Authors: Boyi Wei, Weijia Shi, Yangsibo Huang, Noah A. Smith, Chiyuan Zhang, Luke Zettlemoyer, Kai Li, Peter Henderson
Abstract: Language models (LMs) derive their capabilities from extensive training on diverse data, including potentially copyrighted material. These models can memorize and generate content similar to their training data, posing potential concerns. Therefore, model creators are motivated to develop mitigation methods that prevent generating protected content. We term this procedure as copyright takedowns for LMs, noting the conceptual similarity to (but legal distinction from) the DMCA takedown This paper introduces the first evaluation of the feasibility and side effects of copyright takedowns for LMs. We propose CoTaEval, an evaluation framework to assess the effectiveness of copyright takedown methods, the impact on the model's ability to retain uncopyrightable factual knowledge from the training data whose recitation is embargoed, and how well the model maintains its general utility and efficiency. We examine several strategies, including adding system prompts, decoding-time filtering interventions, and unlearning approaches. Our findings indicate that no tested method excels across all metrics, showing significant room for research in this unique problem setting and indicating potential unresolved challenges for live policy proposals.
Authors: Guanting Dong, Yutao Zhu, Chenghao Zhang, Zechen Wang, Zhicheng Dou, Ji-Rong Wen
Abstract: Retrieval-augmented generation (RAG) has demonstrated effectiveness in mitigating the hallucination problem of large language models (LLMs). However, the difficulty of aligning the retriever with the diverse LLMs' knowledge preferences inevitably poses an inevitable challenge in developing a reliable RAG system. To address this issue, we propose DPA-RAG, a universal framework designed to align diverse knowledge preferences within RAG systems. Specifically, we initially introduce a preference knowledge construction pipline and incorporate five novel query augmentation strategies to alleviate preference data scarcity. Based on preference data, DPA-RAG accomplishes both external and internal preference alignment: 1) It jointly integrate pair-wise, point-wise, and contrastive preference alignment abilities into the reranker, achieving external preference alignment among RAG components. 2) It further introduces a pre-aligned stage before vanilla Supervised Fine-tuning (SFT), enabling LLMs to implicitly capture knowledge aligned with their reasoning preferences, achieving LLMs' internal alignment. Experimental results across four knowledge-intensive QA datasets demonstrate that DPA-RAG outperforms all baselines and seamlessly integrates both black-box and open-sourced LLM readers. Further qualitative analysis and discussions also provide empirical guidance for achieving reliable RAG systems. Our code is publicly available at https://github.com/dongguanting/DPA-RAG.
Authors: Aakanksha, Arash Ahmadian, Beyza Ermis, Seraphina Goldfarb-Tarrant, Julia Kreutzer, Marzieh Fadaee, Sara Hooker
Abstract: A key concern with the concept of "alignment" is the implicit question of "alignment to what?". AI systems are increasingly used across the world, yet safety alignment is often focused on homogeneous monolingual settings. Additionally, preference training and safety measures often overfit to harms common in Western-centric datasets. Here, we explore the viability of different alignment approaches when balancing dual objectives: addressing and optimizing for a non-homogeneous set of languages and cultural preferences while minimizing both global and local harms. We collect the first set of human annotated red-teaming prompts in different languages distinguishing between global and local harm, which serve as a laboratory for understanding the reliability of alignment techniques when faced with preference distributions that are non-stationary across geographies and languages. While this setting is seldom covered by the literature to date, which primarily centers on English harm mitigation, it captures real-world interactions with AI systems around the world. We establish a new precedent for state-of-the-art alignment techniques across 6 languages with minimal degradation in general performance. Our work provides important insights into cross-lingual transfer and novel optimization approaches to safeguard AI systems designed to serve global populations.
Authors: Quan Mai, Susan Gauch, Douglas Adams, Miaoqing Huang
Abstract: Online debates involve a dynamic exchange of ideas over time, where participants need to actively consider their opponents' arguments, respond with counterarguments, reinforce their own points, and introduce more compelling arguments as the discussion unfolds. Modeling such a complex process is not a simple task, as it necessitates the incorporation of both sequential characteristics and the capability to capture interactions effectively. To address this challenge, we employ a sequence-graph approach. Building the conversation as a graph allows us to effectively model interactions between participants through directed edges. Simultaneously, the propagation of information along these edges in a sequential manner enables us to capture a more comprehensive representation of context. We also introduce a Sequence Graph Attention layer to illustrate the proposed information update scheme. The experimental results show that sequence graph networks achieve superior results to existing methods in online debates.
Authors: Baharan Nouriinanloo, Maxime Lamothe
Abstract: Large Language Models (LLMs) have been revolutionizing a myriad of natural language processing tasks with their diverse zero-shot capabilities. Indeed, existing work has shown that LLMs can be used to great effect for many tasks, such as information retrieval (IR), and passage ranking. However, current state-of-the-art results heavily lean on the capabilities of the LLM being used. Currently, proprietary, and very large LLMs such as GPT-4 are the highest performing passage re-rankers. Hence, users without the resources to leverage top of the line LLMs, or ones that are closed source, are at a disadvantage. In this paper, we investigate the use of a pre-filtering step before passage re-ranking in IR. Our experiments show that by using a small number of human generated relevance scores, coupled with LLM relevance scoring, it is effectively possible to filter out irrelevant passages before re-ranking. Our experiments also show that this pre-filtering then allows the LLM to perform significantly better at the re-ranking task. Indeed, our results show that smaller models such as Mixtral can become competitive with much larger proprietary models (e.g., ChatGPT and GPT-4).
Authors: Shi Zong, Jimmy Lin
Abstract: There have been a huge number of benchmarks proposed to evaluate how large language models (LLMs) behave for logic inference tasks. However, it remains an open question how to properly evaluate this ability. In this paper, we provide a systematic overview of prior works on the logical reasoning ability of LLMs for analyzing categorical syllogisms. We first investigate all the possible variations for the categorical syllogisms from a purely logical perspective and then examine the underlying configurations (i.e., mood and figure) tested by the existing datasets. Our results indicate that compared to template-based synthetic datasets, crowdsourcing approaches normally sacrifice the coverage of configurations (i.e., mood and figure) of categorical syllogisms for more language variations, thus bringing challenges to fully testing LLMs under different situations. We then proceed to summarize the findings and observations for the performances of LLMs to infer the validity of syllogisms from the current literature. The error rate breakdown analyses suggest that the interpretation of the quantifiers seems to be the current bottleneck that limits the performances of the LLMs and is thus worth more attention. Finally, we discuss several points that might be worth considering when researchers plan on the future release of categorical syllogism datasets. We hope our work will not only provide a timely review of the current literature regarding categorical syllogisms, but also motivate more interdisciplinary research between communities, specifically computational linguists and logicians.
Authors: Muhammed Saeed, Peter Bourgonje, Vera Demberg
Abstract: Despite attempts to make Large Language Models multi-lingual, many of the world's languages are still severely under-resourced. This widens the performance gap between NLP and AI applications aimed at well-financed, and those aimed at less-resourced languages. In this paper, we focus on Nigerian Pidgin (NP), which is spoken by nearly 100 million people, but has comparatively very few NLP resources and corpora. We address the task of Implicit Discourse Relation Classification (IDRC) and systematically compare an approach translating NP data to English and then using a well-resourced IDRC tool and back-projecting the labels versus creating a synthetic discourse corpus for NP, in which we translate PDTB and project PDTB labels, and then train an NP IDR classifier. The latter approach of learning a "native" NP classifier outperforms our baseline by 13.27\% and 33.98\% in f$_{1}$ score for 4-way and 11-way classification, respectively.
Authors: Jean Marie Tshimula, D'Jeff K. Nkashama, Jean Tshibangu Muabila, Ren\'e Manass\'e Galekwa, Hugues Kanda, Maximilien V. Dialufuma, Mbuyi Mukendi Didier, Kalala Kalonji, Serge Mundele, Patience Kinshie Lenye, Tighana Wenge Basele, Aristarque Ilunga, Christian N. Mayemba, Nathana\"el M. Kasoro, Selain K. Kasereka, Hardy Mikese, Pierre-Martin Tardif, Marc Frappier, Froduald Kabanza, Belkacem Chikhaoui, Shengrui Wang, Ali Mulenda Sumbu, Xavier Ndona, Raoul Kienge-Kienge Intudi
Abstract: The increasing sophistication of cyber threats necessitates innovative approaches to cybersecurity. In this paper, we explore the potential of psychological profiling techniques, particularly focusing on the utilization of Large Language Models (LLMs) and psycholinguistic features. We investigate the intersection of psychology and cybersecurity, discussing how LLMs can be employed to analyze textual data for identifying psychological traits of threat actors. We explore the incorporation of psycholinguistic features, such as linguistic patterns and emotional cues, into cybersecurity frameworks. \iffalse Through case studies and experiments, we discuss the effectiveness of these methods in enhancing threat detection and mitigation strategies.\fi Our research underscores the importance of integrating psychological perspectives into cybersecurity practices to bolster defense mechanisms against evolving threats.
Authors: Jinguang Wang, Yuexi Yin, Haifeng Sun, Qi Qi, Jingyu Wang, Zirui Zhuang, Tingting Yang, Jianxin Liao
Abstract: Quantizing the activations of large language models (LLMs) has been a significant challenge due to the presence of structured outliers. Most existing methods focus on the per-token or per-tensor quantization of activations, making it difficult to achieve both accuracy and hardware efficiency. To address this problem, we propose OutlierTune, an efficient per-channel post-training quantization (PTQ) method for the activations of LLMs. OutlierTune consists of two components: pre-execution of dequantization and symmetrization. The pre-execution of dequantization updates the model weights by the activation scaling factors, avoiding the internal scaling and costly additional computational overheads brought by the per-channel activation quantization. The symmetrization further reduces the quantization differences arising from the weight updates by ensuring the balanced numerical ranges across different activation channels. OutlierTune is easy to implement and hardware-efficient, introducing almost no additional computational overheads during the inference. Extensive experiments show that the proposed framework outperforms existing methods across multiple different tasks. Demonstrating better generalization, this framework improves the Int6 quantization of the instruction-tuning LLMs, such as OPT-IML, to the same level as half-precision (FP16). Moreover, we have shown that the proposed framework is 1.48x faster than the FP16 implementation while reducing approximately 2x memory usage.
Authors: Qiushi Huang, Shuai Fu, Xubo Liu, Wenwu Wang, Tom Ko, Yu Zhang, Lilian Tang
Abstract: Personalized dialogue generation, focusing on generating highly tailored responses by leveraging persona profiles and dialogue context, has gained significant attention in conversational AI applications. However, persona profiles, a prevalent setting in current personalized dialogue datasets, typically composed of merely four to five sentences, may not offer comprehensive descriptions of the persona about the agent, posing a challenge to generate truly personalized dialogues. To handle this problem, we propose $\textbf{L}$earning Retrieval $\textbf{A}$ugmentation for $\textbf{P}$ersonalized $\textbf{D}$ial$\textbf{O}$gue $\textbf{G}$eneration ($\textbf{LAPDOG}$), which studies the potential of leveraging external knowledge for persona dialogue generation. Specifically, the proposed LAPDOG model consists of a story retriever and a dialogue generator. The story retriever uses a given persona profile as queries to retrieve relevant information from the story document, which serves as a supplementary context to augment the persona profile. The dialogue generator utilizes both the dialogue history and the augmented persona profile to generate personalized responses. For optimization, we adopt a joint training framework that collaboratively learns the story retriever and dialogue generator, where the story retriever is optimized towards desired ultimate metrics (e.g., BLEU) to retrieve content for the dialogue generator to generate personalized responses. Experiments conducted on the CONVAI2 dataset with ROCStory as a supplementary data source show that the proposed LAPDOG method substantially outperforms the baselines, indicating the effectiveness of the proposed method. The LAPDOG model code is publicly available for further exploration. https://github.com/hqsiswiliam/LAPDOG
Authors: Yuxin Fu, Shijing Si, Leyi Mai, Xi-ang Li
Abstract: Large Language Models (LLMs) have stunningly advanced the field of machine translation, though their effectiveness within the financial domain remains largely underexplored. To probe this issue, we constructed a fine-grained Chinese-English parallel corpus of financial news called FFN. We acquired financial news articles spanning between January 1st, 2014, to December 31, 2023, from mainstream media websites such as CNN, FOX, and China Daily. The dataset consists of 1,013 main text and 809 titles, all of which have been manually corrected. We measured the translation quality of two LLMs -- ChatGPT and ERNIE-bot, utilizing BLEU, TER and chrF scores as the evaluation metrics. For comparison, we also trained an OpenNMT model based on our dataset. We detail problems of LLMs and provide in-depth analysis, intending to stimulate further research and solutions in this largely uncharted territory. Our research underlines the need to optimize LLMs within the specific field of financial translation to ensure accuracy and quality.
Authors: Ziyu Yang, Santhosh Cherian, Slobodan Vucetic
Abstract: Radiology reports are highly technical documents aimed primarily at doctor-doctor communication. There has been an increasing interest in sharing those reports with patients, necessitating providing them patient-friendly simplifications of the original reports. This study explores the suitability of large language models in automatically generating those simplifications. We examine the usefulness of chain-of-thought and self-correction prompting mechanisms in this domain. We also propose a new evaluation protocol that employs radiologists and laypeople, where radiologists verify the factual correctness of simplifications, and laypeople assess simplicity and comprehension. Our experimental results demonstrate the effectiveness of self-correction prompting in producing high-quality simplifications. Our findings illuminate the preferences of radiologists and laypeople regarding text simplification, informing future research on this topic.
Authors: Austen Liao, Nicholas Tomlin, Dan Klein
Abstract: Game-playing agents like AlphaGo have achieved superhuman performance through self-play, which is theoretically guaranteed to yield optimal policies in competitive games. However, most language tasks are partially or fully cooperative, so it is an open question whether techniques like self-play can effectively be used to improve language models. We empirically investigate this question in a negotiation game setting known as Deal or No Deal (DoND). Crucially, the objective in DoND can be modified to produce a fully cooperative game, a strictly competitive one, or anything in between. We finetune language models in self-play over multiple rounds of filtered behavior cloning in DoND for each of these objectives. Contrary to expectations, we find that language model self-play leads to significant performance gains in both cooperation and competition with humans, suggesting that self-play and related techniques have promise despite a lack of theoretical guarantees.
Authors: Vipul Rathore, Aniruddha Deb, Ankish Chandresh, Parag Singla, Mausam
Abstract: Recently, very large language models (LLMs) have shown exceptional performance on several English NLP tasks with just in-context learning (ICL), but their utility in other languages is still underexplored. We investigate their effectiveness for NLP tasks in low-resource languages (LRLs), especially in the setting of zero-labelled cross-lingual transfer (0-CLT), where no labelled training data for the target language is available -- however training data from one or more related medium-resource languages (MRLs) is utilized, alongside the available unlabeled test data for a target language. We introduce Self-Supervised Prompting (SSP), a novel ICL approach tailored for the 0-CLT setting. SSP is based on the key observation that LLMs output more accurate labels if in-context exemplars are from the target language (even if their labels are slightly noisy). To operationalize this, since target language training data is not available in 0-CLT, SSP operates in two stages. In Stage I, using source MRL training data, target language's test data is noisily labeled. In Stage II, these noisy test data points are used as exemplars in ICL for further improved labelling. Additionally, our implementation of SSP uses a novel Integer Linear Programming (ILP)-based exemplar selection that balances similarity, prediction confidence (when available) and label coverage. Experiments on three tasks and eleven LRLs (from three regions) demonstrate that SSP strongly outperforms existing SOTA fine-tuned and prompting-based baselines in 0-CLT setup.
Authors: Michael Ginn, Mans Hulden, Alexis Palmer
Abstract: Interlinear glossed text (IGT) is a popular format in language documentation projects, where each morpheme is labeled with a descriptive annotation. Automating the creation of interlinear glossed text can be desirable to reduce annotator effort and maintain consistency across annotated corpora. Prior research has explored a number of statistical and neural methods for automatically producing IGT. As large language models (LLMs) have showed promising results across multilingual tasks, even for rare, endangered languages, it is natural to wonder whether they can be utilized for the task of generating IGT. We explore whether LLMs can be effective at the task of interlinear glossing with in-context learning, without any traditional training. We propose new approaches for selecting examples to provide in-context, observing that targeted selection can significantly improve performance. We find that LLM-based methods beat standard transformer baselines, despite requiring no training at all. These approaches still underperform state-of-the-art supervised systems for the task, but are highly practical for researchers outside of the NLP community, requiring minimal effort to use.
Authors: Melanie Walsh, Anna Preus, Maria Antoniak
Abstract: Large language models (LLMs) can now generate and recognize text in a wide range of styles and genres, including highly specialized, creative genres like poetry. But what do LLMs really know about poetry? What can they know about poetry? We develop a task to evaluate how well LLMs recognize a specific aspect of poetry, poetic form, for more than 20 forms and formal elements in the English language. Poetic form captures many different poetic features, including rhyme scheme, meter, and word or line repetition. We use this task to reflect on LLMs' current poetic capabilities, as well as the challenges and pitfalls of creating NLP benchmarks for poetry and for other creative tasks. In particular, we use this task to audit and reflect on the poems included in popular pretraining datasets. Our findings have implications for NLP researchers interested in model evaluation, digital humanities and cultural analytics scholars, and cultural heritage professionals.
Authors: Michael Ginn, Mans Hulden
Abstract: Dynamic topic models have been proposed as a tool for historical analysis, but traditional approaches have had limited usefulness, being difficult to configure, interpret, and evaluate. In this work, we experiment with a recent approach for dynamic topic modeling using BERT embeddings. We compare topic models built using traditional statistical models (LDA and NMF) and the BERT-based model, modeling topics over the entire surviving corpus of Roman literature. We find that while quantitative metrics prefer statistical models, qualitative evaluation finds better insights from the neural model. Furthermore, the neural topic model is less sensitive to hyperparameter configuration and thus may make dynamic topic modeling more viable for historical researchers.
Authors: Atsushi Ando, Takafumi Moriya, Shota Horiguchi, Ryo Masumura
Abstract: This paper presents a novel speaking-style captioning method that generates diverse descriptions while accurately predicting speaking-style information. Conventional learning criteria directly use original captions that contain not only speaking-style factor terms but also syntax words, which disturbs learning speaking-style information. To solve this problem, we introduce factor-conditioned captioning (FCC), which first outputs a phrase representing speaking-style factors (e.g., gender, pitch, etc.), and then generates a caption to ensure the model explicitly learns speaking-style factors. We also propose greedy-then-sampling (GtS) decoding, which first predicts speaking-style factors deterministically to guarantee semantic accuracy, and then generates a caption based on factor-conditioned sampling to ensure diversity. Experiments show that FCC outperforms the original caption-based training, and with GtS, it generates more diverse captions while keeping style prediction performance.
Authors: Wen Zhang, Long Jin, Yushan Zhu, Jiaoyan Chen, Zhiwei Huang, Junjie Wang, Yin Hua, Lei Liang, Huajun Chen
Abstract: Natural language question answering (QA) over structured data sources such as tables and knowledge graphs (KGs) have been widely investigated, for example with Large Language Models (LLMs). The main solutions include question to formal query parsing and retrieval-based answer generation. However, current methods of the former often suffer from weak generalization, failing to dealing with multiple sources simultaneously, while the later is limited in trustfulness. In this paper, we propose UnifiedTQA, a trustful QA framework that can simultaneously support multiple types of structured data in a unified way. To this end, it adopts an LLM-friendly and unified knowledge representation method called Condition Graph (CG), and uses an LLM and demonstration-based two-level method for CG querying. For enhancement, it is also equipped with dynamic demonstration retrieval. We have evaluated UnifiedTQA with 5 benchmarks covering 3 types of structured data. It outperforms 2 existing unified structured data QA methods and in comparison with the baselines that are specific to a data type, it achieves state-of-the-art on 2 of them. Further more, we demonstrates potential of our method for more general QA tasks, QA over mixed structured data and QA across structured data.
Authors: Yiting Ran, Xintao Wang, Rui Xu, Xinfeng Yuan, Jiaqing Liang, Yanghua Xiao, Deqing Yang
Abstract: Role-playing agents (RPA) have been a popular application area for large language models (LLMs), attracting significant interest from both industry and academia.While existing RPAs well portray the characters' knowledge and tones, they face challenges in capturing their minds, especially for small role-playing language models (RPLMs). In this paper, we propose to enhance RPLMs via personality-indicative data. Specifically, we leverage questions from psychological scales and distill advanced RPAs to generate dialogues that grasp the minds of characters. Experimental results validate that RPLMs trained with our dataset exhibit advanced role-playing capabilities for both general and personality-related evaluations. Code and data are available at \href{https://github.com/alienet1109/RolePersonality}{this URL}.
Authors: Jiwan Chung, Sungjae Lee, Minseo Kim, Seungju Han, Ashkan Yousefpour, Jack Hessel, Youngjae Yu
Abstract: Visual arguments, often used in advertising or social causes, rely on images to persuade viewers to do or believe something. Understanding these arguments requires selective vision: only specific visual stimuli within an image are relevant to the argument, and relevance can only be understood within the context of a broader argumentative structure. While visual arguments are readily appreciated by human audiences, we ask: are today's AI capable of similar understanding? We collect and release VisArgs, an annotated corpus designed to make explicit the (usually implicit) structures underlying visual arguments. VisArgs includes 1,611 images accompanied by three types of textual annotations: 5,112 visual premises (with region annotations), 5,574 commonsense premises, and reasoning trees connecting them to a broader argument. We propose three tasks over VisArgs to probe machine capacity for visual argument understanding: localization of premises, identification of premises, and deduction of conclusions. Experiments demonstrate that 1) machines cannot fully identify the relevant visual cues. The top-performing model, GPT-4-O, achieved an accuracy of only 78.5%, whereas humans reached 98.0%. All models showed a performance drop, with an average decrease in accuracy of 19.5%, when the comparison set was changed from objects outside the image to irrelevant objects within the image. Furthermore, 2) this limitation is the greatest factor impacting their performance in understanding visual arguments. Most models improved the most when given relevant visual premises as additional inputs, compared to other inputs, for deducing the conclusion of the visual argument.
Authors: Siyuan Wu, Yue Huang, Chujie Gao, Dongping Chen, Qihui Zhang, Yao Wan, Tianyi Zhou, Xiangliang Zhang, Jianfeng Gao, Chaowei Xiao, Lichao Sun
Abstract: Large Language Models (LLMs) such as GPT-4 and Llama3 have significantly impacted various fields by enabling high-quality synthetic data generation and reducing dependence on expensive human-generated datasets. Despite this, challenges remain in the areas of generalization, controllability, diversity, and truthfulness within the existing generative frameworks. To address these challenges, this paper presents UniGen, a comprehensive LLM-powered framework designed to produce diverse, accurate, and highly controllable datasets. UniGen is adaptable, supporting all types of text datasets and enhancing the generative process through innovative mechanisms. To augment data diversity, UniGen incorporates an attribute-guided generation module and a group checking feature. For accuracy, it employs a code-based mathematical assessment for label verification alongside a retrieval-augmented generation technique for factual validation. The framework also allows for user-specified constraints, enabling customization of the data generation process to suit particular requirements. Extensive experiments demonstrate the superior quality of data generated by UniGen, and each module within UniGen plays a critical role in this enhancement. Additionally, UniGen is applied in two practical scenarios: benchmarking LLMs and data augmentation. The results indicate that UniGen effectively supports dynamic and evolving benchmarking, and that data augmentation improves LLM capabilities in various domains, including agent-oriented abilities and reasoning skills.
Authors: Yue Guo, Yi Yang
Abstract: Large language models (LLMs) are now rapidly advancing and surpassing human abilities on many natural language tasks. However, aligning these super-human LLMs with human knowledge remains challenging because the supervision signals from human annotators may be wrong. This issue, known as the "super-alignment" problem, requires enhancing weak-to-strong generalization, where a strong LLM must generalize from imperfect supervision provided by a weaker source. To address this issue, we propose an approach to improve weak-to-strong generalization by involving the reliability of weak supervision signals in the alignment process. In our method, we query the weak supervisor for multiple answers, estimate the answer reliability, and enhance the alignment process by filtering out uncertain data or re-weighting reliable data. Experiments on four datasets demonstrate that our methods effectively identify the quality of weak labels and significantly enhance weak-to-strong generalization. Our work presents effective techniques for error-robust model alignment, reducing error propagation from noisy supervision and enhancing the accuracy and reliability of LLMs. Codes are publicly available at http://github.com/Irenehere/ReliableAlignment.
Authors: Wenbin Li, Di Yao, Ruibo Zhao, Wenjie Chen, Zijie Xu, Chengxue Luo, Chang Gong, Quanliang Jing, Haining Tan, Jingping Bi
Abstract: The rapid evolution of large language models (LLMs) holds promise for reforming the methodology of spatio-temporal data mining. However, current works for evaluating the spatio-temporal understanding capability of LLMs are somewhat limited and biased. These works either fail to incorporate the latest language models or only focus on assessing the memorized spatio-temporal knowledge. To address this gap, this paper dissects LLMs' capability of spatio-temporal data into four distinct dimensions: knowledge comprehension, spatio-temporal reasoning, accurate computation, and downstream applications. We curate several natural language question-answer tasks for each category and build the benchmark dataset, namely STBench, containing 13 distinct tasks and over 60,000 QA pairs. Moreover, we have assessed the capabilities of 13 LLMs, such as GPT-4o, Gemma and Mistral. Experimental results reveal that existing LLMs show remarkable performance on knowledge comprehension and spatio-temporal reasoning tasks, with potential for further enhancement on other tasks through in-context learning, chain-of-though prompting, and fine-tuning. The code and datasets of STBench are released on https://github.com/LwbXc/STBench.
Authors: Ondrej Sotolar
Abstract: Empathetic response generation is a desirable aspect of conversational agents, crucial for facilitating engaging and emotionally intelligent multi-turn conversations between humans and machines. Leveraging large language models for this task has shown promising results, yet challenges persist in ensuring both the empathetic quality of the responses and retention of the generalization performance of the models. In this paper, we propose a novel approach where we construct theory-driven preference datasets and use them to align LLMs with preference optimization algorithms to address these challenges. To measure empathetic response generation, we employ the EmpatheticDialogues dataset, assessing empathy with the diff-EPITOME and BERTscore metrics, and evaluate the generalization performance on the MMLU benchmark. We make all datasets, source code, and models publicly available.
Authors: Irina Saparina, Mirella Lapata
Abstract: Practical semantic parsers are expected to understand user utterances and map them to executable programs, even when these are ambiguous. We introduce a new benchmark, AMBROSIA, which we hope will inform and inspire the development of text-to-SQL parsers capable of recognizing and interpreting ambiguous requests. Our dataset contains questions showcasing three different types of ambiguity (scope ambiguity, attachment ambiguity, and vagueness), their interpretations, and corresponding SQL queries. In each case, the ambiguity persists even when the database context is provided. This is achieved through a novel approach that involves controlled generation of databases from scratch. We benchmark various LLMs on AMBROSIA, revealing that even the most advanced models struggle to identify and interpret ambiguity in questions.
Authors: Tosin Adewumi, Lama Alkhaled, Namrata Gurung, Goya van Boven, Irene Pagliai
Abstract: The importance of addressing fairness and bias in artificial intelligence (AI) systems cannot be over-emphasized. Mainstream media has been awashed with news of incidents around stereotypes and bias in many of these systems in recent years. In this survey, we fill a gap with regards to the minimal study of fairness and bias in Large Multimodal Models (LMMs) compared to Large Language Models (LLMs), providing 50 examples of datasets and models along with the challenges affecting them; we identify a new category of quantifying bias (preuse), in addition to the two well-known ones in the literature: intrinsic and extrinsic; we critically discuss the various ways researchers are addressing these challenges. Our method involved two slightly different search queries on Google Scholar, which revealed that 33,400 and 538,000 links are the results for the terms "Fairness and bias in Large Multimodal Models" and "Fairness and bias in Large Language Models", respectively. We believe this work contributes to filling this gap and providing insight to researchers and other stakeholders on ways to address the challenge of fairness and bias in multimodal A!.
Authors: Lokesh Mishra, Sohayl Dhibi, Yusik Kim, Cesar Berrospi Ramis, Shubham Gupta, Michele Dolfi, Peter Staar
Abstract: Environment, Social, and Governance (ESG) KPIs assess an organization's performance on issues such as climate change, greenhouse gas emissions, water consumption, waste management, human rights, diversity, and policies. ESG reports convey this valuable quantitative information through tables. Unfortunately, extracting this information is difficult due to high variability in the table structure as well as content. We propose Statements, a novel domain agnostic data structure for extracting quantitative facts and related information. We propose translating tables to statements as a new supervised deep-learning universal information extraction task. We introduce SemTabNet - a dataset of over 100K annotated tables. Investigating a family of T5-based Statement Extraction Models, our best model generates statements which are 82% similar to the ground-truth (compared to baseline of 21%). We demonstrate the advantages of statements by applying our model to over 2700 tables from ESG reports. The homogeneous nature of statements permits exploratory data analysis on expansive information found in large collections of ESG reports.
Authors: Hsuvas Borkakoty, Luis Espinosa-Anke
Abstract: We introduce CHEW, a novel dataset of changing events in Wikipedia expressed in naturally occurring text. We use CHEW for probing LLMs for their timeline understanding of Wikipedia entities and events in generative and classification experiments. Our results suggest that LLMs, despite having temporal information available, struggle to construct accurate timelines. We further show the usefulness of CHEW-derived embeddings for identifying meaning shift.
Authors: Judith Sieker, Simeon Junker, Ronja Utescher, Nazia Attari, Heiko Wersing, Hendrik Buschmeier, Sina Zarrie{\ss}
Abstract: We examine how users perceive the limitations of an AI system when it encounters a task that it cannot perform perfectly and whether providing explanations alongside its answers aids users in constructing an appropriate mental model of the system's capabilities and limitations. We employ a visual question answer and explanation task where we control the AI system's limitations by manipulating the visual inputs: during inference, the system either processes full-color or grayscale images. Our goal is to determine whether participants can perceive the limitations of the system. We hypothesize that explanations will make limited AI capabilities more transparent to users. However, our results show that explanations do not have this effect. Instead of allowing users to more accurately assess the limitations of the AI system, explanations generally increase users' perceptions of the system's competence - regardless of its actual performance.
Authors: Gabriel Bernier-Colborne, Sowmya Vajjala
Abstract: Named Entity Recognition (NER) is a well-studied problem in NLP. However, there is much less focus on studying NER datasets, compared to developing new NER models. In this paper, we employed three simple techniques to detect annotation errors in the OntoNotes 5.0 corpus for English NER, which is the largest available NER corpus for English. Our techniques corrected ~10% of the sentences in train/dev/test data. In terms of entity mentions, we corrected the span and/or type of ~8% of mentions in the dataset, while adding/deleting/splitting/merging a few more. These are large numbers of changes, considering the size of OntoNotes. We used three NER libraries to train, evaluate and compare the models trained with the original and the re-annotated datasets, which showed an average improvement of 1.23% in overall F-scores, with large (>10%) improvements for some of the entity types. While our annotation error detection methods are not exhaustive and there is some manual annotation effort involved, they are largely language agnostic and can be employed with other NER datasets, and other sequence labelling tasks.
Authors: Zijun Yao, Weijian Qi, Liangming Pan, Shulin Cao, Linmei Hu, Weichuan Liu, Lei Hou, Juanzi Li
Abstract: This paper introduces Self-aware Knowledge Retrieval (SeaKR), a novel adaptive RAG model that extracts self-aware uncertainty of LLMs from their internal states. SeaKR activates retrieval when the LLMs present high self-aware uncertainty for generation. To effectively integrate retrieved knowledge snippets, SeaKR re-ranks them based on LLM's self-aware uncertainty to preserve the snippet that reduces their uncertainty to the utmost. To facilitate solving complex tasks that require multiple retrievals, SeaKR utilizes their self-aware uncertainty to choose among different reasoning strategies. Our experiments on both complex and simple Question Answering datasets show that SeaKR outperforms existing adaptive RAG methods. We release our code at https://github.com/THU-KEG/SeaKR.
Authors: Bj\"orn Deiseroth, Manuel Brack, Patrick Schramowski, Kristian Kersting, Samuel Weinbach
Abstract: Tokenizers are crucial for encoding information in Large Language Models, but their development has recently stagnated, and they contain inherent weaknesses. Major limitations include computational overhead, ineffective vocabulary use, and unnecessarily large embedding and head layers. Additionally, their performance is biased towards a reference corpus, leading to reduced effectiveness for underrepresented languages. To remedy these issues, we propose T-FREE, which directly embeds words through sparse activation patterns over character triplets, and does not require a reference corpus. T-FREE inherently exploits morphological similarities and allows for strong compression of embedding layers. In our exhaustive experimental evaluation, we achieve competitive downstream performance with a parameter reduction of more than 85% on these layers. Further, T-FREE shows significant improvements in cross-lingual transfer learning.
Authors: Zheyuan Zhang, Daniel Zhang-Li, Jifan Yu, Linlu Gong, Jinchang Zhou, Zhiyuan Liu, Lei Hou, Juanzi Li
Abstract: Large language models (LLMs) have been employed in various intelligent educational tasks to assist teaching. While preliminary explorations have focused on independent LLM-empowered agents for specific educational tasks, the potential for LLMs within a multi-agent collaborative framework to simulate a classroom with real user participation remains unexplored. In this work, we propose SimClass, a multi-agent classroom simulation framework involving user participation. We recognize representative class roles and introduce a novel class control mechanism for automatic classroom teaching, and conduct user experiments in two real-world courses. Utilizing the Flanders Interactive Analysis System and Community of Inquiry theoretical frame works from educational analysis, we demonstrate that LLMs can simulate traditional classroom interaction patterns effectively while enhancing user's experience. We also observe emergent group behaviors among agents in SimClass, where agents collaborate to create enlivening interactions in classrooms to improve user learning process. We hope this work pioneers the application of LLM-empowered multi-agent systems in virtual classroom teaching.
Authors: Yantao Liu, Zhao Zhang, Zijun Yao, Shulin Cao, Lei Hou, Juanzi Li
Abstract: Large Language Models (LLMs) have shown significant promise as copilots in various tasks. Local deployment of LLMs on edge devices is necessary when handling privacy-sensitive data or latency-sensitive tasks. The computational constraints of such devices make direct deployment of powerful large-scale LLMs impractical, necessitating the Knowledge Distillation from large-scale models to lightweight models. Lots of work has been done to elicit diversity and quality training examples from LLMs, but little attention has been paid to aligning teacher instructional content based on student preferences, akin to "responsive teaching" in pedagogy. Thus, we propose ARTE, dubbed Aligning TeacheR with StudenT PreferencEs, a framework that aligns the teacher model with student preferences to generate tailored training examples for Knowledge Distillation. Specifically, we elicit draft questions and rationales from the teacher model, then collect student preferences on these questions and rationales using students' performance with in-context learning as a proxy, and finally align the teacher model with student preferences. In the end, we repeat the first step with the aligned teacher model to elicit tailored training examples for the student model on the target task. Extensive experiments on academic benchmarks demonstrate the superiority of ARTE over existing instruction-tuning datasets distilled from powerful LLMs. Moreover, we thoroughly investigate the generalization of ARTE, including the generalization of fine-tuned student models in reasoning ability and the generalization of aligned teacher models to generate tailored training data across tasks and students. In summary, our contributions lie in proposing a novel framework for tailored training example generation, demonstrating its efficacy in experiments, and investigating the generalization of both student & aligned teacher models in ARTE.
Authors: Jimin Sun, So Yeon Min, Yingshan Chang, Yonatan Bisk
Abstract: Tools have become a mainstay of LLMs, allowing them to retrieve knowledge not in their weights, to perform tasks on the web, and even to control robots. However, most ontologies and surveys of tool-use have assumed the core challenge for LLMs is choosing the tool. Instead, we introduce a framework for tools more broadly which guides us to explore a model's ability to detect "silent" tool errors, and reflect on how to plan. This more directly aligns with the increasingly popular use of models as tools. We provide an initial approach to failure recovery with promising results both on a controlled calculator setting and embodied agent planning.
Authors: Ekaterina Taktasheva, Maxim Bazhukov, Kirill Koncha, Alena Fenogenova, Ekaterina Artemova
Abstract: Minimal pairs are a well-established approach to evaluating the grammatical knowledge of language models. However, existing resources for minimal pairs address a limited number of languages and lack diversity of language-specific grammatical phenomena. This paper introduces the Russian Benchmark of Linguistic Minimal Pairs (RuBLiMP), which includes 45k pairs of sentences that differ in grammaticality and isolate a morphological, syntactic, or semantic phenomenon. In contrast to existing benchmarks of linguistic minimal pairs, RuBLiMP is created by applying linguistic perturbations to automatically annotated sentences from open text corpora and carefully curating test data. We describe the data collection protocol and present the results of evaluating 25 language models in various scenarios. We find that the widely used language models for Russian are sensitive to morphological and agreement-oriented contrasts but fall behind humans on phenomena requiring understanding of structural relations, negation, transitivity, and tense. RuBLiMP, the codebase, and other materials are publicly available.
Authors: Shubhankar Singh, Purvi Chaurasia, Yerram Varun, Pranshu Pandya, Vatsal Gupta, Vivek Gupta, Dan Roth
Abstract: Existing benchmarks for visual question answering lack in visual grounding and complexity, particularly in evaluating spatial reasoning skills. We introduce FlowVQA, a novel benchmark aimed at assessing the capabilities of visual question-answering multimodal language models in reasoning with flowcharts as visual contexts. FlowVQA comprises 2,272 carefully generated and human-verified flowchart images from three distinct content sources, along with 22,413 diverse question-answer pairs, to test a spectrum of reasoning tasks, including information localization, decision-making, and logical progression. We conduct a thorough baseline evaluation on a suite of both open-source and proprietary multimodal language models using various strategies, followed by an analysis of directional bias. The results underscore the benchmark's potential as a vital tool for advancing the field of multimodal modeling, providing a focused and challenging environment for enhancing model performance in visual and logical reasoning tasks.
Authors: Dustin Wright, Arnav Arora, Nadav Borenstein, Srishti Yadav, Serge Belongie, Isabelle Augenstein
Abstract: Uncovering latent values and opinions in large language models (LLMs) can help identify biases and mitigate potential harm. Recently, this has been approached by presenting LLMs with survey questions and quantifying their stances towards morally and politically charged statements. However, the stances generated by LLMs can vary greatly depending on how they are prompted, and there are many ways to argue for or against a given position. In this work, we propose to address this by analysing a large and robust dataset of 156k LLM responses to the 62 propositions of the Political Compass Test (PCT) generated by 6 LLMs using 420 prompt variations. We perform coarse-grained analysis of their generated stances and fine-grained analysis of the plain text justifications for those stances. For fine-grained analysis, we propose to identify tropes in the responses: semantically similar phrases that are recurrent and consistent across different prompts, revealing patterns in the text that a given LLM is prone to produce. We find that demographic features added to prompts significantly affect outcomes on the PCT, reflecting bias, as well as disparities between the results of tests when eliciting closed-form vs. open domain responses. Additionally, patterns in the plain text rationales via tropes show that similar justifications are repeatedly generated across models and prompts even with disparate stances.
Authors: Jia Fu, Xiaoting Qin, Fangkai Yang, Lu Wang, Jue Zhang, Qingwei Lin, Yubo Chen, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
Abstract: Recent advancements in Large Language Models have transformed ML/AI development, necessitating a reevaluation of AutoML principles for the Retrieval-Augmented Generation (RAG) systems. To address the challenges of hyper-parameter optimization and online adaptation in RAG, we propose the AutoRAG-HP framework, which formulates the hyper-parameter tuning as an online multi-armed bandit (MAB) problem and introduces a novel two-level Hierarchical MAB (Hier-MAB) method for efficient exploration of large search spaces. We conduct extensive experiments on tuning hyper-parameters, such as top-k retrieved documents, prompt compression ratio, and embedding methods, using the ALCE-ASQA and Natural Questions datasets. Our evaluation from jointly optimization all three hyper-parameters demonstrate that MAB-based online learning methods can achieve Recall@5 $\approx 0.8$ for scenarios with prominent gradients in search space, using only $\sim20\%$ of the LLM API calls required by the Grid Search approach. Additionally, the proposed Hier-MAB approach outperforms other baselines in more challenging optimization scenarios. The code will be made available at https://aka.ms/autorag.
URLs: https://aka.ms/autorag.
Authors: Yue Fan, Lei Ding, Ching-Chen Kuo, Shan Jiang, Yang Zhao, Xinze Guan, Jie Yang, Yi Zhang, Xin Eric Wang
Abstract: Graphical User Interfaces (GUIs) are central to our interaction with digital devices. Recently, growing efforts have been made to build models for various GUI understanding tasks. However, these efforts largely overlook an important GUI-referring task: screen reading based on user-indicated points, which we name the Screen Point-and-Read (SPR) task. This task is predominantly handled by rigid accessible screen reading tools, in great need of new models driven by advancements in Multimodal Large Language Models (MLLMs). In this paper, we propose a Tree-of-Lens (ToL) agent, utilizing a novel ToL grounding mechanism, to address the SPR task. Based on the input point coordinate and the corresponding GUI screenshot, our ToL agent constructs a Hierarchical Layout Tree. Based on the tree, our ToL agent not only comprehends the content of the indicated area but also articulates the layout and spatial relationships between elements. Such layout information is crucial for accurately interpreting information on the screen, distinguishing our ToL agent from other screen reading tools. We also thoroughly evaluate the ToL agent against other baselines on a newly proposed SPR benchmark, which includes GUIs from mobile, web, and operating systems. Last but not least, we test the ToL agent on mobile GUI navigation tasks, demonstrating its utility in identifying incorrect actions along the path of agent execution trajectories. Code and data: screen-point-and-read.github.io
Authors: Praneeth Vadlapati
Abstract: Up-to-date and reliable Large Language Models (LLMs) are consistently sought after. Typically, LLMs are trained on a fixed dataset and then deployed. However, the training data continually becomes outdated. Enable automatic training of AI using web data involves significant concerns regarding data quality and safety due to bias, spam, and other unsafe or unwanted text. Pure data is essential for producing reliable models. Training a model on impure data may result in undesirable outcomes. This research proposes a system that collects web data and automatically filters out unwanted text with the assistance of existing trusted AI models. In the experiment, a small sample of web data was collected and filtered, demonstrating the system's effectiveness in purifying the data.
Authors: Yixiao Song, Yekyung Kim, Mohit Iyyer
Abstract: Existing metrics for evaluating the factuality of long-form text, such as FACTSCORE (Min et al., 2023) and SAFE (Wei et al., 2024), decompose an input text into "atomic claims" and verify each against a knowledge base like Wikipedia. These metrics are not suitable for most generation tasks because they assume that every claim is verifiable (i.e., can plausibly be proven true or false). We address this issue with VERISCORE, a metric for diverse long-form generation tasks that contain both verifiable and unverifiable content. VERISCORE can be effectively implemented with either closed or fine-tuned open-weight language models, and human evaluation confirms that VERISCORE's extracted claims are more sensible than those from competing methods across eight different long-form tasks. We use VERISCORE to evaluate generations from 16 different models across multiple long-form tasks and find that while GPT-4o is the best-performing model overall, open-weight models such as Mixtral-8x22 are closing the gap. We show that an LM's VERISCORE on one task (e.g., biography generation) does not necessarily correlate to its VERISCORE on a different task (e.g., long-form QA), highlighting the need for expanding factuality evaluation across tasks with varying fact density.
Authors: Shaobo Cui, Zhijing Jin, Bernhard Sch\"olkopf, Boi Faltings
Abstract: Understanding commonsense causality is a unique mark of intelligence for humans. It helps people understand the principles of the real world better and benefits the decision-making process related to causation. For instance, commonsense causality is crucial in judging whether a defendant's action causes the plaintiff's loss in determining legal liability. Despite its significance, a systematic exploration of this topic is notably lacking. Our comprehensive survey bridges this gap by focusing on taxonomies, benchmarks, acquisition methods, qualitative reasoning, and quantitative measurements in commonsense causality, synthesizing insights from over 200 representative articles. Our work aims to provide a systematic overview, update scholars on recent advancements, provide a pragmatic guide for beginners, and highlight promising future research directions in this vital field.
Authors: Colin White, Samuel Dooley, Manley Roberts, Arka Pal, Ben Feuer, Siddhartha Jain, Ravid Shwartz-Ziv, Neel Jain, Khalid Saifullah, Siddartha Naidu, Chinmay Hegde, Yann LeCun, Tom Goldstein, Willie Neiswanger, Micah Goldblum
Abstract: Test set contamination, wherein test data from a benchmark ends up in a newer model's training set, is a well-documented obstacle for fair LLM evaluation and can quickly render benchmarks obsolete. To mitigate this, many recent benchmarks crowdsource new prompts and evaluations from human or LLM judges; however, these can introduce significant biases, and break down when scoring hard questions. In this work, we introduce a new benchmark for LLMs designed to be immune to both test set contamination and the pitfalls of LLM judging and human crowdsourcing. We release LiveBench, the first benchmark that (1) contains frequently-updated questions from recent information sources, (2) scores answers automatically according to objective ground-truth values, and (3) contains a wide variety of challenging tasks, spanning math, coding, reasoning, language, instruction following, and data analysis. To achieve this, LiveBench contains questions that are based on recently-released math competitions, arXiv papers, news articles, and datasets, and it contains harder, contamination-free versions of tasks from previous benchmarks such as Big-Bench Hard, AMPS, and IFEval. We evaluate many prominent closed-source models, as well as dozens of open-source models ranging from 0.5B to 110B in size. LiveBench is difficult, with top models achieving below 65% accuracy. We release all questions, code, and model answers. Questions will be added and updated on a monthly basis, and we will release new tasks and harder versions of tasks over time so that LiveBench can distinguish between the capabilities of LLMs as they improve in the future. We welcome community engagement and collaboration for expanding the benchmark tasks and models.
Authors: Lucky Susanto, Musa Izzanardi Wijanarko, Prasetia Anugrah Pratama, Traci Hong, Ika Idris, Alham Fikri Aji, Derry Wijaya
Abstract: Hate speech poses a significant threat to social harmony. Over the past two years, Indonesia has seen a ten-fold increase in the online hate speech ratio, underscoring the urgent need for effective detection mechanisms. However, progress is hindered by the limited availability of labeled data for Indonesian texts. The condition is even worse for marginalized minorities, such as Shia, LGBTQ, and other ethnic minorities because hate speech is underreported and less understood by detection tools. Furthermore, the lack of accommodation for subjectivity in current datasets compounds this issue. To address this, we introduce IndoToxic2024, a comprehensive Indonesian hate speech and toxicity classification dataset. Comprising 43,692 entries annotated by 19 diverse individuals, the dataset focuses on texts targeting vulnerable groups in Indonesia, specifically during the hottest political event in the country: the presidential election. We establish baselines for seven binary classification tasks, achieving a macro-F1 score of 0.78 with a BERT model (IndoBERTweet) fine-tuned for hate speech classification. Furthermore, we demonstrate how incorporating demographic information can enhance the zero-shot performance of the large language model, gpt-3.5-turbo. However, we also caution that an overemphasis on demographic information can negatively impact the fine-tuned model performance due to data fragmentation.
Authors: Peter Hase, Thomas Hofweber, Xiang Zhou, Elias Stengel-Eskin, Mohit Bansal
Abstract: The model editing problem concerns how language models should learn new facts about the world over time. While empirical research on model editing has drawn widespread attention, the conceptual foundations of model editing remain shaky -- perhaps unsurprisingly, since model editing is essentially belief revision, a storied problem in philosophy that has eluded succinct solutions for decades. Model editing nonetheless demands a solution, since we need to be able to control the knowledge within language models. With this goal in mind, this paper critiques the standard formulation of the model editing problem and proposes a formal testbed for model editing research. We first describe 12 open problems with model editing, based on challenges with (1) defining the problem, (2) developing benchmarks, and (3) assuming LLMs have editable beliefs in the first place. Many of these challenges are extremely difficult to address, e.g. determining far-reaching consequences of edits, labeling probabilistic entailments between facts, and updating beliefs of agent simulators. Next, we introduce a semi-synthetic dataset for model editing based on Wikidata, where we can evaluate edits against labels given by an idealized Bayesian agent. This enables us to say exactly how belief revision in language models falls short of a desirable epistemic standard. We encourage further research exploring settings where such a gold standard can be compared against. Our code is publicly available at: https://github.com/peterbhase/LLM-belief-revision
Authors: Nigel Fernandez, Alexander Scarlatos, Simon Woodhead, Andrew Lan
Abstract: High-quality distractors are crucial to both the assessment and pedagogical value of multiple-choice questions (MCQs), where manually crafting ones that anticipate knowledge deficiencies or misconceptions among real students is difficult. Meanwhile, automated distractor generation, even with the help of large language models (LLMs), remains challenging for subjects like math. It is crucial to not only identify plausible distractors but also understand the error behind them. In this paper, we introduce DiVERT (Distractor Generation with Variational Errors Represented as Text), a novel variational approach that learns an interpretable representation of errors behind distractors in math MCQs. Through experiments on a real-world math MCQ dataset with 1,434 questions used by hundreds of thousands of students, we show that DiVERT, despite using a base open-source LLM with 7B parameters, outperforms state-of-the-art approaches using GPT-4o on downstream distractor generation. We also conduct a human evaluation with math educators and find that DiVERT leads to error labels that are of comparable quality to human-authored ones.
Authors: Xiliang Zhu, Shayna Gardiner, Tere Rold\'an, David Rossouw
Abstract: Sentiment analysis serves as a pivotal component in Natural Language Processing (NLP). Advancements in multilingual pre-trained models such as XLM-R and mT5 have contributed to the increasing interest in cross-lingual sentiment analysis. The recent emergence in Large Language Models (LLM) has significantly advanced general NLP tasks, however, the capability of such LLMs in cross-lingual sentiment analysis has not been fully studied. This work undertakes an empirical analysis to compare the cross-lingual transfer capability of public Small Multilingual Language Models (SMLM) like XLM-R, against English-centric LLMs such as Llama-3, in the context of sentiment analysis across English, Spanish, French and Chinese. Our findings reveal that among public models, SMLMs exhibit superior zero-shot cross-lingual performance relative to LLMs. However, in few-shot cross-lingual settings, public LLMs demonstrate an enhanced adaptive potential. In addition, we observe that proprietary GPT-3.5 and GPT-4 lead in zero-shot cross-lingual capability, but are outpaced by public models in few-shot scenarios.
Authors: Chau Minh Pham, Simeng Sun, Mohit Iyyer
Abstract: Existing research on instruction following largely focuses on tasks with simple instructions and short responses. In this work, we explore multi-constraint instruction following for generating long-form text. We create Suri, a dataset with 20K human-written long-form texts paired with LLM-generated backtranslated instructions that contain multiple complex constraints. Because of prohibitive challenges associated with collecting human preference judgments on long-form texts, preference-tuning algorithms such as DPO are infeasible in our setting; thus, we propose Instructional ORPO (I-ORPO), an alignment method based on the ORPO algorithm. Instead of receiving negative feedback from dispreferred responses, I-ORPO obtains negative feedback from synthetically corrupted instructions generated by an LLM. Using Suri, we perform supervised and I-ORPO fine-tuning on Mistral-7b-Instruct-v0.2. The resulting models, Suri-SFT and Suri-I-ORPO, generate significantly longer texts (~5K tokens) than base models without significant quality deterioration. Our human evaluation shows that while both SFT and I-ORPO models satisfy most constraints, Suri-I-ORPO generations are generally preferred for their coherent and informative incorporation of the constraints. We release our code at https://github.com/chtmp223/suri.
Authors: Kukjin Choi, Jihun Yi, Jisoo Mok, Sungroh Yoon
Abstract: Continuous efforts are being made to advance anomaly detection in various manufacturing processes to increase the productivity and safety of industrial sites. Deep learning replaced rule-based methods and recently emerged as a promising method for anomaly detection in diverse industries. However, in the real world, the scarcity of abnormal data and difficulties in obtaining labeled data create limitations in the training of detection models. In this study, we addressed these shortcomings by proposing a learnable data augmentation-based time-series anomaly detection (LATAD) technique that is trained in a self-supervised manner. LATAD extracts discriminative features from time-series data through contrastive learning. At the same time, learnable data augmentation produces challenging negative samples to enhance learning efficiency. We measured anomaly scores of the proposed technique based on latent feature similarities. As per the results, LATAD exhibited comparable or improved performance to the state-of-the-art anomaly detection assessments on several benchmark datasets and provided a gradient-based diagnosis technique to help identify root causes.
Authors: Yufan Cai, Zhe Hou, Xiaokun Luan, David Miguel Sanan Baena, Yun Lin, Jun Sun, Jin Song Dong
Abstract: Program refinement involves correctness-preserving transformations from formal high-level specification statements into executable programs. Traditional verification tool support for program refinement is highly interactive and lacks automation. On the other hand, the emergence of large language models (LLMs) enables automatic code generations from informal natural language specifications. However, code generated by LLMs is often unreliable. Moreover, the opaque procedure from specification to code provided by LLM is an uncontrolled black box. We propose LLM4PR, a tool that combines formal program refinement techniques with informal LLM-based methods to (1) transform the specification to preconditions and postconditions, (2) automatically build prompts based on refinement calculus, (3) interact with LLM to generate code, and finally, (4) verify that the generated code satisfies the conditions of refinement calculus, thus guaranteeing the correctness of the code. We have implemented our tool using GPT4, Coq, and Coqhammer, and evaluated it on the HumanEval and EvalPlus datasets.
Authors: Oskar Wysocki, Magdalena Wysocka, Danilo Carvalho, Alex Teodor Bogatu, Danilo Miranda Gusicuma, Maxime Delmas, Harriet Unsworth, Andre Freitas
Abstract: We present BioLunar, developed using the Lunar framework, as a tool for supporting biological analyses, with a particular emphasis on molecular-level evidence enrichment for biomarker discovery in oncology. The platform integrates Large Language Models (LLMs) to facilitate complex scientific reasoning across distributed evidence spaces, enhancing the capability for harmonizing and reasoning over heterogeneous data sources. Demonstrating its utility in cancer research, BioLunar leverages modular design, reusable data access and data analysis components, and a low-code user interface, enabling researchers of all programming levels to construct LLM-enabled scientific workflows. By facilitating automatic scientific discovery and inference from heterogeneous evidence, BioLunar exemplifies the potential of the integration between LLMs, specialised databases and biomedical tools to support expert-level knowledge synthesis and discovery.
Authors: Xin Lai, Zhuotao Tian, Yukang Chen, Senqiao Yang, Xiangru Peng, Jiaya Jia
Abstract: Mathematical reasoning presents a significant challenge for Large Language Models (LLMs) due to the extensive and precise chain of reasoning required for accuracy. Ensuring the correctness of each reasoning step is critical. To address this, we aim to enhance the robustness and factuality of LLMs by learning from human feedback. However, Direct Preference Optimization (DPO) has shown limited benefits for long-chain mathematical reasoning, as models employing DPO struggle to identify detailed errors in incorrect answers. This limitation stems from a lack of fine-grained process supervision. We propose a simple, effective, and data-efficient method called Step-DPO, which treats individual reasoning steps as units for preference optimization rather than evaluating answers holistically. Additionally, we have developed a data construction pipeline for Step-DPO, enabling the creation of a high-quality dataset containing 10K step-wise preference pairs. We also observe that in DPO, self-generated data is more effective than data generated by humans or GPT-4, due to the latter's out-of-distribution nature. Our findings demonstrate that as few as 10K preference data pairs and fewer than 500 Step-DPO training steps can yield a nearly 3% gain in accuracy on MATH for models with over 70B parameters. Notably, Step-DPO, when applied to Qwen2-72B-Instruct, achieves scores of 70.8% and 94.0% on the test sets of MATH and GSM8K, respectively, surpassing a series of closed-source models, including GPT-4-1106, Claude-3-Opus, and Gemini-1.5-Pro. Our code, data, and models are available at https://github.com/dvlab-research/Step-DPO.
Authors: Isaac Ong, Amjad Almahairi, Vincent Wu, Wei-Lin Chiang, Tianhao Wu, Joseph E. Gonzalez, M Waleed Kadous, Ion Stoica
Abstract: Large language models (LLMs) exhibit impressive capabilities across a wide range of tasks, yet the choice of which model to use often involves a trade-off between performance and cost. More powerful models, though effective, come with higher expenses, while less capable models are more cost-effective. To address this dilemma, we propose several efficient router models that dynamically select between a stronger and a weaker LLM during inference, aiming to optimize the balance between cost and response quality. We develop a training framework for these routers leveraging human preference data and data augmentation techniques to enhance performance. Our evaluation on widely-recognized benchmarks shows that our approach significantly reduces costs-by over 2 times in certain cases-without compromising the quality of responses. Interestingly, our router models also demonstrate significant transfer learning capabilities, maintaining their performance even when the strong and weak models are changed at test time. This highlights the potential of these routers to provide a cost-effective yet high-performance solution for deploying LLMs.
Authors: Minhwa Lee, Zae Myung Kim, Vivek A. Khetan, Dongyeop Kang
Abstract: Large Language Models (LLMs) have assisted humans in several writing tasks, including text revision and story generation. However, their effectiveness in supporting domain-specific writing, particularly in business contexts, is relatively less explored. Our formative study with industry professionals revealed the limitations in current LLMs' understanding of the nuances in such domain-specific writing. To address this gap, we propose an approach of human-AI collaborative taxonomy development to perform as a guideline for domain-specific writing assistants. This method integrates iterative feedback from domain experts and multiple interactions between these experts and LLMs to refine the taxonomy. Through larger-scale experiments, we aim to validate this methodology and thus improve LLM-powered writing assistance, tailoring it to meet the unique requirements of different stakeholder needs.
Authors: Jaehyung Kim, Yiming Yang
Abstract: As the diversity of users increases, the capability of providing personalized responses by large language models (LLMs) has become increasingly important. Existing approaches have only limited successes in LLM personalization, due to the absence of personalized learning or the reliance on shared personal data. This paper proposes a new approach for a few-shot personalization of LLMs with their mis-aligned responses (Fermi). Our key idea is to learn a set of personalized prompts for each user by progressively improving the prompts using LLMs, based on user profile (e.g., demographic information) and a few examples of previous opinions. During an iterative process of prompt improvement, we incorporate the contexts of mis-aligned responses by LLMs, which are especially crucial for the effective personalization of LLMs. In addition, we develop an effective inference method to further leverage the context of the test query and the personalized prompts. Our experimental results demonstrate that Fermi significantly improves performance across various benchmarks, compared to the best-performing baselines.
Authors: Xiang Li, Vivek Govindan, Rohit Paturi, Sundararajan Srinivasan
Abstract: End-to-end neural diarization (EEND) models offer significant improvements over traditional embedding-based Speaker Diarization (SD) approaches but falls short on generalizing to long-form audio with large number of speakers. EEND-vector-clustering method mitigates this by combining local EEND with global clustering of speaker embeddings from local windows, but this requires an additional speaker embedding framework alongside the EEND module. In this paper, we propose a novel framework applying EEND both locally and globally for long-form audio without separate speaker embeddings. This approach achieves significant relative DER reduction of 13% and 10% over the conventional 1-pass EEND on Callhome American English and RT03-CTS datasets respectively and marginal improvements over EEND-vector-clustering without the need for additional speaker embeddings. Furthermore, we discuss the computational complexity of our proposed framework and explore strategies for reducing processing times.
Authors: Jaehyung Kim, Dongyoung Kim, Yiming Yang
Abstract: An open challenge in recent machine learning is about how to improve the reasoning capability of large language models (LLMs) in a black-box setting, i.e., without access to detailed information such as output token probabilities. Existing approaches either rely on accessibility (which is often unrealistic) or involve significantly increased train- and inference-time costs. This paper addresses those limitations or shortcomings by proposing a novel approach, namely CoBB (Correct for improving QA reasoning of Black-Box LLMs). It uses a trained adaptation model to perform a seq2seq mapping from the often-imperfect reasonings of the original black-box LLM to the correct or improved reasonings. Specifically, the adaptation model is initialized with a relatively small open-source LLM and adapted over a collection of sub-sampled training pairs. To select the representative pairs of correct and incorrect reasonings, we formulated the dataset construction as an optimization problem that minimizes the statistical divergence between the sampled subset and the entire collection, and solved it via a genetic algorithm. We then train the adaptation model over the sampled pairs by contrasting the likelihoods of correct and incorrect reasonings. Our experimental results demonstrate that CoBB significantly improves reasoning accuracy across various QA benchmarks, compared to the best-performing adaptation baselines.
Authors: Zachary R. Baker, Zarif L. Azher
Abstract: This study introduces a novel approach to simulating legislative processes using LLM-driven virtual agents, focusing on the U.S. Senate Intelligence Committee. We developed agents representing individual senators and placed them in simulated committee discussions. The agents demonstrated the ability to engage in realistic debate, provide thoughtful reflections, and find bipartisan solutions under certain conditions. Notably, the simulation also showed promise in modeling shifts towards bipartisanship in response to external perturbations. Our results indicate that this LLM-driven approach could become a valuable tool for understanding and potentially improving legislative processes, supporting a broader pattern of findings highlighting how LLM-based agents can usefully model real-world phenomena. Future works will focus on enhancing agent complexity, expanding the simulation scope, and exploring applications in policy testing and negotiation.
Authors: Mingyang Wang, Heike Adel, Lukas Lange, Jannik Str\"otgen, Hinrich Sch\"utze
Abstract: In real-world environments, continual learning is essential for machine learning models, as they need to acquire new knowledge incrementally without forgetting what they have already learned. While pretrained language models have shown impressive capabilities on various static tasks, applying them to continual learning poses significant challenges, including avoiding catastrophic forgetting, facilitating knowledge transfer, and maintaining parameter efficiency. In this paper, we introduce MoCL-P, a novel lightweight continual learning method that addresses these challenges simultaneously. Unlike traditional approaches that continuously expand parameters for newly arriving tasks, MoCL-P integrates task representation-guided module composition with adaptive pruning, effectively balancing knowledge integration and computational overhead. Our evaluation across three continual learning benchmarks with up to 176 tasks shows that MoCL-P achieves state-of-the-art performance and improves parameter efficiency by up to three times, demonstrating its potential for practical applications where resource requirements are constrained.
Authors: Mansour Al Ghanim, Saleh Almohaimeed, Mengxin Zheng, Yan Solihin, Qian Lou
Abstract: This study identifies the potential vulnerabilities of Large Language Models (LLMs) to 'jailbreak' attacks, specifically focusing on the Arabic language and its various forms. While most research has concentrated on English-based prompt manipulation, our investigation broadens the scope to investigate the Arabic language. We initially tested the AdvBench benchmark in Standardized Arabic, finding that even with prompt manipulation techniques like prefix injection, it was insufficient to provoke LLMs into generating unsafe content. However, when using Arabic transliteration and chatspeak (or arabizi), we found that unsafe content could be produced on platforms like OpenAI GPT-4 and Anthropic Claude 3 Sonnet. Our findings suggest that using Arabic and its various forms could expose information that might remain hidden, potentially increasing the risk of jailbreak attacks. We hypothesize that this exposure could be due to the model's learned connection to specific words, highlighting the need for more comprehensive safety training across all language forms.
Authors: Yi Zhu, Tiago Falk
Abstract: Speech is known to carry health-related attributes, which has emerged as a novel venue for remote and long-term health monitoring. However, existing models are usually tailored for a specific type of disease, and have been shown to lack generalizability across datasets. Furthermore, concerns have been raised recently towards the leakage of speaker identity from health embeddings. To mitigate these limitations, we propose WavRx, a speech health diagnostics model that captures the respiration and articulation related dynamics from a universal speech representation. Our in-domain and cross-domain experiments on six pathological speech datasets demonstrate WavRx as a new state-of-the-art health diagnostic model. Furthermore, we show that the amount of speaker identity entailed in the WavRx health embeddings is significantly reduced without extra guidance during training. An in-depth analysis of the model was performed, thus providing physiological interpretation of its improved generalizability and privacy-preserving ability.
Authors: Junfeng Jiao, Saleh Afroogh, Yiming Xu, Connor Phillips
Abstract: This study addresses ethical issues surrounding Large Language Models (LLMs) within the field of artificial intelligence. It explores the common ethical challenges posed by both LLMs and other AI systems, such as privacy and fairness, as well as ethical challenges uniquely arising from LLMs. It highlights challenges such as hallucination, verifiable accountability, and decoding censorship complexity, which are unique to LLMs and distinct from those encountered in traditional AI systems. The study underscores the need to tackle these complexities to ensure accountability, reduce biases, and enhance transparency in the influential role that LLMs play in shaping information dissemination. It proposes mitigation strategies and future directions for LLM ethics, advocating for interdisciplinary collaboration. It recommends ethical frameworks tailored to specific domains and dynamic auditing systems adapted to diverse contexts. This roadmap aims to guide responsible development and integration of LLMs, envisioning a future where ethical considerations govern AI advancements in society.
Authors: Junfeng Jiao, Saleh Afroogh, Kevin Chen, David Atkinson, Amit Dhurandhar
Abstract: The integration of Generative Artificial Intelligence (GAI) and Large Language Models (LLMs) in academia has spurred a global discourse on their potential pedagogical benefits and ethical considerations. Positive reactions highlight some potential, such as collaborative creativity, increased access to education, and empowerment of trainers and trainees. However, negative reactions raise concerns about ethical complexities, balancing innovation and academic integrity, unequal access, and misinformation risks. Through a systematic survey and text-mining-based analysis of global and national directives, insights from independent research, and eighty university-level guidelines, this study provides a nuanced understanding of the opportunities and challenges posed by GAI and LLMs in education. It emphasizes the importance of balanced approaches that harness the benefits of these technologies while addressing ethical considerations and ensuring equitable access and educational outcomes. The paper concludes with recommendations for fostering responsible innovation and ethical practices to guide the integration of GAI and LLMs in academia.
Authors: Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu, He Huang, Boris Ginsburg, Yu-Chiang Frank Wang, Hung-yi Lee
Abstract: Recent speech language models (SLMs) typically incorporate pre-trained speech models to extend the capabilities from large language models (LLMs). In this paper, we propose a Descriptive Speech-Text Alignment approach that leverages speech captioning to bridge the gap between speech and text modalities, enabling SLMs to interpret and generate comprehensive natural language descriptions, thereby facilitating the capability to understand both linguistic and non-linguistic features in speech. Enhanced with the proposed approach, our model demonstrates superior performance on the Dynamic-SUPERB benchmark, particularly in generalizing to unseen tasks. Moreover, we discover that the aligned model exhibits a zero-shot instruction-following capability without explicit speech instruction tuning. These findings highlight the potential to reshape instruction-following SLMs by incorporating rich, descriptive speech captions.
Authors: Yehoshua Dissen, Shiry Yonash, Israel Cohen, Joseph Keshet
Abstract: In the realm of automatic speech recognition (ASR), robustness in noisy environments remains a significant challenge. Recent ASR models, such as Whisper, have shown promise, but their efficacy in noisy conditions can be further enhanced. This study is focused on recovering from packet loss to improve the word error rate (WER) of ASR models. We propose using a front-end adaptation network connected to a frozen ASR model. The adaptation network is trained to modify the corrupted input spectrum by minimizing the criteria of the ASR model in addition to an enhancement loss function. Our experiments demonstrate that the adaptation network, trained on Whisper's criteria, notably reduces word error rates across domains and languages in packet-loss scenarios. This improvement is achieved with minimal affect to Whisper model's foundational performance, underscoring our method's practicality and potential in enhancing ASR models in challenging acoustic environments.
Authors: Rafa{\l} Stefa\'nski
Abstract: This thesis studies the single-use restriction for register automata and transducers over infinite alphabets. The restriction requires that a read-access to a register should have the side effect of destroying its contents. This constraint results in robust classes of languages and transductions. For automata models, we show that one-way register automata, two-way register automata, and orbit-finite monoids have the same expressive power. For transducer models, we show that single-use Mealy machines and single-use two-way transducers admit versions of the Krohn-Rhodes decomposition theorem. Moreover, single-use Mealy machines are equivalent to an algebraic model called local algebraic semigroup transductions. Additionally, we show that single-use two-way transducers are equivalent to single-use streaming string transducers (SSTs) over infinite alphabets and to regular list functions with atoms. Compared with the previous work arXiv:1907.10504, this thesis offers a coherent narrative on the single-use restriction. We introduce an abstract notion of single-use functions and use them to define all the discussed single-use models. We also introduce and study the algebraic models of local semigroup transduction and local rational semigroup transduction.
Authors: Atsunori Ogawa, Naoyuki Kamo, Kohei Matsuura, Takanori Ashihara, Takafumi Moriya, Takatomo Kano, Naohiro Tawara, Marc Delcroix
Abstract: Large language models (LLMs) have been successfully applied for rescoring automatic speech recognition (ASR) hypotheses. However, their ability to rescore ASR hypotheses of casual conversations has not been sufficiently explored. In this study, we reveal it by performing N-best ASR hypotheses rescoring using Llama2 on the CHiME-7 distant ASR (DASR) task. Llama2 is one of the most representative LLMs, and the CHiME-7 DASR task provides datasets of casual conversations between multiple participants. We investigate the effects of domain adaptation of the LLM and context carry-over when performing N-best rescoring. Experimental results show that, even without domain adaptation, Llama2 outperforms a standard-size domain-adapted Transformer-LM, especially when using a long context. Domain adaptation shortens the context length needed with Llama2 to achieve its best performance, i.e., it reduces the computational cost of Llama2.
Authors: Fanfan Liu, Feng Yan, Liming Zheng, Chengjian Feng, Yiyang Huang, Lin Ma
Abstract: Utilizing Vision-Language Models (VLMs) for robotic manipulation represents a novel paradigm, aiming to enhance the model's ability to generalize to new objects and instructions. However, due to variations in camera specifications and mounting positions, existing methods exhibit significant performance disparities across different robotic platforms. To address this challenge, we propose RoboUniView in this paper, an innovative approach that decouples visual feature extraction from action learning. We first learn a unified view representation from multi-perspective views by pre-training on readily accessible data, and then derive actions from this unified view representation to control robotic manipulation. This unified view representation more accurately mirrors the physical world and is not constrained by the robotic platform's camera parameters. Thanks to this methodology, we achieve state-of-the-art performance on the demanding CALVIN benchmark, enhancing the success rate in the $D \to D$ setting from 88.7% to 96.2%, and in the $ABC \to D$ setting from 82.4% to 94.2%. Moreover, our model exhibits outstanding adaptability and flexibility: it maintains high performance under unseen camera parameters, can utilize multiple datasets with varying camera parameters, and is capable of joint cross-task learning across datasets. Code is provided for re-implementation. https://github.com/liufanfanlff/RoboUniview
Authors: Tomer Porian, Mitchell Wortsman, Jenia Jitsev, Ludwig Schmidt, Yair Carmon
Abstract: Kaplan et al. and Hoffmann et al. developed influential scaling laws for the optimal model size as a function of the compute budget, but these laws yield substantially different predictions. We explain the discrepancy by reproducing the Kaplan scaling law on two datasets (OpenWebText2 and RefinedWeb) and identifying three factors causing the difference: last layer computational cost, warmup duration, and scale-dependent optimizer tuning. With these factors corrected, we obtain excellent agreement with the Hoffmann et al. (i.e., "Chinchilla") scaling law. Counter to a hypothesis of Hoffmann et al., we find that careful learning rate decay is not essential for the validity of their scaling law. As a secondary result, we derive scaling laws for the optimal learning rate and batch size, finding that tuning the AdamW $\beta_2$ parameter is essential at lower batch sizes.
Authors: Changze Lv, Jianhan Xu, Xiaoqing Zheng
Abstract: Spiking neural networks (SNNs) offer a promising pathway to implement deep neural networks (DNNs) in a more energy-efficient manner since their neurons are sparsely activated and inferences are event-driven. However, there have been very few works that have demonstrated the efficacy of SNNs in language tasks partially because it is non-trivial to represent words in the forms of spikes and to deal with variable-length texts by SNNs. This work presents a "conversion + fine-tuning" two-step method for training SNNs for text classification and proposes a simple but effective way to encode pre-trained word embeddings as spike trains. We show empirically that after fine-tuning with surrogate gradients, the converted SNNs achieve comparable results to their DNN counterparts with much less energy consumption across multiple datasets for both English and Chinese. We also show that such SNNs are more robust to adversarial attacks than DNNs.
Authors: Hao Fei, Shengqiong Wu, Meishan Zhang, Min Zhang, Tat-Seng Chua, Shuicheng Yan
Abstract: While pre-training large-scale video-language models (VLMs) has shown remarkable potential for various downstream video-language tasks, existing VLMs can still suffer from certain commonly seen limitations, e.g., coarse-grained cross-modal aligning , under-modeling of temporal dynamics, detached video-language view. In this work, we target enhancing VLMs with a fine-grained structural spatio-temporal alignment learning method (namely Finsta). First of all, we represent the input texts and videos with fine-grained scene graph (SG) structures, both of which are further unified into a holistic SG (HSG) for bridging two modalities. Then, an SG-based framework is built, where the textual SG (TSG) is encoded with a graph Transformer, while the video dynamic SG (DSG) and the HSG are modeled with a novel recurrent graph Transformer for spatial and temporal feature propagation. A spatial-temporal Gaussian differential graph Transformer is further devised to strengthen the sense of the changes in objects across spatial and temporal dimensions. Next, based on the fine-grained structural features of TSG and DSG, we perform object-centered spatial alignment and predicate-centered temporal alignment respectively, enhancing the video-language grounding in both the spatiality and temporality. We design our method as a plug&play system, which can be integrated into existing well-trained VLMs for further representation augmentation, without training from scratch or relying on SG annotations in downstream applications. On 6 representative VL modeling tasks over 12 datasets in both standard and long-form video scenarios, Finsta consistently improves the existing 13 strong-performing VLMs persistently, and refreshes the current state-of-the-art end task performance significantly in both the fine-tuning and zero-shot settings.
Authors: Junying Chen, Ruyi Ouyang, Anningzhe Gao, Shunian Chen, Guiming Hardy Chen, Xidong Wang, Ruifei Zhang, Zhenyang Cai, Ke Ji, Guangjun Yu, Xiang Wan, Benyou Wang
Abstract: The rapid development of multimodal large language models (MLLMs), such as GPT-4V, has led to significant advancements. However, these models still face challenges in medical multimodal capabilities due to limitations in the quantity and quality of medical vision-text data, stemming from data privacy concerns and high annotation costs. While pioneering approaches utilize PubMed's large-scale, de-identified medical image-text pairs to address these limitations, they still fall short due to inherent data noise. To tackle this, we refined medical image-text pairs from PubMed and employed MLLMs (GPT-4V) in an 'unblinded' capacity to denoise and reformat the data, resulting in the creation of the PubMedVision dataset with 1.3 million medical VQA samples. Our validation demonstrates that: (1) PubMedVision can significantly enhance the medical multimodal capabilities of current MLLMs, showing significant improvement in benchmarks including the MMMU Health & Medicine track; (2) manual checks by medical experts and empirical results validate the superior data quality of our dataset compared to other data construction methods. Using PubMedVision, we train a 34B medical MLLM HuatuoGPT-Vision, which shows superior performance in medical multimodal scenarios among open-source MLLMs.
Authors: Zheyang Xiong, Vasilis Papageorgiou, Kangwook Lee, Dimitris Papailiopoulos
Abstract: Recent studies have shown that Large Language Models (LLMs) struggle to accurately retrieve information and maintain reasoning capabilities when processing long-context inputs. To address these limitations, we propose a finetuning approach utilizing a carefully designed synthetic dataset comprising numerical key-value retrieval tasks. Our experiments on models like GPT-3.5 Turbo and Mistral 7B demonstrate that finetuning LLMs on this dataset significantly improves LLMs' information retrieval and reasoning capabilities in longer-context settings. We present an analysis of the finetuned models, illustrating the transfer of skills from synthetic to real task evaluations (e.g., $10.5\%$ improvement on $20$ documents MDQA at position $10$ for GPT-3.5 Turbo). We also find that finetuned LLMs' performance on general benchmarks remains almost constant while LLMs finetuned on other baseline long-context augmentation data can encourage hallucination (e.g., on TriviaQA, Mistral 7B finetuned on our synthetic data cause no performance drop while other baseline data can cause a drop that ranges from $2.33\%$ to $6.19\%$). Our study highlights the potential of finetuning on synthetic data for improving the performance of LLMs on longer-context tasks.
Authors: Parand A. Alamdari, Yanshuai Cao, Kevin H. Wilson
Abstract: We present substantial evidence demonstrating the benefits of integrating Large Language Models (LLMs) with a Contextual Multi-Armed Bandit framework. Contextual bandits have been widely used in recommendation systems to generate personalized suggestions based on user-specific contexts. We show that LLMs, pre-trained on extensive corpora rich in human knowledge and preferences, can simulate human behaviours well enough to jump-start contextual multi-armed bandits to reduce online learning regret. We propose an initialization algorithm for contextual bandits by prompting LLMs to produce a pre-training dataset of approximate human preferences for the bandit. This significantly reduces online learning regret and data-gathering costs for training such models. Our approach is validated empirically through two sets of experiments with different bandit setups: one which utilizes LLMs to serve as an oracle and a real-world experiment utilizing data from a conjoint survey experiment.
Authors: Vedang Lad, Wes Gurnee, Max Tegmark
Abstract: We demonstrate and investigate the remarkable robustness of Large Language Models by deleting and swapping adjacent layers. We find that deleting and swapping interventions retain 72-95\% of the original model's prediction accuracy without fine-tuning, whereas models with more layers exhibit more robustness. Based on the results of the layer-wise intervention and further experiments, we hypothesize the existence of four universal stages of inference across eight different models: detokenization, feature engineering, prediction ensembling, and residual sharpening. The first stage integrates local information, lifting raw token representations into higher-level contextual representations. Next is the iterative refinement of task and entity-specific features. Then, the second half of the model begins with a phase transition, where hidden representations align more with the vocabulary space due to specialized model components. Finally, the last layer sharpens the following token distribution by eliminating obsolete features that add noise to the prediction.
Authors: Moayed Haji-Ali, Willi Menapace, Aliaksandr Siarohin, Guha Balakrishnan, Sergey Tulyakov, Vicente Ordonez
Abstract: Generating ambient sounds and effects is a challenging problem due to data scarcity and often insufficient caption quality, making it difficult to employ large-scale generative models for the task. In this work, we tackle the problem by introducing two new models. First, we propose AutoCap, a high-quality and efficient automatic audio captioning model. We show that by leveraging metadata available with the audio modality, we can substantially improve the quality of captions. AutoCap reaches CIDEr score of 83.2, marking a 3.2% improvement from the best available captioning model at four times faster inference speed. We then use AutoCap to caption clips from existing datasets, obtaining 761,000 audio clips with high-quality captions, forming the largest available audio-text dataset. Second, we propose GenAu, a scalable transformer-based audio generation architecture that we scale up to 1.25B parameters and train with our new dataset. When compared to state-of-the-art audio generators, GenAu obtains significant improvements of 15.7% in FAD score, 22.7% in IS, and 13.5% in CLAP score, indicating significantly improved quality of generated audio compared to previous works. This shows that the quality of data is often as important as its quantity. Besides, since AutoCap is fully automatic, new audio samples can be added to the training dataset, unlocking the training of even larger generative models for audio synthesis.
Authors: Yequan Wang, Hengran Zhang, Aixin Sun, Xuying Meng
Abstract: Given comparative text, comparative relation extraction aims to extract two targets (\eg two cameras) in comparison and the aspect they are compared for (\eg image quality). The extracted comparative relations form the basis of further opinion analysis.Existing solutions formulate this task as a sequence labeling task, to extract targets and aspects. However, they cannot directly extract comparative relation(s) from text. In this paper, we show that comparative relations can be directly extracted with high accuracy, by generative model. Based on GPT-2, we propose a Generation-based Comparative Relation Extractor (GCRE-GPT). Experiment results show that \modelname achieves state-of-the-art accuracy on two datasets.
Authors: Oleg Vasilyev, Fumika Isono, John Bohannon
Abstract: Semantics of a sentence is defined with much less ambiguity than semantics of a single word, and we assume that it should be better preserved by translation to another language. If multilingual sentence embeddings intend to represent sentence semantics, then the similarity between embeddings of any two sentences must be invariant with respect to translation. Based on this suggestion, we consider a simple linear cross-lingual mapping as a possible improvement of the multilingual embeddings. We also consider deviation from orthogonality conditions as a measure of deficiency of the embeddings.
Authors: Andreas Waldis, Yufang Hou, Iryna Gurevych
Abstract: The advent of pre-trained Language Models (LMs) has markedly advanced natural language processing, but their efficacy in out-of-distribution (OOD) scenarios remains a significant challenge. Computational argumentation (CA), modeling human argumentation processes, is a field notably impacted by these challenges because complex annotation schemes and high annotation costs naturally lead to resources barely covering the multiplicity of available text sources and topics. Due to this data scarcity, generalization to data from uncovered covariant distributions is a common challenge for CA tasks like stance detection or argument classification. This work systematically assesses LMs' capabilities for such OOD scenarios. While previous work targets specific OOD types like topic shifts or OOD uniformly, we address three prevalent OOD scenarios in CA: topic shift, domain shift, and language shift. Our findings challenge the previously asserted general superiority of in-context learning (ICL) for OOD. We find that the efficacy of such learning paradigms varies with the type of OOD. Specifically, while ICL excels for domain shifts, prompt-based fine-tuning surpasses for topic shifts. To sum up, we navigate the heterogeneity of OOD scenarios in CA and empirically underscore the potential of base-sized LMs in overcoming these challenges.
Authors: Michael J. Parker, Caitlin Anderson, Claire Stone, YeaRim Oh
Abstract: This paper assesses the potential for the large language models (LLMs) GPT-4 and GPT-3.5 to aid in deriving insight from education feedback surveys. Exploration of LLM use cases in education has focused on teaching and learning, with less exploration of capabilities in education feedback analysis. Survey analysis in education involves goals such as finding gaps in curricula or evaluating teachers, often requiring time-consuming manual processing of textual responses. LLMs have the potential to provide a flexible means of achieving these goals without specialized machine learning models or fine-tuning. We demonstrate a versatile approach to such goals by treating them as sequences of natural language processing (NLP) tasks including classification (multi-label, multi-class, and binary), extraction, thematic analysis, and sentiment analysis, each performed by LLM. We apply these workflows to a real-world dataset of 2500 end-of-course survey comments from biomedical science courses, and evaluate a zero-shot approach (i.e., requiring no examples or labeled training data) across all tasks, reflecting education settings, where labeled data is often scarce. By applying effective prompting practices, we achieve human-level performance on multiple tasks with GPT-4, enabling workflows necessary to achieve typical goals. We also show the potential of inspecting LLMs' chain-of-thought (CoT) reasoning for providing insight that may foster confidence in practice. Moreover, this study features development of a versatile set of classification categories, suitable for various course types (online, hybrid, or in-person) and amenable to customization. Our results suggest that LLMs can be used to derive a range of insights from survey text.
Authors: Rui Yang, Jiahao Zhu, Jianping Man, Li Fang, Yi Zhou
Abstract: The design and development of text-based knowledge graph completion (KGC) methods leveraging textual entity descriptions are at the forefront of research. These methods involve advanced optimization techniques such as soft prompts and contrastive learning to enhance KGC models. The effectiveness of text-based methods largely hinges on the quality and richness of the training data. Large language models (LLMs) can utilize straightforward prompts to alter text data, thereby enabling data augmentation for KGC. Nevertheless, LLMs typically demand substantial computational resources. To address these issues, we introduce a framework termed constrained prompts for KGC (CP-KGC). This CP-KGC framework designs prompts that adapt to different datasets to enhance semantic richness. Additionally, CP-KGC employs a context constraint strategy to effectively identify polysemous entities within KGC datasets. Through extensive experimentation, we have verified the effectiveness of this framework. Even after quantization, the LLM (Qwen-7B-Chat-int4) still enhances the performance of text-based KGC methods \footnote{Code and datasets are available at \href{https://github.com/sjlmg/CP-KGC}{https://github.com/sjlmg/CP-KGC}}. This study extends the performance limits of existing models and promotes further integration of KGC with LLMs.
URLs: https://github.com/sjlmg/CP-KGC, https://github.com/sjlmg/CP-KGC
Authors: Huao Li, Yu Quan Chong, Simon Stepputtis, Joseph Campbell, Dana Hughes, Michael Lewis, Katia Sycara
Abstract: While Large Language Models (LLMs) have demonstrated impressive accomplishments in both reasoning and planning, their abilities in multi-agent collaborations remains largely unexplored. This study evaluates LLM-based agents in a multi-agent cooperative text game with Theory of Mind (ToM) inference tasks, comparing their performance with Multi-Agent Reinforcement Learning (MARL) and planning-based baselines. We observed evidence of emergent collaborative behaviors and high-order Theory of Mind capabilities among LLM-based agents. Our results reveal limitations in LLM-based agents' planning optimization due to systematic failures in managing long-horizon contexts and hallucination about the task state. We explore the use of explicit belief state representations to mitigate these issues, finding that it enhances task performance and the accuracy of ToM inferences for LLM-based agents.
Authors: Evangelia Gogoulou, Timoth\'ee Lesort, Magnus Boman, Joakim Nivre
Abstract: The recent increase in data and model scale for language model pre-training has led to huge training costs. In scenarios where new data become available over time, updating a model instead of fully retraining it would therefore provide significant gains. We study the pros and cons of updating a language model when new data comes from new languages -- the case of continual learning under language shift. Starting from a monolingual English language model, we incrementally add data from Danish, Icelandic, and Norwegian to investigate how forward and backward transfer effects depend on pre-training order and characteristics of languages, for three different model sizes. Our results show that, while forward transfer is largely positive and independent of language order, backward transfer can be positive or negative depending on the order and characteristics of new languages. We explore a number of potentially explanatory factors and find that a combination of language contamination and syntactic similarity best fits our results.
Authors: Marcio Fonseca, Shay B. Cohen
Abstract: Although large language models (LLMs) exhibit remarkable capacity to leverage in-context demonstrations, it is still unclear to what extent they can learn new concepts or facts from ground-truth labels. To address this question, we examine the capacity of instruction-tuned LLMs to follow in-context concept guidelines for sentence labeling tasks. We design guidelines that present different types of factual and counterfactual concept definitions, which are used as prompts for zero-shot sentence classification tasks. Our results show that although concept definitions consistently help in task performance, only the larger models (with 70B parameters or more) have limited ability to work under counterfactual contexts. Importantly, only proprietary models such as GPT-3.5 and GPT-4 can recognize nonsensical guidelines, which we hypothesize is due to more sophisticated alignment methods. Finally, we find that Falcon-180B-chat is outperformed by Llama-2-70B-chat is most cases, which indicates that careful fine-tuning is more effective than increasing model scale. Altogether, our simple evaluation method reveals significant gaps in concept understanding between the most capable open-source language models and the leading proprietary APIs.
Authors: Panfeng Li, Mohamed Abouelenien, Rada Mihalcea, Zhicheng Ding, Qikai Yang, Yiming Zhou
Abstract: Deception detection is gaining increasing interest due to ethical and security concerns. This paper explores the application of convolutional neural networks for the purpose of multimodal deception detection. We use a dataset built by interviewing 104 subjects about two topics, with one truthful and one falsified response from each subject about each topic. In particular, we make three main contributions. First, we extract linguistic and physiological features from this data to train and construct the neural network models. Second, we propose a fused convolutional neural network model using both modalities in order to achieve an improved overall performance. Third, we compare our new approach with earlier methods designed for multimodal deception detection. We find that our system outperforms regular classification methods; our results indicate the feasibility of using neural networks for deception detection even in the presence of limited amounts of data.
Authors: Shaobo Cui, Lazar Milikic, Yiyang Feng, Mete Ismayilzada, Debjit Paul, Antoine Bosselut, Boi Faltings
Abstract: Defeasibility in causal reasoning implies that the causal relationship between cause and effect can be strengthened or weakened. Namely, the causal strength between cause and effect should increase or decrease with the incorporation of strengthening arguments (supporters) or weakening arguments (defeaters), respectively. However, existing works ignore defeasibility in causal reasoning and fail to evaluate existing causal strength metrics in defeasible settings. In this work, we present $\delta$-CAUSAL, the first benchmark dataset for studying defeasibility in causal reasoning. $\delta$-CAUSAL includes around 11K events spanning ten domains, featuring defeasible causality pairs, i.e., cause-effect pairs accompanied by supporters and defeaters. We further show current causal strength metrics fail to reflect the change of causal strength with the incorporation of supporters or defeaters in $\delta$-CAUSAL. To this end, we propose CESAR (Causal Embedding aSsociation with Attention Rating), a metric that measures causal strength based on token-level causal relationships. CESAR achieves a significant 69.7% relative improvement over existing metrics, increasing from 47.2% to 80.1% in capturing the causal strength change brought by supporters and defeaters. We further demonstrate even Large Language Models (LLMs) like GPT-3.5 still lag 4.5 and 10.7 points behind humans in generating supporters and defeaters, emphasizing the challenge posed by $\delta$-CAUSAL.
Authors: Afra Feyza Aky\"urek, Ekin Aky\"urek, Leshem Choshen, Derry Wijaya, Jacob Andreas
Abstract: While language models (LMs) can sometimes generate factually correct text and estimate truth values of individual claims, these generally do not reflect a globally coherent, manipulable model of the world. As a consequence, current LMs also generate incorrect or nonsensical content, and are difficult to edit and bring up to date. We present a method called Deductive Closure Training (DCT) that uses LMs themselves to identify implications of (and contradictions within) the text that they generate, yielding an efficient self-supervised procedure for improving LM factuality. Given a collection of seed documents, DCT prompts LMs to generate additional text implied by these documents, reason globally about the correctness of this generated text, and finally fine-tune on text inferred to be correct. Given seed documents from a trusted source, DCT provides a tool for supervised model updating; if seed documents are sampled from the LM itself, DCT enables fully unsupervised fine-tuning for improved coherence and accuracy. Across the CREAK, MQUaKE, and Reversal Curse datasets, supervised DCT improves LM fact verification and text generation accuracy by 3-26%; on CREAK fully unsupervised DCT improves verification accuracy by 12%. These results show that LMs' reasoning capabilities during inference can be leveraged during training to improve their reliability.
Authors: Trung Quoc Luong, Xinbo Zhang, Zhanming Jie, Peng Sun, Xiaoran Jin, Hang Li
Abstract: One way to enhance the reasoning capability of Large Language Models (LLMs) is to conduct Supervised Fine-Tuning (SFT) using Chain-of-Thought (CoT) annotations. This approach does not show sufficiently strong generalization ability, however, because the training only relies on the given CoT data. In math problem-solving, for example, there is usually only one annotated reasoning path for each question in the training data. Intuitively, it would be better for the algorithm to learn from multiple annotated reasoning paths given a question. To address this issue, we propose a simple yet effective approach called Reinforced Fine-Tuning (ReFT) to enhance the generalizability of learning LLMs for reasoning, with math problem-solving as an example. ReFT first warmups the model with SFT, and then employs on-line reinforcement learning, specifically the PPO algorithm in this paper, to further fine-tune the model, where an abundance of reasoning paths are automatically sampled given the question and the rewards are naturally derived from the ground-truth answers. Extensive experiments on GSM8K, MathQA, and SVAMP datasets show that ReFT significantly outperforms SFT, and the performance can be potentially further boosted by combining inference-time strategies such as majority voting and re-ranking. Note that ReFT obtains the improvement by learning from the same training questions as SFT, without relying on extra or augmented training questions. This indicates a superior generalization ability for ReFT.
Authors: Pengfei Hong, Navonil Majumder, Deepanway Ghosal, Somak Aditya, Rada Mihalcea, Soujanya Poria
Abstract: Recent advancements in Large Language Models (LLMs) have showcased striking results on existing logical reasoning benchmarks, with some models even surpassing human performance. However, the true depth of their competencies and robustness in reasoning tasks remains an open question. To this end, in this paper, we focus on two popular reasoning tasks: arithmetic reasoning and code generation. Particularly, we introduce: (i) a general ontology of perturbations for maths and coding questions, (ii) a semi-automatic method to apply these perturbations, and (iii) two datasets, MORE and CORE, respectively, of perturbed maths and coding problems to probe the limits of LLM capabilities in numeric reasoning and coding tasks. Through comprehensive evaluations of both closed-source and open-source LLMs, we show a significant performance drop across all the models against the perturbed questions, suggesting that the current LLMs lack robust problem solving skills and structured reasoning abilities in many areas, as defined by our ontology. We open source the datasets and source codes at: https://github.com/declare-lab/llm_robustness.
Authors: Marcio Fonseca, Shay B. Cohen
Abstract: In this work, we investigate the controllability of large language models (LLMs) on scientific summarization tasks. We identify key stylistic and content coverage factors that characterize different types of summaries such as paper reviews, abstracts, and lay summaries. By controlling stylistic features, we find that non-fine-tuned LLMs outperform humans in the MuP review generation task, both in terms of similarity to reference summaries and human preferences. Also, we show that we can improve the controllability of LLMs with keyword-based classifier-free guidance (CFG) while achieving lexical overlap comparable to strong fine-tuned baselines on arXiv and PubMed. However, our results also indicate that LLMs cannot consistently generate long summaries with more than 8 sentences. Furthermore, these models exhibit limited capacity to produce highly abstractive lay summaries. Although LLMs demonstrate strong generic summarization competency, sophisticated content control without costly fine-tuning remains an open problem for domain-specific applications.
Authors: Haoyu Wang, Guozheng Ma, Ziqiao Meng, Zeyu Qin, Li Shen, Zhong Zhang, Bingzhe Wu, Liu Liu, Yatao Bian, Tingyang Xu, Xueqian Wang, Peilin Zhao
Abstract: Self-alignment is an effective way to reduce the cost of human annotation while ensuring promising model capability. However, most current methods complete the data collection and training steps in a single round, which may overlook the continuously improving ability of self-aligned models. This gives rise to a key query: What if we do multi-time bootstrapping self-alignment? Does this strategy enhance model performance or lead to rapid degradation? In this paper, our pioneering exploration delves into the impact of bootstrapping self-alignment on large language models. Our findings reveal that bootstrapping self-alignment markedly surpasses the single-round approach, by guaranteeing data diversity from in-context learning. To further exploit the capabilities of bootstrapping, we investigate and adjust the training order of data, which yields improved performance of the model. Drawing on these findings, we propose Step-On-Feet Tuning (SOFT) which leverages model's continuously enhanced few-shot ability to boost zero or one-shot performance. Based on easy-to-hard training recipe, we propose SOFT+ which further boost self-alignment's performance. Our experiments demonstrate the efficiency of SOFT (SOFT+) across various classification and generation tasks, highlighting the potential of bootstrapping self-alignment on continually enhancing model alignment performance.
Authors: Zhihao Fan, Jialong Tang, Wei Chen, Siyuan Wang, Zhongyu Wei, Jun Xi, Fei Huang, Jingren Zhou
Abstract: Artificial intelligence has significantly advanced healthcare, particularly through large language models (LLMs) that excel in medical question answering benchmarks. However, their real-world clinical application remains limited due to the complexities of doctor-patient interactions. To address this, we introduce \textbf{AI Hospital}, a multi-agent framework simulating dynamic medical interactions between \emph{Doctor} as player and NPCs including \emph{Patient}, \emph{Examiner}, \emph{Chief Physician}. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the Multi-View Medical Evaluation (MVME) benchmark, utilizing high-quality Chinese medical records and NPCs to evaluate LLMs' performance in symptom collection, examination recommendations, and diagnoses. Additionally, a dispute resolution collaborative mechanism is proposed to enhance diagnostic accuracy through iterative discussions. Despite improvements, current LLMs exhibit significant performance gaps in multi-turn interactions compared to one-step approaches. Our findings highlight the need for further research to bridge these gaps and improve LLMs' clinical diagnostic capabilities. Our data, code, and experimental results are all open-sourced at \url{https://github.com/LibertFan/AI_Hospital}.
Authors: Shengrui Li, Junzhe Chen, Xueting Han, Jing Bai
Abstract: The considerable size of Large Language Models (LLMs) presents notable deployment challenges, particularly on resource-constrained hardware. Structured pruning, offers an effective means to compress LLMs, thereby reducing storage costs and enhancing inference speed for more efficient utilization. In this work, we study data-efficient and resource-efficient structure pruning methods to obtain smaller yet still powerful models. Knowledge Distillation is well-suited for pruning, as the intact model can serve as an excellent teacher for pruned students. However, it becomes challenging in the context of LLMs due to memory constraints. To address this, we propose an efficient progressive Numerous-teacher pruning method (NutePrune). NutePrune mitigates excessive memory costs by loading only one intact model and integrating it with various masks and LoRA modules, enabling it to seamlessly switch between teacher and student roles. This approach allows us to leverage numerous teachers with varying capacities to progressively guide the pruned model, enhancing overall performance. Extensive experiments across various tasks demonstrate the effectiveness of NutePrune. In LLaMA-7B zero-shot experiments, NutePrune retains 97.17% of the performance of the original model at 20% sparsity and 95.07% at 25% sparsity. Our code is available at https://github.com/Lucius-lsr/NutePrune.
Authors: Yuxia Wang, Jonibek Mansurov, Petar Ivanov, Jinyan Su, Artem Shelmanov, Akim Tsvigun, Osama Mohanned Afzal, Tarek Mahmoud, Giovanni Puccetti, Thomas Arnold, Alham Fikri Aji, Nizar Habash, Iryna Gurevych, Preslav Nakov
Abstract: The advent of Large Language Models (LLMs) has brought an unprecedented surge in machine-generated text (MGT) across diverse channels. This raises legitimate concerns about its potential misuse and societal implications. The need to identify and differentiate such content from genuine human-generated text is critical in combating disinformation, preserving the integrity of education and scientific fields, and maintaining trust in communication. In this work, we address this problem by introducing a new benchmark based on a multilingual, multi-domain, and multi-generator corpus of MGTs -- M4GT-Bench. The benchmark is compiled of three tasks: (1) mono-lingual and multi-lingual binary MGT detection; (2) multi-way detection where one need to identify, which particular model generated the text; and (3) mixed human-machine text detection, where a word boundary delimiting MGT from human-written content should be determined. On the developed benchmark, we have tested several MGT detection baselines and also conducted an evaluation of human performance. We see that obtaining good performance in MGT detection usually requires an access to the training data from the same domain and generators. The benchmark is available at https://github.com/mbzuai-nlp/M4GT-Bench.
Authors: Rendi Chevi, Alham Fikri Aji
Abstract: We often verbally express emotions in a multifaceted manner, they may vary in their intensities and may be expressed not just as a single but as a mixture of emotions. This wide spectrum of emotions is well-studied in the structural model of emotions, which represents variety of emotions as derivative products of primary emotions with varying degrees of intensity. In this paper, we propose an emotional text-to-speech design to simulate a wider spectrum of emotions grounded on the structural model. Our proposed design, Daisy-TTS, incorporates a prosody encoder to learn emotionally-separable prosody embedding as a proxy for emotion. This emotion representation allows the model to simulate: (1) Primary emotions, as learned from the training samples, (2) Secondary emotions, as a mixture of primary emotions, (3) Intensity-level, by scaling the emotion embedding, and (4) Emotions polarity, by negating the emotion embedding. Through a series of perceptual evaluations, Daisy-TTS demonstrated overall higher emotional speech naturalness and emotion perceiveability compared to the baseline.
Authors: Sunjun Kweon, Jiyoun Kim, Heeyoung Kwak, Dongchul Cha, Hangyul Yoon, Kwanghyun Kim, Jeewon Yang, Seunghyun Won, Edward Choi
Abstract: Discharge summaries in Electronic Health Records (EHRs) are crucial for clinical decision-making, but their length and complexity make information extraction challenging, especially when dealing with accumulated summaries across multiple patient admissions. Large Language Models (LLMs) show promise in addressing this challenge by efficiently analyzing vast and complex data. Existing benchmarks, however, fall short in properly evaluating LLMs' capabilities in this context, as they typically focus on single-note information or limited topics, failing to reflect the real-world inquiries required by clinicians. To bridge this gap, we introduce EHRNoteQA, a novel benchmark built on the MIMIC-IV EHR, comprising 962 different QA pairs each linked to distinct patients' discharge summaries. Every QA pair is initially generated using GPT-4 and then manually reviewed and refined by three clinicians to ensure clinical relevance. EHRNoteQA includes questions that require information across multiple discharge summaries and covers eight diverse topics, mirroring the complexity and diversity of real clinical inquiries. We offer EHRNoteQA in two formats: open-ended and multi-choice question answering, and propose a reliable evaluation method for each. We evaluate 27 LLMs using EHRNoteQA and examine various factors affecting the model performance (e.g., the length and number of discharge summaries). Furthermore, to validate EHRNoteQA as a reliable proxy for expert evaluations in clinical practice, we measure the correlation between the LLM performance on EHRNoteQA, and the LLM performance manually evaluated by clinicians. Results show that LLM performance on EHRNoteQA have higher correlation with clinician-evaluated performance (Spearman: 0.78, Kendall: 0.62) compared to other benchmarks, demonstrating its practical relevance in evaluating LLMs in clinical settings.
Authors: Jiachun Li, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Daojian Zeng, Kang Liu, Jun Zhao
Abstract: Large language models exhibit high-level commonsense reasoning abilities, especially with enhancement methods like Chain-of-Thought (CoT). However, we find these CoT-like methods lead to a considerable number of originally correct answers turning wrong, which we define as the Toxic CoT problem. To interpret and mitigate this problem, we first utilize attribution tracing and causal tracing methods to probe the internal working mechanism of the LLM during CoT reasoning. Through comparisons, we prove that the model exhibits information loss from the question over the shallow attention layers when generating rationales or answers. Based on the probing findings, we design a novel method called RIDERS (Residual decodIng and sERial-position Swap), which compensates for the information deficit in the model from both decoding and serial-position perspectives. Through extensive experiments on multiple commonsense reasoning benchmarks, we validate that this method not only significantly eliminates Toxic CoT problems (decreased by 23.6%), but also effectively improves the model's overall commonsense reasoning performance (increased by 5.5%).
Authors: Sara Abdali, Richard Anarfi, CJ Barberan, Jia He
Abstract: Large Language Models (LLMs) have revolutionized the field of Natural Language Generation (NLG) by demonstrating an impressive ability to generate human-like text. However, their widespread usage introduces challenges that necessitate thoughtful examination, ethical scrutiny, and responsible practices. In this study, we delve into these challenges, explore existing strategies for mitigating them, with a particular emphasis on identifying AI-generated text as the ultimate solution. Additionally, we assess the feasibility of detection from a theoretical perspective and propose novel research directions to address the current limitations in this domain.
Authors: Michael Ginn (University of Colorado), Lindia Tjuatja (Carnegie Mellon University), Taiqi He (Carnegie Mellon University), Enora Rice (University of Colorado), Graham Neubig (Carnegie Mellon University), Alexis Palmer (University of Colorado), Lori Levin (Carnegie Mellon University)
Abstract: Language documentation projects often involve the creation of annotated text in a format such as interlinear glossed text (IGT), which captures fine-grained morphosyntactic analyses in a morpheme-by-morpheme format. However, there are few existing resources providing large amounts of standardized, easily accessible IGT data, limiting their applicability to linguistic research, and making it difficult to use such data in NLP modeling. We compile the largest existing corpus of IGT data from a variety of sources, covering over 450k examples across 1.8k languages, to enable research on crosslingual transfer and IGT generation. We normalize much of our data to follow a standard set of labels across languages. Furthermore, we explore the task of automatically generating IGT in order to aid documentation projects. As many languages lack sufficient monolingual data, we pretrain a large multilingual model on our corpus. We demonstrate the utility of this model by finetuning it on monolingual corpora, outperforming SOTA models by up to 6.6%. We will make our pretrained model and dataset available through Hugging Face, as well as provide access through a web interface for use in language documentation efforts.
Authors: Juan Manuel Zambrano Chaves, Shih-Cheng Huang, Yanbo Xu, Hanwen Xu, Naoto Usuyama, Sheng Zhang, Fei Wang, Yujia Xie, Mahmoud Khademi, Ziyi Yang, Hany Awadalla, Julia Gong, Houdong Hu, Jianwei Yang, Chunyuan Li, Jianfeng Gao, Yu Gu, Cliff Wong, Mu Wei, Tristan Naumann, Muhao Chen, Matthew P. Lungren, Akshay Chaudhari, Serena Yeung-Levy, Curtis P. Langlotz, Sheng Wang, Hoifung Poon
Abstract: The scaling laws and extraordinary performance of large foundation models motivate the development and utilization of such models in biomedicine. However, despite early promising results on some biomedical benchmarks, there are still major challenges that need to be addressed before these models can be used in real-world clinics. Frontier general-domain models such as GPT-4V still have significant performance gaps in multimodal biomedical applications. More importantly, less-acknowledged pragmatic issues, including accessibility, model cost, and tedious manual evaluation make it hard for clinicians to use state-of-the-art large models directly on private patient data. Here, we explore training open-source small multimodal models (SMMs) to bridge competency gaps for unmet clinical needs in radiology. To maximize data efficiency, we adopt a modular approach by incorporating state-of-the-art pre-trained models for image and text modalities, and focusing on training a lightweight adapter to ground each modality to the text embedding space, as exemplified by LLaVA-Med. For training, we assemble a large dataset of over 697 thousand radiology image-text pairs. For evaluation, we propose CheXprompt, a GPT-4-based metric for factuality evaluation, and demonstrate its parity with expert evaluation. For best practice, we conduct a systematic ablation study on various choices in data engineering and multimodal training. The resulting LlaVA-Rad (7B) model attains state-of-the-art results on standard radiology tasks such as report generation and cross-modal retrieval, even outperforming much larger models such as GPT-4V and Med-PaLM M (84B). The inference of LlaVA-Rad is fast and can be performed on a single V100 GPU in private settings, offering a promising state-of-the-art tool for real-world clinical applications.
Authors: Kai Sun, Yushi Bai, Ji Qi, Lei Hou, Juanzi Li
Abstract: To advance the evaluation of multimodal math reasoning in large multimodal models (LMMs), this paper introduces a novel benchmark, MM-MATH. MM-MATH consists of 5,929 open-ended middle school math problems with visual contexts, with fine-grained classification across difficulty, grade level, and knowledge points. Unlike existing benchmarks relying on binary answer comparison, MM-MATH incorporates both outcome and process evaluations. Process evaluation employs LMM-as-a-judge to automatically analyze solution steps, identifying and categorizing errors into specific error types. Extensive evaluation of ten models on MM-MATH reveals significant challenges for existing LMMs, highlighting their limited utilization of visual information and struggles with higher-difficulty problems. The best-performing model achieves only 31% accuracy on MM-MATH, compared to 82% for humans. This highlights the challenging nature of our benchmark for existing models and the significant gap between the multimodal reasoning capabilities of current models and humans. Our process evaluation reveals that diagram misinterpretation is the most common error, accounting for more than half of the total error cases, underscoring the need for improved image comprehension in multimodal reasoning.
Authors: Yongcheng Zeng, Guoqing Liu, Weiyu Ma, Ning Yang, Haifeng Zhang, Jun Wang
Abstract: Fine-tuning pre-trained Large Language Models (LLMs) is essential to align them with human values and intentions. This process often utilizes methods like pairwise comparisons and KL divergence against a reference LLM, focusing on the evaluation of full answers generated by the models. However, the generation of these responses occurs in a token level, following a sequential, auto-regressive fashion. In this paper, we introduce Token-level Direct Preference Optimization (TDPO), a novel approach to align LLMs with human preferences by optimizing policy at the token level. Unlike previous methods, which face challenges in divergence efficiency, TDPO incorporates forward KL divergence constraints for each token, improving alignment and diversity. Utilizing the Bradley-Terry model for a token-based reward system, TDPO enhances the regulation of KL divergence, while preserving simplicity without the need for explicit reward modeling. Experimental results across various text tasks demonstrate TDPO's superior performance in balancing alignment with generation diversity. Notably, fine-tuning with TDPO strikes a better balance than DPO in the controlled sentiment generation and single-turn dialogue datasets, and significantly improves the quality of generated responses compared to both DPO and PPO-based RLHF methods. Our code is open-sourced at https://github.com/Vance0124/Token-level-Direct-Preference-Optimization.
URLs: https://github.com/Vance0124/Token-level-Direct-Preference-Optimization.
Authors: Yuchen Tian, Weixiang Yan, Qian Yang, Qian Chen, Wen Wang, Ziyang Luo, Lei Ma
Abstract: Large Language Models (LLMs) have made significant progress in code generation, providing developers with unprecedented automated programming support. However, LLMs often generate code that is syntactically correct and even semantically plausible but may not execute as expected or meet specified requirements. This phenomenon of hallucinations in the code domain has not been systematically explored. To enhance the community's understanding and research on this issue, we introduce the concept of code hallucinations and propose a classification method for code hallucination based on execution verification. We classify code hallucinations into four main types: mapping, naming, resource, and logic hallucinations, with each category further divided into different subcategories to understand and address the unique challenges faced by LLMs in code generation with finer granularity. Additionally, we develop a dynamic detection algorithm named CodeHalu to quantify code hallucinations and establish the CodeHaluEval benchmark, which includes 8,883 samples from 699 tasks to systematically and quantitatively evaluate code hallucinations. By evaluating 17 popular LLMs on this benchmark, we reveal significant differences in their accuracy and reliability in code generation and provide detailed insights for further improving the code generation capabilities of LLMs. The CodeHalu benchmark and code are publicly available at https://github.com/yuchen814/CodeHalu.
Authors: Matthew Raffel, Victor Agostinelli, Lizhong Chen
Abstract: Large language models (LLMs) have achieved state-of-the-art performance in various language processing tasks, motivating their adoption in simultaneous translation. Current fine-tuning methods to adapt LLMs for simultaneous translation focus on prompting optimization strategies using either data augmentation or prompt structure modifications. However, these methods suffer from several issues, such as unnecessarily expanded training sets, computational inefficiency from dumping the key and value cache, increased prompt sizes, or restriction to a single decision policy. To eliminate these issues, in this work, we propose SimulMask, a new paradigm for fine-tuning LLMs for simultaneous translation. It utilizes a novel attention mask approach that models simultaneous translation during fine-tuning by masking attention for a desired decision policy. Applying the proposed SimulMask on a Falcon LLM for the IWSLT 2017 dataset, we have observed a significant translation quality improvement compared to state-of-the-art prompting optimization strategies on five language pairs while reducing the computational cost.
Authors: Rui Guo, Greg Farnan, Niall McLaughlin, Barry Devereux
Abstract: The BioNLP ACL'24 Shared Task on Streamlining Discharge Documentation aims to reduce the administrative burden on clinicians by automating the creation of critical sections of patient discharge letters. This paper presents our approach using the Llama3 8B quantized model to generate the "Brief Hospital Course" and "Discharge Instructions" sections. We employ a zero-shot method combined with Retrieval-Augmented Generation (RAG) to produce concise, contextually accurate summaries. Our contributions include the development of a curated template-based approach to ensure reliability and consistency, as well as the integration of RAG for word count prediction. We also describe several unsuccessful experiments to provide insights into our pathway for the competition. Our results demonstrate the effectiveness and efficiency of our approach, achieving high scores across multiple evaluation metrics.
Authors: Marcely Zanon Boito, Vivek Iyer, Nikolaos Lagos, Laurent Besacier, Ioan Calapodescu
Abstract: We present mHuBERT-147, the first general-purpose massively multilingual HuBERT speech representation model trained on 90K hours of clean, open-license data. To scale up the multi-iteration HuBERT approach, we use faiss-based clustering, achieving 5.2x faster label assignment than the original method. We also apply a new multilingual batching up-sampling strategy, leveraging both language and dataset diversity. After 3 training iterations, our compact 95M parameter mHuBERT-147 outperforms larger models trained on substantially more data. We rank second and first on the ML-SUPERB 10min and 1h leaderboards, with SOTA scores for 3 tasks. Across ASR/LID tasks, our model consistently surpasses XLS-R (300M params; 436K hours) and demonstrates strong competitiveness against the much larger MMS (1B params; 491K hours). Our findings indicate that mHuBERT-147 is a promising model for multilingual speech tasks, offering an unprecedented balance between high performance and parameter efficiency.
Authors: Zijin Hong, Zheng Yuan, Qinggang Zhang, Hao Chen, Junnan Dong, Feiran Huang, Xiao Huang
Abstract: Generating accurate SQL according to natural language questions (text-to-SQL) is a long-standing challenge due to the complexities involved in user question understanding, database schema comprehension, and SQL generation. Conventional text-to-SQL systems, comprising human engineering and deep neural networks, have made substantial progress. Subsequently, pre-trained language models (PLMs) have been developed and utilized for text-to-SQL tasks, achieving promising performance. As modern databases become more complex, the corresponding user questions also grow more challenging, leading PLMs with limited comprehension capabilities to produce incorrect SQL. This necessitates more sophisticated and tailored optimization methods for PLMs, which, in turn, restricts the applications of PLM-based systems. Most recently, large language models (LLMs) have demonstrated significant capabilities in natural language understanding as the model scale remains increasing. Therefore, integrating the LLM-based implementation can bring unique opportunities, improvements, and solutions to text-to-SQL research. In this survey, we present a comprehensive review of LLM-based text-to-SQL. Specifically, we propose a brief overview of the technical challenges and the evolutionary process of text-to-SQL. Then, we provide a detailed introduction to the datasets and metrics designed to evaluate text-to-SQL systems. After that, we present a systematic analysis of recent advances in LLM-based text-to-SQL. Finally, we discuss the remaining challenges in this field and propose expectations for future research directions.
Authors: Chengzhengxu Li, Xiaoming Liu, Zhaohan Zhang, Yichen Wang, Chen Liu, Yu Lan, Chao Shen
Abstract: Recent advances in prompt optimization have notably enhanced the performance of pre-trained language models (PLMs) on downstream tasks. However, the potential of optimized prompts on domain generalization has been under-explored. To explore the nature of prompt generalization on unknown domains, we conduct pilot experiments and find that (i) Prompts gaining more attention weight from PLMs' deep layers are more generalizable and (ii) Prompts with more stable attention distributions in PLMs' deep layers are more generalizable. Thus, we offer a fresh objective towards domain-generalizable prompts optimization named "Concentration", which represents the "lookback" attention from the current decoding token to the prompt tokens, to increase the attention strength on prompts and reduce the fluctuation of attention distribution. We adapt this new objective to popular soft prompt and hard prompt optimization methods, respectively. Extensive experiments demonstrate that our idea improves comparison prompt optimization methods by 1.42% for soft prompt generalization and 2.16% for hard prompt generalization in accuracy on the multi-source domain generalization setting, while maintaining satisfying in-domain performance. The promising results validate the effectiveness of our proposed prompt optimization objective and provide key insights into domain-generalizable prompts.
Authors: Yuyan Zhou, Liang Song, Bingning Wang, Weipeng Chen
Abstract: The advent of large language models (LLMs) like GPT-4 has catalyzed the exploration of multi-task learning (MTL), in which a single model demonstrates proficiency across diverse tasks. Task arithmetic has emerged as a cost-effective approach for MTL. It enables performance enhancement across multiple tasks by adding their corresponding task vectors to a pre-trained model. However, the current lack of a method that can simultaneously achieve optimal performance, computational efficiency, and data privacy limits their application to LLMs. In this paper, we propose \textbf{M}odel \textbf{E}xclusive \textbf{T}ask \textbf{A}rithmetic for merging \textbf{GPT}-scale models, which formalizes the objective of model merging into a multi-task learning framework, aiming to minimize the average loss difference between the merged model and each individual task model. Since data privacy limits the use of multi-task training data, we leverage LLMs' local linearity and task vectors' orthogonality to separate the data term and scaling coefficients term and derive a model-exclusive task arithmetic method. Our proposed MetaGPT is data-agnostic and bypasses the heavy search process, making it cost-effective and easy to implement for LLMs.Extensive experiments demonstrate that MetaGPT leads to improvements in task arithmetic and achieves state-of-the-art performance on multiple tasks.
Authors: Boyi Deng, Wenjie Wang, Fengbin Zhu, Qifan Wang, Fuli Feng
Abstract: Retrieval-Augmented Generation (RAG) can alleviate hallucinations of Large Language Models (LLMs) by referencing external documents. However, the misinformation in external documents may mislead LLMs' generation. To address this issue, we explore the task of "credibility-aware RAG", in which LLMs automatically adjust the influence of retrieved documents based on their credibility scores to counteract misinformation. To this end, we introduce a plug-and-play method named $\textbf{Cr}$edibility-aware $\textbf{A}$ttention $\textbf{M}$odification (CrAM). CrAM identifies influential attention heads in LLMs and adjusts their attention weights based on the credibility of the documents, thereby reducing the impact of low-credibility documents. Experiments on Natual Questions and TriviaQA using Llama2-13B, Llama3-8B, and Qwen-7B show that CrAM improves the RAG performance of LLMs against misinformation pollution by over 20%, even surpassing supervised fine-tuning methods.
Authors: Nikhil Khandekar, Qiao Jin, Guangzhi Xiong, Soren Dunn, Serina S Applebaum, Zain Anwar, Maame Sarfo-Gyamfi, Conrad W Safranek, Abid A Anwar, Andrew Zhang, Aidan Gilson, Maxwell B Singer, Amisha Dave, Andrew Taylor, Aidong Zhang, Qingyu Chen, Zhiyong Lu
Abstract: As opposed to evaluating computation and logic-based reasoning, current benchmarks for evaluating large language models (LLMs) in medicine are primarily focused on question-answering involving domain knowledge and descriptive reasoning. While such qualitative capabilities are vital to medical diagnosis, in real-world scenarios, doctors frequently use clinical calculators that follow quantitative equations and rule-based reasoning paradigms for evidence-based decision support. To this end, we propose MedCalc-Bench, a first-of-its-kind dataset focused on evaluating the medical calculation capability of LLMs. MedCalc-Bench contains an evaluation set of over 1000 manually reviewed instances from 55 different medical calculation tasks. Each instance in MedCalc-Bench consists of a patient note, a question requesting to compute a specific medical value, a ground truth answer, and a step-by-step explanation showing how the answer is obtained. While our evaluation results show the potential of LLMs in this area, none of them are effective enough for clinical settings. Common issues include extracting the incorrect entities, not using the correct equation or rules for a calculation task, or incorrectly performing the arithmetic for the computation. We hope our study highlights the quantitative knowledge and reasoning gaps in LLMs within medical settings, encouraging future improvements of LLMs for various clinical calculation tasks.
Authors: Yichen Pan, Dehan Kong, Sida Zhou, Cheng Cui, Yifei Leng, Bing Jiang, Hangyu Liu, Yanyi Shang, Shuyan Zhou, Tongshuang Wu, Zhengyang Wu
Abstract: For web agents to be practically useful, they must adapt to the continuously evolving web environment characterized by frequent updates to user interfaces and content. However, most existing benchmarks only capture the static aspects of the web. To bridge this gap, we introduce WebCanvas, an innovative online evaluation framework for web agents that effectively addresses the dynamic nature of web interactions. WebCanvas contains three main components to facilitate realistic assessments: (1) A novel evaluation metric which reliably capture critical intermediate actions or states necessary for task completions while disregarding noise caused by insignificant events or changed web-elements. (2) A benchmark dataset called Mind2Web-Live, a refined version of original Mind2Web static dataset containing 542 tasks with 2439 intermediate evaluation states; (3) Lightweight and generalizable annotation tools and testing pipelines that enables the community to collect and maintain the high-quality, up-to-date dataset. Building on WebCanvas, we open-source an agent framework with extensible modules for reasoning, providing a foundation for the community to conduct online inference and evaluations. Our best-performing agent achieves a task success rate of 23.1% and a task completion rate of 48.8% on the Mind2Web-Live test set. Additionally, we analyze the performance discrepancies across various websites, domains, and experimental environments. We encourage the community to contribute further insights on online agent evaluation, thereby advancing this field of research.
Authors: Hongbang Yuan, Yubo Chen, Pengfei Cao, Zhuoran Jin, Kang Liu, Jun Zhao
Abstract: Large language models (LLMs) have achieved remarkable success but still tend to generate factually erroneous responses, a phenomenon known as hallucination. A recent trend is to use preference learning to fine-tune models to align with factuality. However, existing work primarily evaluates fine-tuned models on in-domain (ID) datasets and the factuality on out-of-domain (OOD) datasets remains underexplored. In this paper, we conduct a comprehensive evaluation of the factuality of different models tuned by various preference learning algorithms and demonstrate that their performance on OOD datasets either increases minimally or decreases. Subsequently, we reveal that the main cause of model's failure to uphold factuality under a distribution shift is \textbf{under-alignment}, rather than \textbf{over-alignment}, by analyzing the token distribution shift of the models before and after tuning. Finally, we propose \textbf{APEFT} (\textbf{A}tomic \textbf{P}reference \textbf{E}nhanced \textbf{F}actuality \textbf{T}uning), a framework that enhances model's awareness of factuality at the granularity of individual facts. Extensive experiments demonstrate that APEFT improves model performance by an average of $\boldsymbol{3.45\%}$ on both ID and OOD datasets, which is highly effective.
Authors: Qinyuan Cheng, Xiaonan Li, Shimin Li, Qin Zhu, Zhangyue Yin, Yunfan Shao, Linyang Li, Tianxiang Sun, Hang Yan, Xipeng Qiu
Abstract: In Retrieval-Augmented Generation (RAG), retrieval is not always helpful and applying it to every instruction is sub-optimal. Therefore, determining whether to retrieve is crucial for RAG, which is usually referred to as Active Retrieval. However, existing active retrieval methods face two challenges: 1. They usually rely on a single criterion, which struggles with handling various types of instructions. 2. They depend on specialized and highly differentiated procedures, and thus combining them makes the RAG system more complicated and leads to higher response latency. To address these challenges, we propose Unified Active Retrieval (UAR). UAR contains four orthogonal criteria and casts them into plug-and-play classification tasks, which achieves multifaceted retrieval timing judgements with negligible extra inference cost. We further introduce the Unified Active Retrieval Criteria (UAR-Criteria), designed to process diverse active retrieval scenarios through a standardized procedure. Experiments on four representative types of user instructions show that UAR significantly outperforms existing work on the retrieval timing judgement and the performance of downstream tasks, which shows the effectiveness of UAR and its helpfulness to downstream tasks.
Authors: Devichand Budagam, Sankalp KJ, Ashutosh Kumar, Vinija Jain, Aman Chadha
Abstract: Assessing the effectiveness of large language models (LLMs) in addressing diverse tasks is essential for comprehending their strengths and weaknesses. Conventional evaluation techniques typically apply a single prompting strategy uniformly across datasets, not considering the varying degrees of task complexity. We introduce the Hierarchical Prompting Taxonomy (HPT), a taxonomy that employs a Hierarchical Prompt Framework (HPF) composed of five unique prompting strategies, arranged from the simplest to the most complex, to assess LLMs more precisely and to offer a clearer perspective. This taxonomy assigns a score, called the Hierarchical Prompting Score (HP-Score), to datasets as well as LLMs based on the rules of the taxonomy, providing a nuanced understanding of their ability to solve diverse tasks and offering a universal measure of task complexity. Additionally, we introduce the Adaptive Hierarchical Prompt framework, which automates the selection of appropriate prompting strategies for each task. This study compares manual and adaptive hierarchical prompt frameworks using four instruction-tuned LLMs, namely Llama 3 8B, Phi 3 3.8B, Mistral 7B, and Gemma 7B, across four datasets: BoolQ, CommonSenseQA (CSQA), IWSLT-2017 en-fr (IWSLT), and SamSum. Experiments demonstrate the effectiveness of HPT, providing a reliable way to compare different tasks and LLM capabilities. This paper leads to the development of a universal evaluation metric that can be used to evaluate both the complexity of the datasets and the capabilities of LLMs. The implementation of both manual HPF and adaptive HPF is publicly available.
Authors: Xueqing Wu, Zongyu Lin, Songyan Zhao, Te-Lin Wu, Pan Lu, Nanyun Peng, Kai-Wei Chang
Abstract: Visual programs are executable code generated by large language models to address visual reasoning problems. They decompose complex questions into multiple reasoning steps and invoke specialized models for each step to solve the problems. However, these programs are prone to logic errors, with our preliminary evaluation showing that 58% of the total errors are caused by program logic errors. Debugging complex visual programs remains a major bottleneck for visual reasoning. To address this, we introduce VDebugger, a novel critic-refiner framework trained to localize and debug visual programs by tracking execution step by step. VDebugger identifies and corrects program errors leveraging detailed execution feedback, improving interpretability and accuracy. The training data is generated through an automated pipeline that injects errors into correct visual programs using a novel mask-best decoding technique. Evaluations on six datasets demonstrate VDebugger's effectiveness, showing performance improvements of up to 3.2% in downstream task accuracy. Further studies show VDebugger's ability to generalize to unseen tasks, bringing a notable improvement of 2.3% on the unseen COVR task. Code, data and models are made publicly available at https://github.com/shirley-wu/vdebugger/
Authors: Yiduo Guo, Jie Fu, Huishuai Zhang, Dongyan Zhao, Yikang Shen
Abstract: Continual pre-training has increasingly become the predominant approach for adapting Large Language Models (LLMs) to new domains. This process involves updating the pre-trained LLM with a corpus from a new domain, resulting in a shift in the training distribution. To study the behavior of LLMs during this shift, we measured the model's performance throughout the continual pre-training process. we observed a temporary performance drop at the beginning, followed by a recovery phase, a phenomenon known as the "stability gap," previously noted in vision models classifying new classes. To address this issue and enhance LLM performance within a fixed compute budget, we propose three effective strategies: (1) Continually pre-training the LLM on a subset with a proper size for multiple epochs, resulting in faster performance recovery than pre-training the LLM on a large corpus in a single epoch; (2) Pre-training the LLM only on high-quality sub-corpus, which rapidly boosts domain performance; and (3) Using a data mixture similar to the pre-training data to reduce distribution gap. We conduct various experiments on Llama-family models to validate the effectiveness of our strategies in both medical continual pre-training and instruction tuning. For example, our strategies improve the average medical task performance of the OpenLlama-3B model from 36.2% to 40.7% with only 40% of the original training budget and enhance the average general task performance without causing forgetting. Furthermore, we apply our strategies to the Llama-3-8B model. The resulting model, Llama-3-Physician, achieves the best medical performance among current open-source models, and performs comparably to or even better than GPT-4 on several medical benchmarks. We release our models at \url{https://huggingface.co/YiDuo1999/Llama-3-Physician-8B-Instruct}.
URLs: https://huggingface.co/YiDuo1999/Llama-3-Physician-8B-Instruct
Authors: Shijia Zhou, Siyao Peng, Barbara Plank
Abstract: Climate Change (CC) is a pressing topic of global importance, attracting increasing attention across research fields, from social sciences to Natural Language Processing (NLP). CC is also discussed in various settings and communication platforms, from academic publications to social media forums. Understanding who and what is mentioned in such data is a first critical step to gaining new insights into CC. We present CLIMATELI (CLIMATe Entity LInking), the first manually annotated CC dataset that links 3,087 entity spans to Wikipedia. Using CLIMATELI (CLIMATe Entity LInking), we evaluate existing entity linking (EL) systems on the CC topic across various genres and propose automated filtering methods for CC entities. We find that the performance of EL models notably lags behind humans at both token and entity levels. Testing within the scope of retaining or excluding non-nominal and/or non-CC entities particularly impacts the models' performances.
Authors: Abe Bohan Hou, Orion Weller, Guanghui Qin, Eugene Yang, Dawn Lawrie, Nils Holzenberger, Andrew Blair-Stanek, Benjamin Van Durme
Abstract: Legal professionals need to write analyses that rely on citations to relevant precedents, i.e., previous case decisions. Intelligent systems assisting legal professionals in writing such documents provide great benefits but are challenging to design. Such systems need to help locate, summarize, and reason over salient precedents in order to be useful. To enable systems for such tasks, we work with legal professionals to transform a large open-source legal corpus into a dataset supporting two important backbone tasks: information retrieval (IR) and retrieval-augmented generation (RAG). This dataset CLERC (Case Law Evaluation Retrieval Corpus), is constructed for training and evaluating models on their ability to (1) find corresponding citations for a given piece of legal analysis and to (2) compile the text of these citations (as well as previous context) into a cogent analysis that supports a reasoning goal. We benchmark state-of-the-art models on CLERC, showing that current approaches still struggle: GPT-4o generates analyses with the highest ROUGE F-scores but hallucinates the most, while zero-shot IR models only achieve 48.3% recall@1000.
Authors: Yasmin Moslem
Abstract: This paper describes our system submission to the International Conference on Spoken Language Translation (IWSLT 2024) for Irish-to-English speech translation. We built end-to-end systems based on Whisper, and employed a number of data augmentation techniques, such as speech back-translation and noise augmentation. We investigate the effect of using synthetic audio data and discuss several methods for enriching signal diversity.
Authors: Wenjing Zhang, Siqi Xiao, Xuejiao Lei, Ning Wang, Huazheng Zhang, Meijuan An, Bikun Yang, Zhaoxiang Liu, Kai Wang, Shiguo Lian
Abstract: The rapid growth of large language models(LLMs) has emerged as a prominent trend in the field of artificial intelligence. However, current state-of-the-art LLMs are predominantly based on English. They encounter limitations when directly applied to tasks in specific cultural domains, due to deficiencies in domain-specific knowledge and misunderstandings caused by differences in cultural values. To address this challenge, our paper proposes a rapid adaptation method for large models in specific cultural contexts, which leverages instruction-tuning based on specific cultural knowledge and safety values data. Taking Chinese as the specific cultural context and utilizing the LLaMA3-8B as the experimental English LLM, the evaluation results demonstrate that the adapted LLM significantly enhances its capabilities in domain-specific knowledge and adaptability to safety values, while maintaining its original expertise advantages.
Authors: Italo Luis da Silva, Hanqi Yan, Lin Gui, Yulan He
Abstract: The inherent ambiguity of cause and effect boundaries poses a challenge in evaluating causal event extraction tasks. Traditional metrics like Exact Match and BertScore poorly reflect model performance, so we trained evaluation models to approximate human evaluation, achieving high agreement. We used them to perform Reinforcement Learning with extraction models to align them with human preference, prioritising semantic understanding. We successfully explored our approach through multiple datasets, including transferring an evaluator trained on one dataset to another as a way to decrease the reliance on human-annotated data. In that vein, we also propose a weak-to-strong supervision method that uses a fraction of the annotated data to train an evaluation model while still achieving high performance in training an RL model. Our code is available at https://github.com/oyarsa/event_extraction/tree/causal-event-extraction.
URLs: https://github.com/oyarsa/event_extraction/tree/causal-event-extraction.
Authors: Lei Zhang, Yunshui Li, Jiaming Li, Xiaobo Xia, Jiaxi Yang, Run Luo, Minzheng Wang, Longze Chen, Junhao Liu, Min Yang
Abstract: Some recently developed code large language models (Code LLMs) have been pre-trained on repository-level code data (Repo-Code LLMs), enabling these models to recognize repository structures and utilize cross-file information for code completion. However, in real-world development scenarios, simply concatenating the entire code repository often exceeds the context window limits of these Repo-Code LLMs, leading to significant performance degradation. In this study, we conducted extensive preliminary experiments and analyses on six Repo-Code LLMs. The results indicate that maintaining the topological dependencies of files and increasing the code file content in the completion prompts can improve completion accuracy; pruning the specific implementations of functions in all dependent files does not significantly reduce the accuracy of completions. Based on these findings, we proposed a strategy named Hierarchical Context Pruning (HCP) to construct completion prompts with high informational code content. The HCP models the code repository at the function level, maintaining the topological dependencies between code files while removing a large amount of irrelevant code content, significantly reduces the input length for repository-level code completion. We applied the HCP strategy in experiments with six Repo-Code LLMs, and the results demonstrate that our proposed method can significantly enhance completion accuracy while substantially reducing the length of input. Our code and data are available at https://github.com/Hambaobao/HCP-Coder.
Authors: Ann Speed
Abstract: Generative AI models garnered a large amount of public attention and speculation with the release of OpenAIs chatbot, ChatGPT. At least two opinion camps exist: one excited about possibilities these models offer for fundamental changes to human tasks, and another highly concerned about power these models seem to have. To address these concerns, we assessed several LLMs, primarily GPT 3.5, using standard, normed, and validated cognitive and personality measures. For this seedling project, we developed a battery of tests that allowed us to estimate the boundaries of some of these models capabilities, how stable those capabilities are over a short period of time, and how they compare to humans. Our results indicate that LLMs are unlikely to have developed sentience, although its ability to respond to personality inventories is interesting. GPT3.5 did display large variability in both cognitive and personality measures over repeated observations, which is not expected if it had a human-like personality. Variability notwithstanding, LLMs display what in a human would be considered poor mental health, including low self-esteem, marked dissociation from reality, and in some cases narcissism and psychopathy, despite upbeat and helpful responses.
Authors: Pingyi Chen, Honglin Li, Chenglu Zhu, Sunyi Zheng, Zhongyi Shui, Lin Yang
Abstract: Whole slide images are the foundation of digital pathology for the diagnosis and treatment of carcinomas. Writing pathology reports is laborious and error-prone for inexperienced pathologists. To reduce the workload and improve clinical automation, we investigate how to generate pathology reports given whole slide images. On the data end, we curated the largest WSI-text dataset (PathText). In specific, we collected nearly 10000 high-quality WSI-text pairs for visual-language models by recognizing and cleaning pathology reports which narrate diagnostic slides in TCGA. On the model end, we propose the multiple instance generative model (MI-Gen) which can produce pathology reports for gigapixel WSIs. We benchmark our model on the largest subset of TCGA-PathoText. Experimental results show our model can generate pathology reports which contain multiple clinical clues and achieve competitive performance on certain slide-level tasks. We observe that simple semantic extraction from the pathology reports can achieve the best performance (0.838 of F1 score) on BRCA subtyping surpassing previous state-of-the-art approaches. Our collected dataset and related code are available.
Authors: Marta R. Costa-juss\`a, Mariano Coria Meglioli, Pierre Andrews, David Dale, Prangthip Hansanti, Elahe Kalbassi, Alex Mourachko, Christophe Ropers, Carleigh Wood
Abstract: Research in toxicity detection in natural language processing for the speech modality (audio-based) is quite limited, particularly for languages other than English. To address these limitations and lay the groundwork for truly multilingual audio-based toxicity detection, we introduce MuTox, the first highly multilingual audio-based dataset with toxicity labels. The dataset comprises 20,000 audio utterances for English and Spanish, and 4,000 for the other 19 languages. To demonstrate the quality of this dataset, we trained the MuTox audio-based toxicity classifier, which enables zero-shot toxicity detection across a wide range of languages. This classifier outperforms existing text-based trainable classifiers by more than 1% AUC, while expanding the language coverage more than tenfold. When compared to a wordlist-based classifier that covers a similar number of languages, MuTox improves precision and recall by approximately 2.5 times. This significant improvement underscores the potential of MuTox in advancing the field of audio-based toxicity detection.
Authors: Yue Fan, Jing Gu, Kaiwen Zhou, Qianqi Yan, Shan Jiang, Ching-Chen Kuo, Xinze Guan, Xin Eric Wang
Abstract: Multipanel images, commonly seen as web screenshots, posters, etc., pervade our daily lives. These images, characterized by their composition of multiple subfigures in distinct layouts, effectively convey information to people. Toward building advanced multimodal AI applications, such as agents that understand complex scenes and navigate through webpages, the skill of multipanel visual reasoning is essential, and a comprehensive evaluation of models in this regard is important. Therefore, we introduce Multipanel Visual Question Answering (MultipanelVQA), a novel benchmark comprising 6,600 triplets of questions, answers, and multipanel images that specifically challenge models in comprehending multipanel images. Our evaluation shows that questions in the MultipanelVQA benchmark pose significant challenges to the state-of-the-art Multimodal Large Language Models (MLLMs) tested, even though humans can attain approximately 99% accuracy on these questions. Distinctively, the MultipanelVQA benchmark features synthetically generated multipanel images specifically crafted to isolate and assess the impact of various factors, such as the layout, on MLLMs' multipanel image comprehension abilities. As a result, in addition to benchmarking the capabilities of MLLMs in understanding multipanel images, we analyze various factors of the multipanel image that affect MLLMs' performance with synthetic data and offer insights for enhancement. Code and data are released at https://sites.google.com/view/multipanelvqa/home.
Authors: Boyi Wei, Kaixuan Huang, Yangsibo Huang, Tinghao Xie, Xiangyu Qi, Mengzhou Xia, Prateek Mittal, Mengdi Wang, Peter Henderson
Abstract: Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This study explores this brittleness of safety alignment by leveraging pruning and low-rank modifications. We develop methods to identify critical regions that are vital for safety guardrails, and that are disentangled from utility-relevant regions at both the neuron and rank levels. Surprisingly, the isolated regions we find are sparse, comprising about $3\%$ at the parameter level and $2.5\%$ at the rank level. Removing these regions compromises safety without significantly impacting utility, corroborating the inherent brittleness of the model's safety mechanisms. Moreover, we show that LLMs remain vulnerable to low-cost fine-tuning attacks even when modifications to the safety-critical regions are restricted. These findings underscore the urgent need for more robust safety strategies in LLMs.
Authors: Zechun Liu, Changsheng Zhao, Forrest Iandola, Chen Lai, Yuandong Tian, Igor Fedorov, Yunyang Xiong, Ernie Chang, Yangyang Shi, Raghuraman Krishnamoorthi, Liangzhen Lai, Vikas Chandra
Abstract: This paper addresses the growing need for efficient large language models (LLMs) on mobile devices, driven by increasing cloud costs and latency concerns. We focus on designing top-quality LLMs with fewer than a billion parameters, a practical choice for mobile deployment. Contrary to prevailing belief emphasizing the pivotal role of data and parameter quantity in determining model quality, our investigation underscores the significance of model architecture for sub-billion scale LLMs. Leveraging deep and thin architectures, coupled with embedding sharing and grouped-query attention mechanisms, we establish a strong baseline network denoted as MobileLLM, which attains a remarkable 2.7%/4.3% accuracy boost over preceding 125M/350M state-of-the-art models. Additionally, we propose an immediate block-wise weight-sharing approach with no increase in model size and only marginal latency overhead. The resultant models, denoted as MobileLLM-LS, demonstrate a further accuracy enhancement of 0.7%/0.8% than MobileLLM 125M/350M. Moreover, MobileLLM model family shows significant improvements compared to previous sub-billion models on chat benchmarks, and demonstrates close correctness to LLaMA-v2 7B in API calling tasks, highlighting the capability of small models for common on-device use cases.
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 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: Maohao Shen, Subhro Das, Kristjan Greenewald, Prasanna Sattigeri, Gregory Wornell, Soumya Ghosh
Abstract: We consider the issue of calibration in large language models (LLM). Recent studies have found that common interventions such as instruction tuning often result in poorly calibrated LLMs. Although calibration is well-explored in traditional applications, calibrating LLMs is uniquely challenging. These challenges stem as much from the severe computational requirements of LLMs as from their versatility, which allows them to be applied to diverse tasks. Addressing these challenges, we propose THERMOMETER, a calibration approach tailored to LLMs. THERMOMETER learns an auxiliary model, given data from multiple tasks, for calibrating a LLM. It is computationally efficient, preserves the accuracy of the LLM, and produces better-calibrated responses for new tasks. Extensive empirical evaluations across various benchmarks demonstrate the effectiveness of the proposed method.
Authors: Manish Dhakal, Rabin Adhikari, Safal Thapaliya, Bishesh Khanal
Abstract: Foundation Vision-Language Models (VLMs) trained using large-scale open-domain images and text pairs have recently been adapted to develop Vision-Language Segmentation Models (VLSMs) that allow providing text prompts during inference to guide image segmentation. If robust and powerful VLSMs can be built for medical images, it could aid medical professionals in many clinical tasks where they must spend substantial time delineating the target structure of interest. VLSMs for medical images resort to fine-tuning base VLM or VLSM pretrained on open-domain natural image datasets due to fewer annotated medical image datasets; this fine-tuning is resource-consuming and expensive as it usually requires updating all or a significant fraction of the pretrained parameters. Recently, lightweight blocks called adapters have been proposed in VLMs that keep the pretrained model frozen and only train adapters during fine-tuning, substantially reducing the computing resources required. We introduce a novel adapter, VLSM-Adapter, that can fine-tune pretrained vision-language segmentation models using transformer encoders. Our experiments in widely used CLIP-based segmentation models show that with only 3 million trainable parameters, the VLSM-Adapter outperforms state-of-the-art and is comparable to the upper bound end-to-end fine-tuning. The source code is available at: https://github.com/naamiinepal/vlsm-adapter.
Authors: Manuel E. Lladser, Alexander J. Paradise
Abstract: A subset of points in a metric space is said to resolve it if each point in the space is uniquely characterized by its distance to each point in the subset. In particular, resolving sets can be used to represent points in abstract metric spaces as Euclidean vectors. Importantly, due to the triangle inequality, points close by in the space are represented as vectors with similar coordinates, which may find applications in classification problems of symbolic objects under suitably chosen metrics. In this manuscript, we address the resolvability of Jaccard spaces, i.e., metric spaces of the form $(2^X,\text{Jac})$, where $2^X$ is the power set of a finite set $X$, and $\text{Jac}$ is the Jaccard distance between subsets of $X$. Specifically, for different $a,b\in 2^X$, $\text{Jac}(a,b)=|a\Delta b|/|a\cup b|$, where $|\cdot|$ denotes size (i.e., cardinality) and $\Delta$ denotes the symmetric difference of sets. We combine probabilistic and linear algebra arguments to construct highly likely but nearly optimal (i.e., of minimal size) resolving sets of $(2^X,\text{Jac})$. In particular, we show that the metric dimension of $(2^X,\text{Jac})$, i.e., the minimum size of a resolving set of this space, is $\Theta(|X|/\ln|X|)$. In addition, we show that a much smaller subset of $2^X$ suffices to resolve, with high probability, all different pairs of subsets of $X$ of cardinality at most $\sqrt{|X|}/\ln|X|$, up to a factor.
Authors: Sewade Ogun, Abraham T. Owodunni, Tobi Olatunji, Eniola Alese, Babatunde Oladimeji, Tejumade Afonja, Kayode Olaleye, Naome A. Etori, Tosin Adewumi
Abstract: Recent advances in speech synthesis have enabled many useful applications like audio directions in Google Maps, screen readers, and automated content generation on platforms like TikTok. However, these systems are mostly dominated by voices sourced from data-rich geographies with personas representative of their source data. Although 3000 of the world's languages are domiciled in Africa, African voices and personas are under-represented in these systems. As speech synthesis becomes increasingly democratized, it is desirable to increase the representation of African English accents. We present Afro-TTS, the first pan-African accented English speech synthesis system able to generate speech in 86 African accents, with 1000 personas representing the rich phonological diversity across the continent for downstream application in Education, Public Health, and Automated Content Creation. Speaker interpolation retains naturalness and accentedness, enabling the creation of new voices.
Authors: Ahmed Abdeen Hamed, Tamer E. Fandy
Abstract: The objective of this research is to introduce a network specialized in predicting drugs that can be repurposed by investigating real-world evidence sources, such as clinical trials and biomedical literature. Specifically, it aims to generate drug combination therapies for complex diseases (e.g., cancer, Alzheimer's). We present a multilayered network medicine approach, empowered by a highly configured ChatGPT prompt engineering system, which is constructed on the fly to extract drug mentions in clinical trials. Additionally, we introduce a novel algorithm that connects real-world evidence with disease-specific signaling pathways (e.g., KEGG database). This sheds light on the repurposability of drugs if they are found to bind with one or more protein constituents of a signaling pathway. To demonstrate, we instantiated the framework for breast cancer and found that, out of 46 breast cancer signaling pathways, the framework identified 38 pathways that were covered by at least two drugs. This evidence signals the potential for combining those drugs. Specifically, the most covered signaling pathway, ID hsa:2064, was covered by 108 drugs, some of which can be combined. Conversely, the signaling pathway ID hsa:1499 was covered by only two drugs, indicating a significant gap for further research. Our network medicine framework, empowered by GenAI, shows promise in identifying drug combinations with a high degree of specificity, knowing the exact signaling pathways and proteins that serve as targets. It is noteworthy that ChatGPT successfully accelerated the process of identifying drug mentions in clinical trials, though further investigations are required to determine the relationships among the drug mentions.
Authors: Zhiyu Tan, Xiaomeng Yang, Luozheng Qin, Mengping Yang, Cheng Zhang, Hao Li
Abstract: The recent advancements in text-to-image generative models have been remarkable. Yet, the field suffers from a lack of evaluation metrics that accurately reflect the performance of these models, particularly lacking fine-grained metrics that can guide the optimization of the models. In this paper, we propose EvalAlign, a metric characterized by its accuracy, stability, and fine granularity. Our approach leverages the capabilities of Multimodal Large Language Models (MLLMs) pre-trained on extensive datasets. We develop evaluation protocols that focus on two key dimensions: image faithfulness and text-image alignment. Each protocol comprises a set of detailed, fine-grained instructions linked to specific scoring options, enabling precise manual scoring of the generated images. We Supervised Fine-Tune (SFT) the MLLM to align closely with human evaluative judgments, resulting in a robust evaluation model. Our comprehensive tests across 24 text-to-image generation models demonstrate that EvalAlign not only provides superior metric stability but also aligns more closely with human preferences than existing metrics, confirming its effectiveness and utility in model assessment.
Authors: Zengding Liu, Chen Chen, Jiannong Cao, Minglei Pan, Jikui Liu, Nan Li, Fen Miao, Ye Li
Abstract: Large language models (LLMs) have captured significant interest from both academia and industry due to their impressive performance across various textual tasks. However, the potential of LLMs to analyze physiological time-series data remains an emerging research field. Particularly, there is a notable gap in the utilization of LLMs for analyzing wearable biosignals to achieve cuffless blood pressure (BP) measurement, which is critical for the management of cardiovascular diseases. This paper presents the first work to explore the capacity of LLMs to perform cuffless BP estimation based on wearable biosignals. We extracted physiological features from electrocardiogram (ECG) and photoplethysmogram (PPG) signals and designed context-enhanced prompts by combining these features with BP domain knowledge and user information. Subsequently, we adapted LLMs to BP estimation tasks through fine-tuning. To evaluate the proposed approach, we conducted assessments of ten advanced LLMs using a comprehensive public dataset of wearable biosignals from 1,272 participants. The experimental results demonstrate that the optimally fine-tuned LLM significantly surpasses conventional task-specific baselines, achieving an estimation error of 0.00 $\pm$ 9.25 mmHg for systolic BP and 1.29 $\pm$ 6.37 mmHg for diastolic BP. Notably, the ablation studies highlight the benefits of our context enhancement strategy, leading to an 8.9% reduction in mean absolute error for systolic BP estimation. This paper pioneers the exploration of LLMs for cuffless BP measurement, providing a potential solution to enhance the accuracy of cuffless BP measurement.