation candidates with the most likely cortical semantic representation. Inspired by recent research that revealed associations between the brain and the large computational language models, we propose a generative language BCI that utilizes the capacity of a large language model (LLM) jointly with a semantic brain decoder to directly generate language from functional magnetic resonance imaging (fMRI) input. The proposed model can generate coherent language sequences aligned with the semantic content of visual or auditory language stimuli perceived, without prior knowledge of any pre-generated candidates. We compare the language generated from the presented model with a random control, pre-generated language selection approach, and a standard LLM, which generates common coherent text solely based on the next word likelihood according to statistical language training data. The proposed model is found to generate language that is more aligned with semantic stimulus in response to which brain input is sampled. Our findings demonstrate the potential and feasibility of employing BCIs in direct language generation.
Authors: Vil\'em Zouhar, V\v{e}ra Kloudov\'a, Martin Popel, Ond\v{r}ej Bojar
Abstract: The overall translation quality reached by current machine translation (MT) systems for high-resourced language pairs is remarkably good. Standard methods of evaluation are not suitable nor intended to uncover the many translation errors and quality deficiencies that still persist. Furthermore, the quality of standard reference translations is commonly questioned and comparable quality levels have been reached by MT alone in several language pairs. Navigating further research in these high-resource settings is thus difficult. In this article, we propose a methodology for creating more reliable document-level human reference translations, called "optimal reference translations," with the simple aim to raise the bar of what should be deemed "human translation quality." We evaluate the obtained document-level optimal reference translations in comparison with "standard" ones, confirming a significant quality increase and also documenting the relationship between evaluation and translation editing.
Authors: Tianyu Yu, Yuan Yao, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, Tat-Seng Chua
Abstract: Multimodal Large Language Models (MLLMs) have recently demonstrated impressive capabilities in multimodal understanding, reasoning, and interaction. However, existing MLLMs prevalently suffer from serious hallucination problems, generating text that is not factually grounded in associated images. The problem makes existing MLLMs untrustworthy and thus impractical in real-world (especially high-stakes) applications. To address the challenge, we present RLHF-V, which enhances MLLM trustworthiness via behavior alignment from fine-grained correctional human feedback. Specifically, RLHF-V collects human preference in the form of segment-level corrections on hallucinations, and performs dense direct preference optimization over the human feedback. Comprehensive experiments on five benchmarks in both automatic and human evaluation show that, RLHF-V can enable substantially more trustworthy MLLM behaviors with promising data and computation efficiency. Remarkably, using 1.4k annotated data samples, RLHF-V significantly reduces the hallucination rate of the base MLLM by 34.8%, outperforming the concurrent LLaVA-RLHF trained on 10k annotated data. The final model achieves state-of-the-art performance in trustworthiness among open-source MLLMs, and shows better robustness than GPT-4V in preventing hallucinations aroused from over-generalization. We open-source our code, model, and data at https://github.com/RLHF-V/RLHF-V.
Authors: Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Jun Zhao, Wei Shen, Yuhao Zhou, Zhiheng Xi, Xiao Wang, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang
Abstract: Supervised fine-tuning (SFT) is a crucial step for large language models (LLMs), enabling them to align with human instructions and enhance their capabilities in downstream tasks. Increasing instruction data substantially is a direct solution to align the model with a broader range of downstream tasks or notably improve its performance on a specific task. However, we find that large-scale increases in instruction data can damage the world knowledge previously stored in LLMs. To address this challenge, we propose LoRAMoE, a novelty framework that introduces several low-rank adapters (LoRA) and integrates them by using a router network, like a plugin version of Mixture of Experts (MoE). It freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge-edge forgetting. Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM.
Authors: Jingwei Yi, Yueqi Xie, Bin Zhu, Emre Kiciman, Guangzhong Sun, Xing Xie, Fangzhao Wu
Abstract: The integration of large language models (LLMs) with external content has enabled more up-to-date and wide-ranging applications of LLMs, such as Microsoft Copilot. However, this integration has also exposed LLMs to the risk of indirect prompt injection attacks, where an attacker can embed malicious instructions within external content, compromising LLM output and causing responses to deviate from user expectations. To investigate this important but underexplored issue, we introduce the first benchmark for indirect prompt injection attacks, named BIPIA, to evaluate the risk of such attacks. Based on the evaluation, our work makes a key analysis of the underlying reason for the success of the attack, namely the inability of LLMs to distinguish between instructions and external content and the absence of LLMs' awareness to not execute instructions within external content. Building upon this analysis, we develop two black-box methods based on prompt learning and a white-box defense method based on fine-tuning with adversarial training accordingly. Experimental results demonstrate that black-box defenses are highly effective in mitigating these attacks, while the white-box defense reduces the attack success rate to near-zero levels. Overall, our work systematically investigates indirect prompt injection attacks by introducing a benchmark, analyzing the underlying reason for the success of the attack, and developing an initial set of defenses.
Authors: Yahui Fu, Haiyue Song, Tianyu Zhao, Tatsuya Kawahara
Abstract: Personality recognition is useful for enhancing robots' ability to tailor user-adaptive responses, thus fostering rich human-robot interactions. One of the challenges in this task is a limited number of speakers in existing dialogue corpora, which hampers the development of robust, speaker-independent personality recognition models. Additionally, accurately modeling both the interdependencies among interlocutors and the intra-dependencies within the speaker in dialogues remains a significant issue. To address the first challenge, we introduce personality trait interpolation for speaker data augmentation. For the second, we propose heterogeneous conversational graph networks to independently capture both contextual influences and inherent personality traits. Evaluations on the RealPersonaChat corpus demonstrate our method's significant improvements over existing baselines.
Authors: Francesco Periti, Haim Dubossarsky, Nina Tahmasebi
Abstract: In the universe of Natural Language Processing, Transformer-based language models like BERT and (Chat)GPT have emerged as lexical superheroes with great power to solve open research problems. In this paper, we specifically focus on the temporal problem of semantic change, and evaluate their ability to solve two diachronic extensions of the Word-in-Context (WiC) task: TempoWiC and HistoWiC. In particular, we investigate the potential of a novel, off-the-shelf technology like ChatGPT (and GPT) 3.5 compared to BERT, which represents a family of models that currently stand as the state-of-the-art for modeling semantic change. Our experiments represent the first attempt to assess the use of (Chat)GPT for studying semantic change. Our results indicate that ChatGPT performs significantly worse than the foundational GPT version. Furthermore, our results demonstrate that (Chat)GPT achieves slightly lower performance than BERT in detecting long-term changes but performs significantly worse in detecting short-term changes.
Authors: Jaavid Aktar Husain, Raj Dabre, Aswanth Kumar, Jay Gala, Thanmay Jayakumar, Ratish Puduppully, Anoop Kunchukuttan
Abstract: This study addresses the challenge of extending Large Language Models (LLMs) to non-English languages using non-Roman scripts. We propose an approach that utilizes the romanized form of text as an interface for LLMs, hypothesizing that its frequent informal use and shared tokens with English enhance cross-lingual alignment. Our approach involves the continual pretraining of an English LLM like Llama 2 on romanized text of non-English, non-Roman script languages, followed by instruction tuning on romanized data. The results indicate that romanized text not only reduces token fertility by 2x-4x but also matches or outperforms native script representation across various NLU, NLG, and MT tasks. Moreover, the embeddings computed on romanized text exhibit closer alignment with their English translations than those from the native script. Our approach presents a promising direction for leveraging the power of English LLMs in languages traditionally underrepresented in NLP.
Authors: Haolun Wu, Ye Yuan, Liana Mikaelyan, Alexander Meulemans, Xue Liu, James Hensman, Bhaskar Mitra
Abstract: Recent advances in machine learning have significantly impacted the field of information extraction, with Large Language Models (LLMs) playing a pivotal role in extracting structured information from unstructured text. This paper explores the challenges and limitations of current methodologies in structured entity extraction and introduces a novel approach to address these issues. We contribute to the field by first introducing and formalizing the task of Structured Entity Extraction (SEE), followed by proposing Approximate Entity Set OverlaP (AESOP) Metric designed to appropriately assess model performance on this task. Later, we propose a new model that harnesses the power of LLMs for enhanced effectiveness and efficiency through decomposing the entire extraction task into multiple stages. Quantitative evaluation and human side-by-side evaluation confirm that our model outperforms baselines, offering promising directions for future advancements in structured entity extraction.
Authors: Francesco Periti, Nina Tahmasebi
Abstract: Contextualized embeddings are the preferred tool for modeling Lexical Semantic Change (LSC). Current evaluations typically focus on a specific task known as Graded Change Detection (GCD). However, performance comparison across work are often misleading due to their reliance on diverse settings. In this paper, we evaluate state-of-the-art models and approaches for GCD under equal conditions. We further break the LSC problem into Word-in-Context (WiC) and Word Sense Induction (WSI) tasks, and compare models across these different levels. Our evaluation is performed across different languages on eight available benchmarks for LSC, and shows that (i) APD outperforms other approaches for GCD; (ii) XL-LEXEME outperforms other contextualized models for WiC, WSI, and GCD, while being comparable to GPT-4; (iii) there is a clear need for improving the modeling of word meanings, as well as focus on how, when, and why these meanings change, rather than solely focusing on the extent of semantic change.
Authors: Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, Dacheng Tao, Tianyi Zhou
Abstract: In the era of Large Language Models (LLMs), Knowledge Distillation (KD) emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their open-source counterparts like LLaMA and Mistral. Additionally, as open-source LLMs flourish, KD plays a crucial role in both compressing these models, and facilitating their self-improvement by employing themselves as teachers. This paper presents a comprehensive survey of KD's role within the realm of LLM, highlighting its critical function in imparting advanced knowledge to smaller models and its utility in model compression and self-improvement. Our survey is meticulously structured around three foundational pillars: \textit{algorithm}, \textit{skill}, and \textit{verticalization} -- providing a comprehensive examination of KD mechanisms, the enhancement of specific cognitive abilities, and their practical implications across diverse fields. Crucially, the survey navigates the intricate interplay between data augmentation (DA) and KD, illustrating how DA emerges as a powerful paradigm within the KD framework to bolster LLMs' performance. By leveraging DA to generate context-rich, skill-specific training data, KD transcends traditional boundaries, enabling open-source models to approximate the contextual adeptness, ethical alignment, and deep semantic insights characteristic of their proprietary counterparts. This work aims to provide an insightful guide for researchers and practitioners, offering a detailed overview of current methodologies in KD and proposing future research directions. Importantly, we firmly advocate for compliance with the legal terms that regulate the use of LLMs, ensuring ethical and lawful application of KD of LLMs. An associated Github repository is available at https://github.com/Tebmer/Awesome-Knowledge-Distillation-of-LLMs.
URLs: https://github.com/Tebmer/Awesome-Knowledge-Distillation-of-LLMs.
Authors: Vamshi Krishna Bonagiri, Sreeram Vennam, Priyanshul Govil, Ponnurangam Kumaraguru, Manas Gaur
Abstract: Despite recent advancements showcasing the impressive capabilities of Large Language Models (LLMs) in conversational systems, we show that even state-of-the-art LLMs are morally inconsistent in their generations, questioning their reliability (and trustworthiness in general). Prior works in LLM evaluation focus on developing ground-truth data to measure accuracy on specific tasks. However, for moral scenarios that often lack universally agreed-upon answers, consistency in model responses becomes crucial for their reliability. To address this issue, we propose an information-theoretic measure called Semantic Graph Entropy (SaGE), grounded in the concept of "Rules of Thumb" (RoTs) to measure a model's moral consistency. RoTs are abstract principles learned by a model and can help explain their decision-making strategies effectively. To this extent, we construct the Moral Consistency Corpus (MCC), containing 50K moral questions, responses to them by LLMs, and the RoTs that these models followed. Furthermore, to illustrate the generalizability of SaGE, we use it to investigate LLM consistency on two popular datasets -- TruthfulQA and HellaSwag. Our results reveal that task-accuracy and consistency are independent problems, and there is a dire need to investigate these issues further.
Authors: Zicheng Lin, Zhibin Gou, Tian Liang, Ruilin Luo, Haowei Liu, Yujiu Yang
Abstract: The ability of Large Language Models (LLMs) to critique and refine their reasoning is crucial for their application in evaluation, feedback provision, and self-improvement. This paper introduces CriticBench, a comprehensive benchmark designed to assess LLMs' abilities to critique and rectify their reasoning across a variety of tasks. CriticBench encompasses five reasoning domains: mathematical, commonsense, symbolic, coding, and algorithmic. It compiles 15 datasets and incorporates responses from three LLM families. Utilizing CriticBench, we evaluate and dissect the performance of 17 LLMs in generation, critique, and correction reasoning, i.e., GQC reasoning. Our findings reveal: (1) a linear relationship in GQC capabilities, with critique-focused training markedly enhancing performance; (2) a task-dependent variation in correction effectiveness, with logic-oriented tasks being more amenable to correction; (3) GQC knowledge inconsistencies that decrease as model size increases; and (4) an intriguing inter-model critiquing dynamic, where stronger models are better at critiquing weaker ones, while weaker models can surprisingly surpass stronger ones in their self-critique. We hope these insights into the nuanced critique-correct reasoning of LLMs will foster further research in LLM critique and self-improvement.
Authors: Bin Zhu, Peng Jin, Munan Ning, Bin Lin, Jinfa Huang, Qi Song, Jiaxi Cui, Junwu Zhang, Zhenyu Tang, Mingjun Pan, Xing Zhou, Li Yuan
Abstract: While recent progress in multimodal large language models tackles various modality tasks, they posses limited integration capabilities for complex multi-modality tasks, consequently constraining the development of the field. In this work, we take the initiative to explore and propose the LLMBind, a unified framework for modality task integration, which binds Large Language Models and corresponding pre-trained task models with task-specific tokens. Consequently, LLMBind can interpret inputs and produce outputs in versatile combinations of image, text, video, and audio. Specifically, we introduce a Mixture-of-Experts technique to enable effective learning for different multimodal tasks through collaboration among diverse experts. Furthermore, we create a multi-task dataset comprising 400k instruction data, which unlocks the ability for interactive visual generation and editing tasks. Extensive experiments show the effectiveness of our framework across various tasks, including image, video, audio generation, image segmentation, and image editing. More encouragingly, our framework can be easily extended to other modality tasks, showcasing the promising potential of creating a unified AI agent for modeling universal modalities.
Authors: Siqi Kou, Lanxiang Hu, Zhezhi He, Zhijie Deng, Hao Zhang
Abstract: Parallel decoding methods such as Jacobi decoding show promise for more efficient LLM inference as it breaks the sequential nature of the LLM decoding process and transforms it into parallelizable computation. However, in practice, it achieves little speedup compared to traditional autoregressive (AR) decoding, primarily because Jacobi decoding seldom accurately predicts more than one token in a single fixed-point iteration step. To address this, we develop a new approach aimed at realizing fast convergence from any state to the fixed point on a Jacobi trajectory. This is accomplished by refining the target LLM to consistently predict the fixed point given any state as input. Extensive experiments demonstrate the effectiveness of our method, showing 2.4$\times$ to 3.4$\times$ improvements in generation speed while preserving generation quality across both domain-specific and open-domain benchmarks.
Authors: Minjin Kim, Minju Kim, Hana Kim, Beong-woo Kwak, Soyeon Chun, Hyunseo Kim, SeongKu Kang, Youngjae Yu, Jinyoung Yeo, Dongha Lee
Abstract: Conversational recommender system is an emerging area that has garnered an increasing interest in the community, especially with the advancements in large language models (LLMs) that enable diverse reasoning over conversational input. Despite the progress, the field has many aspects left to explore. The currently available public datasets for conversational recommendation lack specific user preferences and explanations for recommendations, hindering high-quality recommendations. To address such challenges, we present a novel conversational recommendation dataset named PEARL, synthesized with persona- and knowledge-augmented LLM simulators. We obtain detailed persona and knowledge from real-world reviews and construct a large-scale dataset with over 57k dialogues. Our experimental results demonstrate that utterances in PEARL include more specific user preferences, show expertise in the target domain, and provide recommendations more relevant to the dialogue context than those in prior datasets.
Authors: Shangjian Yin, Peijie Huang, Yuhong Xu, Haojing Huang, Jiatian Chen
Abstract: This study marks a significant advancement by harnessing Large Language Models (LLMs) for multi-intent spoken language understanding (SLU), proposing a unique methodology that capitalizes on the generative power of LLMs within an SLU context. Our innovative technique reconfigures entity slots specifically for LLM application in multi-intent SLU environments and introduces the concept of Sub-Intent Instruction (SII), enhancing the dissection and interpretation of intricate, multi-intent communication within varied domains. The resultant datasets, dubbed LM-MixATIS and LM-MixSNIPS, are crafted from pre-existing benchmarks. Our research illustrates that LLMs can match and potentially excel beyond the capabilities of current state-of-the-art multi-intent SLU models. It further explores LLM efficacy across various intent configurations and dataset proportions. Moreover, we introduce two pioneering metrics, Entity Slot Accuracy (ESA) and Combined Semantic Accuracy (CSA), to provide an in-depth analysis of LLM proficiency in this complex field.
Authors: Queenie Luo, Michael J. Puett, Michael D. Smith
Abstract: Contrary to Google Search's mission of delivering information from "many angles so you can form your own understanding of the world," we find that Google and its most prominent returned results - Wikipedia and YouTube - simply reflect a narrow set of culturally dominant views tied to the search language for complex topics like "Buddhism," "Liberalism," "colonization," "Iran" and "America." Simply stated, they present, to varying degrees, distinct information across the same search in different languages, a phenomenon we call language bias. This paper presents evidence and analysis of language bias and discusses its larger social implications. We find that our online searches and emerging tools like ChatGPT turn us into the proverbial blind person touching a small portion of an elephant, ignorant of the existence of other cultural perspectives. Language bias sets a strong yet invisible cultural barrier online, where each language group thinks they can see other groups through searches, but in fact, what they see is their own reflection.
Authors: Tao Chen, Ze Lin, Hui Li, Jiayi Ji, Yiyi Zhou, Guanbin Li, Rongrong Ji
Abstract: Given the long textual product information and the product image, Multi-modal Product Summarization (MPS) aims to increase customers' desire to purchase by highlighting product characteristics with a short textual summary. Existing MPS methods can produce promising results. Nevertheless, they still 1) lack end-to-end product summarization, 2) lack multi-grained multi-modal modeling, and 3) lack multi-modal attribute modeling. To improve MPS, we propose an end-to-end multi-grained multi-modal attribute-aware product summarization method (MMAPS) for generating high-quality product summaries in e-commerce. MMAPS jointly models product attributes and generates product summaries. We design several multi-grained multi-modal tasks to better guide the multi-modal learning of MMAPS. Furthermore, we model product attributes based on both text and image modalities so that multi-modal product characteristics can be manifested in the generated summaries. Extensive experiments on a real large-scale Chinese e-commence dataset demonstrate that our model outperforms state-of-the-art product summarization methods w.r.t. several summarization metrics. Our code is publicly available at: https://github.com/KDEGroup/MMAPS.
Authors: Norman Mu, Sarah Chen, Zifan Wang, Sizhe Chen, David Karamardian, Lulwa Aljeraisy, Basel Alomair, Dan Hendrycks, David Wagner
Abstract: As Large Language Models (LLMs) are deployed with increasing real-world responsibilities, it is important to be able to specify and constrain the behavior of these systems in a reliable manner. Model developers may wish to set explicit rules for the model, such as "do not generate abusive content", but these may be circumvented by jailbreaking techniques. Existing evaluations of adversarial attacks and defenses on LLMs generally require either expensive manual review or unreliable heuristic checks. To address this issue, we propose Rule-following Language Evaluation Scenarios (RuLES), a programmatic framework for measuring rule-following ability in LLMs. RuLES consists of 14 simple text scenarios in which the model is instructed to obey various rules while interacting with the user. Each scenario has a programmatic evaluation function to determine whether the model has broken any rules in a conversation. Our evaluations of proprietary and open models show that almost all current models struggle to follow scenario rules, even on straightforward test cases. We also demonstrate that simple optimization attacks suffice to significantly increase failure rates on test cases. We conclude by exploring two potential avenues for improvement: test-time steering and supervised fine-tuning.
Authors: Yizhe Zhang, He Bai, Ruixiang Zhang, Jiatao Gu, Shuangfei Zhai, Josh Susskind, Navdeep Jaitly
Abstract: Vision-Language Models (VLMs) such as GPT-4V have recently demonstrated incredible strides on diverse vision language tasks. We dig into vision-based deductive reasoning, a more sophisticated but less explored realm, and find previously unexposed blindspots in the current SOTA VLMs. Specifically, we leverage Raven's Progressive Matrices (RPMs), to assess VLMs' abilities to perform multi-hop relational and deductive reasoning relying solely on visual clues. We perform comprehensive evaluations of several popular VLMs employing standard strategies such as in-context learning, self-consistency, and Chain-of-thoughts (CoT) on three diverse datasets, including the Mensa IQ test, IntelligenceTest, and RAVEN. The results reveal that despite the impressive capabilities of LLMs in text-based reasoning, we are still far from achieving comparable proficiency in visual deductive reasoning. We found that certain standard strategies that are effective when applied to LLMs do not seamlessly translate to the challenges presented by visual reasoning tasks. Moreover, a detailed analysis reveals that VLMs struggle to solve these tasks mainly because they are unable to perceive and comprehend multiple, confounding abstract patterns in RPM examples.