Authors: Emma Croxford, Yanjun Gao, Nicholas Pellegrino, Karen K. Wong, Graham Wills, Elliot First, Frank J. Liao, Cherodeep Goswami, Brian Patterson, Majid Afshar
Abstract: Large Language Models have advanced clinical Natural Language Generation, creating opportunities to manage the volume of medical text. However, the high-stakes nature of medicine requires reliable evaluation, which remains a challenge. In this narrative review, we assess the current evaluation state for clinical summarization tasks and propose future directions to address the resource constraints of expert human evaluation.
Authors: Daniil Gurgurov, Rishu Kumar, Simon Ostermann
Abstract: Contextualized embeddings based on large language models (LLMs) are available for various languages, but their coverage is often limited for lower resourced languages. Training LLMs for such languages is often difficult due to insufficient data and high computational cost. Especially for very low resource languages, static word embeddings thus still offer a viable alternative. There is, however, a notable lack of comprehensive repositories with such embeddings for diverse languages. To address this, we present LowREm, a centralized repository of static embeddings for 87 low-resource languages. We also propose a novel method to enhance GloVe-based embeddings by integrating multilingual graph knowledge, utilizing another source of knowledge. We demonstrate the superior performance of our enhanced embeddings as compared to contextualized embeddings extracted from XLM-R on sentiment analysis. Our code and data are publicly available under https://huggingface.co/DFKI.
Authors: Yihong Liu, Haotian Ye, Chunlan Ma, Mingyang Wang, Hinrich Sch\"utze
Abstract: Recent multilingual pretrained language models (mPLMs) often avoid using language embeddings -- learnable vectors assigned to different languages. These embeddings are discarded for two main reasons: (1) mPLMs are expected to have a single, unified parameter set across all languages, and (2) they need to function seamlessly as universal text encoders without requiring language IDs as input. However, this removal increases the burden on token embeddings to encode all language-specific information, which may hinder the model's ability to produce more language-neutral representations. To address this challenge, we propose Language-Script Aware Multilingual Pretraining (LangSAMP), a method that incorporates both language and script embeddings to enhance representation learning while maintaining a simple architecture. Specifically, we integrate these embeddings into the output of the transformer blocks before passing the final representations to the language modeling head for prediction. We apply LangSAMP to the continual pretraining of XLM-R on a highly multilingual corpus covering more than 500 languages. The resulting model consistently outperforms the baseline. Extensive analysis further shows that language/script embeddings encode language/script-specific information, which improves the selection of source languages for crosslingual transfer. We make our code and models publicly available at \url{https://github.com/cisnlp/LangSAMP}.
Authors: Devrim Cavusoglu, Secil Sen, Ulas Sert
Abstract: Recent advancements in Natural Language Processing (NLP) have impacted numerous sub-fields such as natural language generation, natural language inference, question answering, and more. However, in the field of question generation, the creation of distractors for multiple-choice questions (MCQ) remains a challenging task. In this work, we present a simple, generic framework for distractor generation using readily available Pre-trained Language Models (PLMs). Unlike previous methods, our framework relies solely on pre-trained language models and does not require additional training on specific datasets. Building upon previous research, we introduce a two-stage framework consisting of candidate generation and candidate selection. Our proposed distractor generation framework outperforms previous methods without the need for training or fine-tuning. Human evaluations confirm that our approach produces more effective and engaging distractors. The related codebase is publicly available at https://github.com/obss/disgem.
Authors: Xin Hong, Yuan Gong, Vidhyasaharan Sethu, Ting Dang
Abstract: Recent advancements in Large Language Models (LLMs) have demonstrated great success in many Natural Language Processing (NLP) tasks. In addition to their cognitive intelligence, exploring their capabilities in emotional intelligence is also crucial, as it enables more natural and empathetic conversational AI. Recent studies have shown LLMs' capability in recognizing emotions, but they often focus on single emotion labels and overlook the complex and ambiguous nature of human emotions. This study is the first to address this gap by exploring the potential of LLMs in recognizing ambiguous emotions, leveraging their strong generalization capabilities and in-context learning. We design zero-shot and few-shot prompting and incorporate past dialogue as context information for ambiguous emotion recognition. Experiments conducted using three datasets indicate significant potential for LLMs in recognizing ambiguous emotions, and highlight the substantial benefits of including context information. Furthermore, our findings indicate that LLMs demonstrate a high degree of effectiveness in recognizing less ambiguous emotions and exhibit potential for identifying more ambiguous emotions, paralleling human perceptual capabilities.
Authors: Ghang Lee, Suhyung Jang, Seokho Hyun
Abstract: Performing building information modeling (BIM) tasks is a complex process that imposes a steep learning curve and a heavy cognitive load due to the necessity of remembering sequences of numerous commands. With the rapid advancement of large language models (LLMs), it is foreseeable that BIM tasks, including querying and managing BIM data, 4D and 5D BIM, design compliance checking, or authoring a design, using written or spoken natural language (i.e., text-to-BIM or speech-to-BIM), will soon supplant traditional graphical user interfaces. This paper proposes a generalized LLM-augmented BIM framework to expedite the development of LLM-enhanced BIM applications by providing a step-by-step development process. The proposed framework consists of six steps: interpret-fill-match-structure-execute-check. The paper demonstrates the applicability of the proposed framework through implementing a speech-to-BIM application, NADIA-S (Natural-language-based Architectural Detailing through Interaction with Artificial Intelligence via Speech), using exterior wall detailing as an example.
Authors: Jiawen Wang, Longfei Zuo, Siyao Peng, Barbara Plank
Abstract: Climate change (CC) has attracted increasing attention in NLP in recent years. However, detecting the stance on CC in multimodal data is understudied and remains challenging due to a lack of reliable datasets. To improve the understanding of public opinions and communication strategies, this paper presents MultiClimate, the first open-source manually-annotated stance detection dataset with $100$ CC-related YouTube videos and $4,209$ frame-transcript pairs. We deploy state-of-the-art vision and language models, as well as multimodal models for MultiClimate stance detection. Results show that text-only BERT significantly outperforms image-only ResNet50 and ViT. Combining both modalities achieves state-of-the-art, $0.747$/$0.749$ in accuracy/F1. Our 100M-sized fusion models also beat CLIP and BLIP, as well as the much larger 9B-sized multimodal IDEFICS and text-only Llama3 and Gemma2, indicating that multimodal stance detection remains challenging for large language models. Our code, dataset, as well as supplementary materials, are available at https://github.com/werywjw/MultiClimate.
Authors: Liangtai Sun, Danyu Luo, Da Ma, Zihan Zhao, Baocai Chen, Zhennan Shen, Su Zhu, Lu Chen, Xin Chen, Kai Yu
Abstract: Recently, there has been a significant upsurge of interest in leveraging large language models (LLMs) to assist scientific discovery. However, most LLMs only focus on general science, while they lack domain-specific knowledge, such as chemical molecules and amino acid sequences. To bridge these gaps, we introduce SciDFM, a mixture-of-experts LLM, which is trained from scratch and is able to conduct college-level scientific reasoning and understand molecules and amino acid sequences. We collect a large-scale training corpus containing numerous scientific papers and books from different disciplines as well as data from domain-specific databases. We further fine-tune the pre-trained model on lots of instruction data to improve performances on downstream benchmarks. From experiment results, we show that SciDFM achieves strong performance on general scientific benchmarks such as SciEval and SciQ, and it reaches a SOTA performance on domain-specific benchmarks among models of similar size. We further analyze the expert layers and show that the results of expert selection vary with data from different disciplines. To benefit the broader research community, we open-source SciDFM at https://huggingface.co/OpenDFM/SciDFM-MoE-A5.6B-v1.0.
Authors: Brian Yan, Vineel Pratap, Shinji Watanabe, Michael Auli
Abstract: Multilingual Automatic Speech Recognition (ASR) models are typically evaluated in a setting where the ground-truth language of the speech utterance is known, however, this is often not the case for most practical settings. Automatic Spoken Language Identification (SLID) models are not perfect and misclassifications have a substantial impact on the final ASR accuracy. In this paper, we present a simple and effective N-best re-ranking approach to improve multilingual ASR accuracy for several prominent acoustic models by employing external features such as language models and text-based language identification models. Our results on FLEURS using the MMS and Whisper models show spoken language identification accuracy improvements of 8.7% and 6.1%, respectively and word error rates which are 3.3% and 2.0% lower on these benchmarks.
Authors: Saptarshi Sengupta, Wenpeng Yin, Preslav Nakov, Shreya Ghosh, Suhang Wang
Abstract: In this paper, we investigate Extractive Question Answering (EQA) with Large Language Models (LLMs) under domain drift, i.e., can LLMs generalize well to closed-domains that require specific knowledge such as medicine and law in a zero-shot fashion without additional in-domain training? To this end, we devise a series of experiments to empirically explain the performance gap. Our findings suggest that: a) LLMs struggle with dataset demands of closed-domains such as retrieving long answer-spans; b) Certain LLMs, despite showing strong overall performance, display weaknesses in meeting basic requirements as discriminating between domain-specific senses of words which we link to pre-processing decisions; c) Scaling model parameters is not always effective for cross-domain generalization; and d) Closed-domain datasets are quantitatively much different than open-domain EQA datasets and current LLMs struggle to deal with them. Our findings point out important directions for improving existing LLMs.
Authors: Aditi Godbole, Jabin Geevarghese George, Smita Shandilya
Abstract: The rapid increase in unstructured data across various fields has made multi-document comprehension and summarization a critical task. Traditional approaches often fail to capture relevant context, maintain logical consistency, and extract essential information from lengthy documents. This paper explores the use of Long-context Large Language Models (LLMs) for multi-document summarization, demonstrating their exceptional capacity to grasp extensive connections, provide cohesive summaries, and adapt to various industry domains and integration with enterprise applications/systems. The paper discusses the workflow of multi-document summarization for effectively deploying long-context LLMs, supported by case studies in legal applications, enterprise functions such as HR, finance, and sourcing, as well as in the medical and news domains. These case studies show notable enhancements in both efficiency and accuracy. Technical obstacles, such as dataset diversity, model scalability, and ethical considerations like bias mitigation and factual accuracy, are carefully analyzed. Prospective research avenues are suggested to augment the functionalities and applications of long-context LLMs, establishing them as pivotal tools for transforming information processing across diverse sectors and enterprise applications.
Authors: Aditya Khan, Mason Shipton, David Anugraha, Kaiyao Duan, Phuong H. Hoang, Eric Khiu, A. Seza Do\u{g}ru\"oz, En-Shiun Annie Lee
Abstract: URIEL is a knowledge base offering geographical, phylogenetic, and typological vector representations for 7970 languages. It includes distance measures between these vectors for 4005 languages, which are accessible via the lang2vec tool. Despite being frequently cited, URIEL is limited in terms of linguistic inclusion and overall usability. To tackle these challenges, we introduce URIEL+, an enhanced version of URIEL and lang2vec addressing these limitations. In addition to expanding typological feature coverage for 2898 languages, URIEL+ improves user experience with robust, customizable distance calculations to better suit the needs of the users. These upgrades also offer competitive performance on downstream tasks and provide distances that better align with linguistic distance studies.
Authors: Tianyang Zhong, Zhengliang Liu, Yi Pan, Yutong Zhang, Yifan Zhou, Shizhe Liang, Zihao Wu, Yanjun Lyu, Peng Shu, Xiaowei Yu, Chao Cao, Hanqi Jiang, Hanxu Chen, Yiwei Li, Junhao Chen, Huawen Hu, Yihen Liu, Huaqin Zhao, Shaochen Xu, Haixing Dai, Lin Zhao, Ruidong Zhang, Wei Zhao, Zhenyuan Yang, Jingyuan Chen, Peilong Wang, Wei Ruan, Hui Wang, Huan Zhao, Jing Zhang, Yiming Ren, Shihuan Qin, Tong Chen, Jiaxi Li, Arif Hassan Zidan, Afrar Jahin, Minheng Chen, Sichen Xia, Jason Holmes, Yan Zhuang, Jiaqi Wang, Bochen Xu, Weiran Xia, Jichao Yu, Kaibo Tang, Yaxuan Yang, Bolun Sun, Tao Yang, Guoyu Lu, Xianqiao Wang, Lilong Chai, He Li, Jin Lu, Lichao Sun, Xin Zhang, Bao Ge, Xintao Hu, Lian Zhang, Hua Zhou, Lu Zhang, Shu Zhang, Ninghao Liu, Bei Jiang, Linglong Kong, Zhen Xiang, Yudan Ren, Jun Liu, Xi Jiang, Yu Bao, Wei Zhang, Xiang Li, Gang Li, Wei Liu, Dinggang Shen, Andrea Sikora, Xiaoming Zhai, Dajiang Zhu, Tianming Liu
Abstract: This comprehensive study evaluates the performance of OpenAI's o1-preview large language model across a diverse array of complex reasoning tasks, spanning multiple domains, including computer science, mathematics, natural sciences, medicine, linguistics, and social sciences. Through rigorous testing, o1-preview demonstrated remarkable capabilities, often achieving human-level or superior performance in areas ranging from coding challenges to scientific reasoning and from language processing to creative problem-solving. Key findings include: -83.3% success rate in solving complex competitive programming problems, surpassing many human experts. -Superior ability in generating coherent and accurate radiology reports, outperforming other evaluated models. -100% accuracy in high school-level mathematical reasoning tasks, providing detailed step-by-step solutions. -Advanced natural language inference capabilities across general and specialized domains like medicine. -Impressive performance in chip design tasks, outperforming specialized models in areas such as EDA script generation and bug analysis. -Remarkable proficiency in anthropology and geology, demonstrating deep understanding and reasoning in these specialized fields. -Strong capabilities in quantitative investing. O1 has comprehensive financial knowledge and statistical modeling skills. -Effective performance in social media analysis, including sentiment analysis and emotion recognition. The model excelled particularly in tasks requiring intricate reasoning and knowledge integration across various fields. While some limitations were observed, including occasional errors on simpler problems and challenges with certain highly specialized concepts, the overall results indicate significant progress towards artificial general intelligence.
Authors: Yixuan Tang, Yi Yang
Abstract: Embedding models play a crucial role in representing and retrieving information across various NLP applications. Recent advancements in Large Language Models (LLMs) have further enhanced the performance of embedding models, which are trained on massive amounts of text covering almost every domain. These models are often benchmarked on general-purpose datasets like Massive Text Embedding Benchmark (MTEB), where they demonstrate superior performance. However, a critical question arises: Is the development of domain-specific embedding models necessary when general-purpose models are trained on vast corpora that already include specialized domain texts? In this paper, we empirically investigate this question, choosing the finance domain as an example. We introduce the Finance Massive Text Embedding Benchmark (FinMTEB), a counterpart to MTEB that consists of financial domain-specific text datasets. We evaluate the performance of seven state-of-the-art embedding models on FinMTEB and observe a significant performance drop compared to their performance on MTEB. To account for the possibility that this drop is driven by FinMTEB's higher complexity, we propose four measures to quantify dataset complexity and control for this factor in our analysis. Our analysis provides compelling evidence that state-of-the-art embedding models struggle to capture domain-specific linguistic and semantic patterns, even when trained on large general-purpose corpora. This study sheds light on the necessity of developing domain-specific embedding models in the LLM era, offering valuable insights for researchers and practitioners.
Authors: Mareike Hartmann, Alexander Koller
Abstract: Goal-directed interactive agents, which autonomously complete tasks through interactions with their environment, can assist humans in various domains of their daily lives. Recent advances in large language models (LLMs) led to a surge of new, more and more challenging tasks to evaluate such agents. To properly contextualize performance across these tasks, it is imperative to understand the different challenges they pose to agents. To this end, this survey compiles relevant tasks and environments for evaluating goal-directed interactive agents, structuring them along dimensions relevant for understanding current obstacles. An up-to-date compilation of relevant resources can be found on our project website: https://coli-saar.github.io/interactive-agents.
Authors: Yi Ren, Tianyi Zhang, Weibin Li, DuoMu Zhou, Chenhao Qin, FangCheng Dong
Abstract: In recent years, with the rapid development of large language models, serval models such as GPT-4o have demonstrated extraordinary capabilities, surpassing human performance in various language tasks. As a result, many researchers have begun exploring their potential applications in the field of public opinion analysis. This study proposes a novel large-language-models-based method for public opinion event heat level prediction. First, we preprocessed and classified 62,836 Chinese hot event data collected between July 2022 and December 2023. Then, based on each event's online dissemination heat index, we used the MiniBatchKMeans algorithm to automatically cluster the events and categorize them into four heat levels (ranging from low heat to very high heat). Next, we randomly selected 250 events from each heat level, totalling 1,000 events, to build the evaluation dataset. During the evaluation process, we employed various large language models to assess their accuracy in predicting event heat levels in two scenarios: without reference cases and with similar case references. The results showed that GPT-4o and DeepseekV2 performed the best in the latter case, achieving prediction accuracies of 41.4% and 41.5%, respectively. Although the overall prediction accuracy remains relatively low, it is worth noting that for low-heat (Level 1) events, the prediction accuracies of these two models reached 73.6% and 70.4%, respectively. Additionally, the prediction accuracy showed a downward trend from Level 1 to Level 4, which correlates with the uneven distribution of data across the heat levels in the actual dataset. This suggests that with the more robust dataset, public opinion event heat level prediction based on large language models will have significant research potential for the future.
Authors: Yangyifan Xu, Jianghao Chen, Junhong Wu, Jiajun Zhang
Abstract: Ensembling various LLMs to unlock their complementary potential and leverage their individual strengths is highly valuable. Previous studies typically focus on two main paradigms: sample-level and token-level ensembles. Sample-level ensemble methods either select or blend fully generated outputs, which hinders dynamic correction and enhancement of outputs during the generation process. On the other hand, token-level ensemble methods enable real-time correction through fine-grained ensemble at each generation step. However, the information carried by an individual token is quite limited, leading to suboptimal decisions at each step. To address these issues, we propose SweetSpan, a span-level ensemble method that effectively balances the need for real-time adjustments and the information required for accurate ensemble decisions. Our approach involves two key steps: First, we have each candidate model independently generate candidate spans based on the shared prefix. Second, we calculate perplexity scores to facilitate mutual evaluation among the candidate models and achieve robust span selection by filtering out unfaithful scores. To comprehensively evaluate ensemble methods, we propose a new challenging setting (ensemble models with significant performance gaps) in addition to the standard setting (ensemble the best-performing models) to assess the performance of model ensembles in more realistic scenarios. Experimental results in both standard and challenging settings across various language generation tasks demonstrate the effectiveness, robustness, and versatility of our approach compared with previous ensemble methods.
Authors: Nicol\`o Penzo, Maryam Sajedinia, Bruno Lepri, Sara Tonelli, Marco Guerini
Abstract: Assessing the performance of systems to classify Multi-Party Conversations (MPC) is challenging due to the interconnection between linguistic and structural characteristics of conversations. Conventional evaluation methods often overlook variances in model behavior across different levels of structural complexity on interaction graphs. In this work, we propose a methodological pipeline to investigate model performance across specific structural attributes of conversations. As a proof of concept we focus on Response Selection and Addressee Recognition tasks, to diagnose model weaknesses. To this end, we extract representative diagnostic subdatasets with a fixed number of users and a good structural variety from a large and open corpus of online MPCs. We further frame our work in terms of data minimization, avoiding the use of original usernames to preserve privacy, and propose alternatives to using original text messages. Results show that response selection relies more on the textual content of conversations, while addressee recognition requires capturing their structural dimension. Using an LLM in a zero-shot setting, we further highlight how sensitivity to prompt variations is task-dependent.
Authors: Jaepill Choi, Kyubyung Chae, Jiwoo Song, Yohan Jo, Taesup Kim
Abstract: In abstractive summarization, the challenge of producing concise and accurate summaries arises from the vast amount of information contained in the source document. Consequently, although Large Language Models (LLMs) can generate fluent text, they often introduce inaccuracies by hallucinating content not found in the original source. While supervised fine-tuning methods that maximize likelihood contribute to this issue, they do not consistently enhance the faithfulness of the summaries. Preference-based optimization methods, such as Direct Preference Optimization (DPO), can further refine the model to align with human preferences. However, these methods still heavily depend on costly human feedback. In this work, we introduce a novel and straightforward approach called Model-based Preference Optimization (MPO) to fine-tune LLMs for improved summarization abilities without any human feedback. By leveraging the model's inherent summarization capabilities, we create a preference dataset that is fully generated by the model using different decoding strategies. Our experiments on standard summarization datasets and various metrics demonstrate that our proposed MPO significantly enhances the quality of generated summaries without relying on human feedback.
Authors: T. Y. S. S. Santosh, Mohamed Hesham Elganayni, Stanis{\l}aw S\'ojka, Matthias Grabmair
Abstract: Inspired by the legal doctrine of stare decisis, which leverages precedents (prior cases) for informed decision-making, we explore methods to integrate them into LJP models. To facilitate precedent retrieval, we train a retriever with a fine-grained relevance signal based on the overlap ratio of alleged articles between cases. We investigate two strategies to integrate precedents: direct incorporation at inference via label interpolation based on case proximity and during training via a precedent fusion module using a stacked-cross attention model. We employ joint training of the retriever and LJP models to address latent space divergence between them. Our experiments on LJP tasks from the ECHR jurisdiction reveal that integrating precedents during training coupled with joint training of the retriever and LJP model, outperforms models without precedents or with precedents incorporated only at inference, particularly benefiting sparser articles.
Authors: T. Y. S. S. Santosh, Irtiza Chowdhury, Shanshan Xu, Matthias Grabmair
Abstract: In high-stakes decision-making tasks within legal NLP, such as Case Outcome Classification (COC), quantifying a model's predictive confidence is crucial. Confidence estimation enables humans to make more informed decisions, particularly when the model's certainty is low, or where the consequences of a mistake are significant. However, most existing COC works prioritize high task performance over model reliability. This paper conducts an empirical investigation into how various design choices including pre-training corpus, confidence estimator and fine-tuning loss affect the reliability of COC models within the framework of selective prediction. Our experiments on the multi-label COC task, focusing on European Court of Human Rights (ECtHR) cases, highlight the importance of a diverse yet domain-specific pre-training corpus for better calibration. Additionally, we demonstrate that larger models tend to exhibit overconfidence, Monte Carlo dropout methods produce reliable confidence estimates, and confident error regularization effectively mitigates overconfidence. To our knowledge, this is the first systematic exploration of selective prediction in legal NLP. Our findings underscore the need for further research on enhancing confidence measurement and improving the trustworthiness of models in the legal domain.
Authors: T. Y. S. S. Santosh, Apolline Isaia, Shiyu Hong, Matthias Grabmair
Abstract: Rhetorical Role Labeling (RRL) of legal documents is pivotal for various downstream tasks such as summarization, semantic case search and argument mining. Existing approaches often overlook the varying difficulty levels inherent in legal document discourse styles and rhetorical roles. In this work, we propose HiCuLR, a hierarchical curriculum learning framework for RRL. It nests two curricula: Rhetorical Role-level Curriculum (RC) on the outer layer and Document-level Curriculum (DC) on the inner layer. DC categorizes documents based on their difficulty, utilizing metrics like deviation from a standard discourse structure and exposes the model to them in an easy-to-difficult fashion. RC progressively strengthens the model to discern coarse-to-fine-grained distinctions between rhetorical roles. Our experiments on four RRL datasets demonstrate the efficacy of HiCuLR, highlighting the complementary nature of DC and RC.
Authors: Yining Juan, Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen
Abstract: In diverse professional environments, ranging from academic conferences to corporate earnings calls, the ability to anticipate audience questions stands paramount. Traditional methods, which rely on manual assessment of an audience's background, interests, and subject knowledge, often fall short - particularly when facing large or heterogeneous groups, leading to imprecision and inefficiency. While NLP has made strides in text-based question generation, its primary focus remains on academic settings, leaving the intricate challenges of professional domains, especially earnings call conferences, underserved. Addressing this gap, our paper pioneers the multi-question generation (MQG) task specifically designed for earnings call contexts. Our methodology involves an exhaustive collection of earnings call transcripts and a novel annotation technique to classify potential questions. Furthermore, we introduce a retriever-enhanced strategy to extract relevant information. With a core aim of generating a spectrum of potential questions that analysts might pose, we derive these directly from earnings call content. Empirical evaluations underscore our approach's edge, revealing notable excellence in the accuracy, consistency, and perplexity of the questions generated.
Authors: Yung-Yu Shih, Ziwei Xu, Hiroya Takamura, Yun-Nung Chen, Chung-Chi Chen
Abstract: Question answering (QA) has been a long-standing focus in the NLP field, predominantly addressing reading comprehension and common sense QA. However, scenarios involving the preparation of answers to probable questions during professional oral presentations remain underexplored. In this paper, we pioneer the examination of this crucial yet overlooked topic by utilizing real-world QA conversation transcripts between company managers and professional analysts. We explore the proposed task using three causal knowledge graphs (KGs) and three large language models (LLMs). This work provides foundational insights into the application of LLMs in professional QA scenarios, highlighting the importance of causal KGs and perspective-taking in generating effective responses.
Authors: Tsung-Hsuan Pan, Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen
Abstract: Training large language models (LLMs) from scratch is an expensive endeavor, particularly as world knowledge continually evolves. To maintain relevance and accuracy of LLMs, model editing has emerged as a pivotal research area. While these methods hold promise, they can also produce unintended side effects. Their underlying factors and causes remain largely unexplored. This paper delves into a critical factor-question type-by categorizing model editing questions. Our findings reveal that the extent of performance degradation varies significantly across different question types, providing new insights for experimental design in knowledge editing. Furthermore, we investigate whether insights from smaller models can be extrapolated to larger models. Our results indicate discrepancies in findings between models of different sizes, suggesting that insights from smaller models may not necessarily apply to larger models. Additionally, we examine the impact of batch size on side effects, discovering that increasing the batch size can mitigate performance drops.
Authors: Sergey Berezin, Reza Farahbakhsh, Noel Crespi
Abstract: We introduce a novel family of adversarial attacks that exploit the inability of language models to interpret ASCII art. To evaluate these attacks, we propose the ToxASCII benchmark and develop two custom ASCII art fonts: one leveraging special tokens and another using text-filled letter shapes. Our attacks achieve a perfect 1.0 Attack Success Rate across ten models, including OpenAI's o1-preview and LLaMA 3.1. Warning: this paper contains examples of toxic language used for research purposes.
Authors: Siheng Li, Cheng Yang, Taiqiang Wu, Chufan Shi, Yuji Zhang, Xinyu Zhu, Zesen Cheng, Deng Cai, Mo Yu, Lemao Liu, Jie Zhou, Yujiu Yang, Ngai Wong, Xixin Wu, Wai Lam
Abstract: Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to faithfully express their knowledge. Despite promising, current LLMs still exhibit significant dishonest behaviors, such as confidently presenting wrong answers or failing to express what they know. In addition, research on the honesty of LLMs also faces challenges, including varying definitions of honesty, difficulties in distinguishing between known and unknown knowledge, and a lack of comprehensive understanding of related research. To address these issues, we provide a survey on the honesty of LLMs, covering its clarification, evaluation approaches, and strategies for improvement. Moreover, we offer insights for future research, aiming to inspire further exploration in this important area.
Authors: Hamed Babaei Giglou, Jennifer D'Souza, S\"oren Auer
Abstract: In response to the growing complexity and volume of scientific literature, this paper introduces the LLMs4Synthesis framework, designed to enhance the capabilities of Large Language Models (LLMs) in generating high-quality scientific syntheses. This framework addresses the need for rapid, coherent, and contextually rich integration of scientific insights, leveraging both open-source and proprietary LLMs. It also examines the effectiveness of LLMs in evaluating the integrity and reliability of these syntheses, alleviating inadequacies in current quantitative metrics. Our study contributes to this field by developing a novel methodology for processing scientific papers, defining new synthesis types, and establishing nine detailed quality criteria for evaluating syntheses. The integration of LLMs with reinforcement learning and AI feedback is proposed to optimize synthesis quality, ensuring alignment with established criteria. The LLMs4Synthesis framework and its components are made available, promising to enhance both the generation and evaluation processes in scientific research synthesis.
Authors: Jeremy Kramer, Tetiana Kravchenko, Beatrice Kaufmann, Friederike J. S. Thilo, Mascha Kurpicz-Briki
Abstract: Latest advances in the field of natural language processing (NLP) enable new use cases for different domains, including the medical sector. In particular, transcription can be used to support automation in the nursing documentation process and give nurses more time to interact with the patients. However, different challenges including (a) data privacy, (b) local languages and dialects, and (c) domain-specific vocabulary need to be addressed. In this case study, we investigate the case of home care nursing documentation in Switzerland. We assessed different transcription tools and models, and conducted several experiments with OpenAI Whisper, involving different variations of German (i.e., dialects, foreign accent) and manually curated example texts by a domain expert of home care nursing. Our results indicate that even the used out-of-the-box model performs sufficiently well to be a good starting point for future research in the field.
Authors: Alexey Tikhonov, Lisa Bylinina, Ivan P. Yamshchikov
Abstract: We show differences between a language-and-vision model CLIP and two text-only models - FastText and SBERT - when it comes to the encoding of individuation information. We study latent representations that CLIP provides for substrates, granular aggregates, and various numbers of objects. We demonstrate that CLIP embeddings capture quantitative differences in individuation better than models trained on text-only data. Moreover, the individuation hierarchy we deduce from the CLIP embeddings agrees with the hierarchies proposed in linguistics and cognitive science.
Authors: Zehan Li, Yan Hu, Scott Lane, Salih Selek, Lokesh Shahani, Rodrigo Machado-Vieira, Jair Soares, Hua Xu, Hongfang Liu, Ming Huang
Abstract: Accurate identification and categorization of suicidal events can yield better suicide precautions, reducing operational burden, and improving care quality in high-acuity psychiatric settings. Pre-trained language models offer promise for identifying suicidality from unstructured clinical narratives. We evaluated the performance of four BERT-based models using two fine-tuning strategies (multiple single-label and single multi-label) for detecting coexisting suicidal events from 500 annotated psychiatric evaluation notes. The notes were labeled for suicidal ideation (SI), suicide attempts (SA), exposure to suicide (ES), and non-suicidal self-injury (NSSI). RoBERTa outperformed other models using binary relevance (acc=0.86, F1=0.78). MentalBERT (F1=0.74) also exceeded BioClinicalBERT (F1=0.72). RoBERTa fine-tuned with a single multi-label classifier further improved performance (acc=0.88, F1=0.81), highlighting that models pre-trained on domain-relevant data and the single multi-label classification strategy enhance efficiency and performance. Keywords: EHR-based Phynotyping; Natural Language Processing; Secondary Use of EHR Data; Suicide Classification; BERT-based Model; Psychiatry; Mental Health
Authors: Fan Lin, Shuyi Xie, Yong Dai, Wenlin Yao, Tianjiao Lang, Zishan Xu, Zhichao Hu, Xiao Xiao, Yuhong Liu, Yu Zhang
Abstract: As Large Language Models (LLMs) grow increasingly adept at managing complex tasks, the evaluation set must keep pace with these advancements to ensure it remains sufficiently discriminative. Item Discrimination (ID) theory, which is widely used in educational assessment, measures the ability of individual test items to differentiate between high and low performers. Inspired by this theory, we propose an ID-induced prompt synthesis framework for evaluating LLMs to ensure the evaluation set can continually update and refine according to model abilities. Our data synthesis framework prioritizes both breadth and specificity. It can generate prompts that comprehensively evaluate the capabilities of LLMs while revealing meaningful performance differences between models, allowing for effective discrimination of their relative strengths and weaknesses across various tasks and domains. To produce high-quality data, we incorporate a self-correct mechanism into our generalization framework, and develop two models to predict prompt discrimination and difficulty score to facilitate our data synthesis framework, contributing valuable tools to evaluation data synthesis research. We apply our generated data to evaluate five SOTA models. Our data achieves an average score of 51.92, accompanied by a variance of 10.06. By contrast, previous works (i.e., SELF-INSTRUCT and WizardLM) obtain an average score exceeding 67, with a variance below 3.2. The results demonstrate that the data generated by our framework is more challenging and discriminative compared to previous works. We will release a dataset of over 3,000 carefully crafted prompts to facilitate evaluation research of LLMs.
Authors: Maryam Berijanian, Spencer Dork, Kuldeep Singh, Michael Riley Millikan, Ashlin Riggs, Aadarsh Swaminathan, Sarah L. Gibbs, Scott E. Friedman, Nathan Brugnone
Abstract: Understanding and modeling collective intelligence is essential for addressing complex social systems. Directed graphs called fuzzy cognitive maps (FCMs) offer a powerful tool for encoding causal mental models, but extracting high-integrity FCMs from text is challenging. This study presents an approach using large language models (LLMs) to automate FCM extraction. We introduce novel graph-based similarity measures and evaluate them by correlating their outputs with human judgments through the Elo rating system. Results show positive correlations with human evaluations, but even the best-performing measure exhibits limitations in capturing FCM nuances. Fine-tuning LLMs improves performance, but existing measures still fall short. This study highlights the need for soft similarity measures tailored to FCM extraction, advancing collective intelligence modeling with NLP.
Authors: Huizi Yu, Jiayan Zhou, Lingyao Li, Shan Chen, Jack Gallifant, Anye Shi, Xiang Li, Wenyue Hua, Mingyu Jin, Guang Chen, Yang Zhou, Zhao Li, Trisha Gupte, Ming-Li Chen, Zahra Azizi, Yongfeng Zhang, Themistocles L. Assimes, Xin Ma, Danielle S. Bitterman, Lin Lu, Lizhou Fan
Abstract: Simulated patient systems play a crucial role in modern medical education and research, providing safe, integrative learning environments and enabling clinical decision-making simulations. Large Language Models (LLM) could advance simulated patient systems by replicating medical conditions and patient-doctor interactions with high fidelity and low cost. However, ensuring the effectiveness and trustworthiness of these systems remains a challenge, as they require a large, diverse, and precise patient knowledgebase, along with a robust and stable knowledge diffusion to users. Here, we developed AIPatient, an advanced simulated patient system with AIPatient Knowledge Graph (AIPatient KG) as the input and the Reasoning Retrieval-Augmented Generation (Reasoning RAG) agentic workflow as the generation backbone. AIPatient KG samples data from Electronic Health Records (EHRs) in the Medical Information Mart for Intensive Care (MIMIC)-III database, producing a clinically diverse and relevant cohort of 1,495 patients with high knowledgebase validity (F1 0.89). Reasoning RAG leverages six LLM powered agents spanning tasks including retrieval, KG query generation, abstraction, checker, rewrite, and summarization. This agentic framework reaches an overall accuracy of 94.15% in EHR-based medical Question Answering (QA), outperforming benchmarks that use either no agent or only partial agent integration. Our system also presents high readability (median Flesch Reading Ease 77.23; median Flesch Kincaid Grade 5.6), robustness (ANOVA F-value 0.6126, p<0.1), and stability (ANOVA F-value 0.782, p<0.1). The promising performance of the AIPatient system highlights its potential to support a wide range of applications, including medical education, model evaluation, and system integration.
Authors: Jiaming Li, Lei Zhang, Yunshui Li, Ziqiang Liu, yuelin bai, Run Luo, Longze Chen, Min Yang
Abstract: The instruction-following ability of large language models enables humans to interact with AI agents in a natural way. However, when required to generate responses of a specific length, large language models often struggle to meet users' needs due to their inherent difficulty in accurately perceiving numerical constraints. To explore the ability of large language models to control the length of generated responses, we propose the Target Length Generation Task (TLG) and design two metrics, Precise Match (PM) and Flexible Match (FM) to evaluate the model's performance in adhering to specified response lengths. Furthermore, we introduce a novel, model-agnostic approach called Ruler, which employs Meta Length Tokens (MLTs) to enhance the instruction-following ability of large language models under length-constrained instructions. Specifically, Ruler equips LLMs with the ability to generate responses of a specified length based on length constraints within the instructions. Moreover, Ruler can automatically generate appropriate MLT when length constraints are not explicitly provided, demonstrating excellent versatility and generalization. Comprehensive experiments show the effectiveness of Ruler across different LLMs on Target Length Generation Task, e.g., at All Level 27.97 average gain on PM, 29.57 average gain on FM. In addition, we conduct extensive ablation experiments to further substantiate the efficacy and generalization of Ruler. Our code and data is available at https://github.com/Geaming2002/Ruler.
Authors: Praneeth Vadlapati
Abstract: This paper introduces a new approach to using Large Language Models (LLMs) for classification tasks, which are typically handled using Machine Learning (ML) models. Unlike ML models that rely heavily on data cleaning and feature engineering, this method streamlines the process using LLMs. This paper proposes a new concept called "Language Model Learning (LML)" powered by a new method called "Data-Augmented Prediction (DAP)". The classification is performed by LLMs using a method similar to humans manually exploring and understanding the data and deciding classifications using data as a reference. Training data is summarized and evaluated to determine the features that lead to the classification of each label the most. In the process of DAP, the system uses the data summary to automatically create a query, which is used to retrieve relevant rows from the dataset. A classification is generated by the LLM using data summary and relevant rows, ensuring satisfactory accuracy even with complex data. Usage of data summary and similar data in DAP ensures context-aware decision-making. The proposed method uses the words "Act as an Explainable Machine Learning Model" in the prompt to enhance the interpretability of the predictions by allowing users to review the logic behind each prediction. In some test cases, the system scored an accuracy above 90%, proving the effectiveness of the system and its potential to outperform conventional ML models in various scenarios. The code is available at https://github.com/Pro-GenAI/LML-DAP
Authors: David Wood, Boris Lublinsky, Alexy Roytman, Shivdeep Singh, Abdulhamid Adebayo, Revital Eres, Mohammad Nassar, Hima Patel, Yousaf Shah, Constantin Adam, Petros Zerfos, Nirmit Desai, Daiki Tsuzuku, Takuya Goto, Michele Dolfi, Saptha Surendran, Paramesvaran Selvam, Sungeun An, Yuan Chi Chang, Dhiraj Joshi, Hajar Emami-Gohari, Xuan-Hong Dang, Yan Koyfman, Shahrokh Daijavad
Abstract: Data preparation is the first and a very important step towards any Large Language Model (LLM) development. This paper introduces an easy-to-use, extensible, and scale-flexible open-source data preparation toolkit called Data Prep Kit (DPK). DPK is architected and designed to enable users to scale their data preparation to their needs. With DPK they can prepare data on a local machine or effortlessly scale to run on a cluster with thousands of CPU Cores. DPK comes with a highly scalable, yet extensible set of modules that transform natural language and code data. If the user needs additional transforms, they can be easily developed using extensive DPK support for transform creation. These modules can be used independently or pipelined to perform a series of operations. In this paper, we describe DPK architecture and show its performance from a small scale to a very large number of CPUs. The modules from DPK have been used for the preparation of Granite Models [1] [2]. We believe DPK is a valuable contribution to the AI community to easily prepare data to enhance the performance of their LLM models or to fine-tune models with Retrieval-Augmented Generation (RAG).
Authors: Michelle S. Lam, Fred Hohman, Dominik Moritz, Jeffrey P. Bigham, Kenneth Holstein, Mary Beth Kery
Abstract: Whether a large language model policy is an explicit constitution or an implicit reward model, it is challenging to assess coverage over the unbounded set of real-world situations that a policy must contend with. We introduce an AI policy design process inspired by mapmaking, which has developed tactics for visualizing and iterating on maps even when full coverage is not possible. With Policy Projector, policy designers can survey the landscape of model input-output pairs, define custom regions (e.g., "violence"), and navigate these regions with rules that can be applied to LLM outputs (e.g., if output contains "violence" and "graphic details," then rewrite without "graphic details"). Policy Projector supports interactive policy authoring using LLM classification and steering and a map visualization reflecting the policy designer's work. In an evaluation with 12 AI safety experts, our system helps policy designers to address problematic model behaviors extending beyond an existing, comprehensive harm taxonomy.
Authors: Elliot L. Epstein, Kaisheng Yao, Jing Li, Xinyi Bai, Hamid Palangi
Abstract: Evaluating instruction following capabilities for multimodal, multi-turn dialogue is challenging. With potentially multiple instructions in the input model context, the task is time-consuming for human raters and we show LLM based judges are biased towards answers from the same model. We propose MMMT-IF, an image based multi-turn Q$\&$A evaluation set with added global instructions between questions, constraining the answer format. This challenges models to retrieve instructions dispersed across long dialogues and reason under instruction constraints. All instructions are objectively verifiable through code execution. We introduce the Programmatic Instruction Following ($\operatorname{PIF}$) metric to measure the fraction of the instructions that are correctly followed while performing a reasoning task. The $\operatorname{PIF-N-K}$ set of metrics further evaluates robustness by measuring the fraction of samples in a corpus where, for each sample, at least K out of N generated model responses achieve a $\operatorname{PIF}$ score of one. The $\operatorname{PIF}$ metric aligns with human instruction following ratings, showing 60 percent correlation. Experiments show Gemini 1.5 Pro, GPT-4o, and Claude 3.5 Sonnet, have a $\operatorname{PIF}$ metric that drops from 0.81 on average at turn 1 across the models, to 0.64 at turn 20. Across all turns, when each response is repeated 4 times ($\operatorname{PIF-4-4}$), GPT-4o and Gemini successfully follow all instructions only $11\%$ of the time. When all the instructions are also appended to the end of the model input context, the $\operatorname{PIF}$ metric improves by 22.3 points on average, showing that the challenge with the task lies not only in following the instructions, but also in retrieving the instructions spread out in the model context. We plan to open source the MMMT-IF dataset and metric computation code.
Authors: Huthaifa I. Ashqar, Ahmed Jaber, Taqwa I. Alhadidi, Mohammed Elhenawy
Abstract: This study aims to comprehensively review and empirically evaluate the application of multimodal large language models (MLLMs) and Large Vision Models (VLMs) in object detection for transportation systems. In the first fold, we provide a background about the potential benefits of MLLMs in transportation applications and conduct a comprehensive review of current MLLM technologies in previous studies. We highlight their effectiveness and limitations in object detection within various transportation scenarios. The second fold involves providing an overview of the taxonomy of end-to-end object detection in transportation applications and future directions. Building on this, we proposed empirical analysis for testing MLLMs on three real-world transportation problems that include object detection tasks namely, road safety attributes extraction, safety-critical event detection, and visual reasoning of thermal images. Our findings provide a detailed assessment of MLLM performance, uncovering both strengths and areas for improvement. Finally, we discuss practical limitations and challenges of MLLMs in enhancing object detection in transportation, thereby offering a roadmap for future research and development in this critical area.
Authors: Derek Tam, Yash Kant, Brian Lester, Igor Gilitschenski, Colin Raffel
Abstract: Merging has become a widespread way to cheaply combine individual models into a single model that inherits their capabilities and attains better performance. This popularity has spurred rapid development of many new merging methods, which are typically validated in disparate experimental settings and frequently differ in the assumptions made about model architecture, data availability, and computational budget. In this work, we characterize the relative merits of different merging methods by evaluating them in a shared experimental setting and precisely identifying the practical requirements of each method. Specifically, our setting focuses on using merging for compositional generalization of capabilities in image classification, image generation, and natural language processing. Additionally, we measure the computational costs of different merging methods as well as how they perform when scaling the number of models being merged. Taken together, our results clarify the state of the field of model merging and provide a comprehensive and rigorous experimental setup to test new methods.
Authors: Chuang Niu, Parisa Kaviani, Qing Lyu, Mannudeep K. Kalra, Christopher T. Whitlow, Ge Wang
Abstract: Structured radiology reporting is advantageous for optimizing clinical workflows and patient outcomes. Current LLMs in creating structured reports face the challenges of formatting errors, content hallucinations, and privacy leakage concerns when uploaded to external servers. We aim to develop an enhanced open-source LLM for creating structured and standardized LCS reports from free-text descriptions. After institutional IRB approvals, 5,442 de-identified LCS reports from two institutions were retrospectively analyzed. 500 reports were randomly selected from the two institutions evenly and then manually labeled for evaluation. Two radiologists from the two institutions developed a standardized template including 29 features for lung nodule reporting. We proposed template-constrained decoding to enhance state-of-the-art open-source LLMs, including LLAMA, Qwen, and Mistral. The LLM performance was extensively evaluated in terms of F1 score, confidence interval, McNemar test, and z-test. Based on the structured reports created from the large-scale dataset, a nodule-level retrieval system was prototyped and an automatic statistical analysis was performed. Our software, vLLM-structure, is publicly available for local deployment with enhanced LLMs. Our template-constrained decoding approach consistently enhanced the LLM performance on multi-institutional datasets, with neither formatting errors nor content hallucinations. Our method improved the best open-source LLAMA-3.1 405B by up to 10.42%, and outperformed GPT-4o by 17.19%. A novel nodule retrieval system was successfully prototyped and demonstrated on a large-scale multimodal database using our enhanced LLM technologies. The automatically derived statistical distributions were closely consistent with the prior findings in terms of nodule type, location, size, status, and Lung-RADS.
Authors: Ryan Shea, Zhou Yu
Abstract: Despite recent advancements in AI and NLP, negotiation remains a difficult domain for AI agents. Traditional game theoretic approaches that have worked well for two-player zero-sum games struggle in the context of negotiation due to their inability to learn human-compatible strategies. On the other hand, approaches that only use human data tend to be domain-specific and lack the theoretical guarantees provided by strategies grounded in game theory. Motivated by the notion of fairness as a criterion for optimality in general sum games, we propose a negotiation framework called FDHC which incorporates fairness into both the reward design and search to learn human-compatible negotiation strategies. Our method includes a novel, RL+search technique called LGM-Zero which leverages a pre-trained language model to retrieve human-compatible offers from large action spaces. Our results show that our method is able to achieve more egalitarian negotiation outcomes and improve negotiation quality.
Authors: Hung Viet Pham, Tung Thanh Nguyen
Abstract: Traditional defect prediction approaches often use metrics that measure the complexity of the design or implementing code of a software system, such as the number of lines of code in a source file. In this paper, we explore a different approach based on content of source code. Our key assumption is that source code of a software system contains information about its technical aspects and those aspects might have different levels of defect-proneness. Thus, content-based features such as words, topics, data types, and package names extracted from a source code file could be used to predict its defects. We have performed an extensive empirical evaluation and found that: i) such content-based features have higher predictive power than code complexity metrics and ii) the use of feature selection, reduction, and combination further improves the prediction performance.
Authors: Guoxi Zhang, Jiuding Duan
Abstract: This paper addresses the cost-efficiency aspect of Reinforcement Learning from Human Feedback (RLHF). RLHF leverages datasets of human preferences over outputs of large language models (LLM) to instill human expectations into LLMs. While preference annotation comes with a monetized cost, the economic utility of a preference dataset has not been considered by far. What exacerbates this situation is that given complex intransitive or cyclic relationships in preference datasets, existing algorithms for fine-tuning LLMs are still far from capturing comprehensive preferences. This raises severe cost-efficiency concerns in production environments, where preference data accumulate over time. In this paper, we see the fine-tuning of LLMs as a monetized economy and introduce an auction mechanism to improve the efficiency of the preference data collection in dollar terms. We show that introducing an auction mechanism can play an essential role in enhancing the cost-efficiency of RLHF while maintaining satisfactory model performance. Experimental results demonstrate that our proposed auction-based protocol is cost-efficient for fine-tuning LLMs by concentrating on high-quality feedback.
Authors: Mucong Ding, Chenghao Deng, Jocelyn Choo, Zichu Wu, Aakriti Agrawal, Avi Schwarzschild, Tianyi Zhou, Tom Goldstein, John Langford, Anima Anandkumar, Furong Huang
Abstract: While generalization over tasks from easy to hard is crucial to profile language models (LLMs), the datasets with fine-grained difficulty annotations for each problem across a broad range of complexity are still blank. Aiming to address this limitation, we present Easy2Hard-Bench, a consistently formatted collection of 6 benchmark datasets spanning various domains, such as mathematics and programming problems, chess puzzles, and reasoning questions. Each problem within these datasets is annotated with numerical difficulty scores. To systematically estimate problem difficulties, we collect abundant performance data on attempts to each problem by humans in the real world or LLMs on the prominent leaderboard. Leveraging the rich performance data, we apply well-established difficulty ranking systems, such as Item Response Theory (IRT) and Glicko-2 models, to uniformly assign numerical difficulty scores to problems. Moreover, datasets in Easy2Hard-Bench distinguish themselves from previous collections by a higher proportion of challenging problems. Through extensive experiments with six state-of-the-art LLMs, we provide a comprehensive analysis of their performance and generalization capabilities across varying levels of difficulty, with the aim of inspiring future research in LLM generalization. The datasets are available at https://huggingface.co/datasets/furonghuang-lab/Easy2Hard-Bench.
URLs: https://huggingface.co/datasets/furonghuang-lab/Easy2Hard-Bench.
Authors: Haoyu Wang, Chunyu Qiang, Tianrui Wang, Cheng Gong, Qiuyu Liu, Yu Jiang, Xiaobao Wang, Chenyang Wang, Chen Zhang
Abstract: Recent advancements in speech synthesis models, trained on extensive datasets, have demonstrated remarkable zero-shot capabilities. These models can control content, timbre, and emotion in generated speech based on prompt inputs. Despite these advancements, the choice of prompts significantly impacts the output quality, yet most existing selection schemes do not adequately address the control of emotional intensity. To address this question, this paper proposes a two-stage prompt selection strategy EmoPro, which is specifically designed for emotionally controllable speech synthesis. This strategy focuses on selecting highly expressive and high-quality prompts by evaluating them from four perspectives: emotional expression strength, speech quality, text-emotion consistency, and model generation performance. Experimental results show that prompts selected using the proposed method result in more emotionally expressive and engaging synthesized speech compared to those obtained through baseline. Audio samples and codes will be available at https://whyrrrrun.github.io/EmoPro/.
Authors: Ricardo Knauer, Mario Koddenbrock, Raphael Wallsberger, Nicholas M. Brisson, Georg N. Duda, Deborah Falla, David W. Evans, Erik Rodner
Abstract: Large language models (LLMs) provide powerful means to leverage prior knowledge for predictive modeling when data is limited. In this work, we demonstrate how LLMs can use their compressed world knowledge to generate intrinsically interpretable machine learning models, i.e., decision trees, without any training data. We find that these zero-shot decision trees can surpass data-driven trees on some small-sized tabular datasets and that embeddings derived from these trees perform on par with data-driven tree-based embeddings on average. Our knowledge-driven decision tree induction and embedding approaches therefore serve as strong new baselines for data-driven machine learning methods in the low-data regime.
Authors: G\'er\^ome Meyer, Philip Breuer, Jonathan F\"urst
Abstract: Open-ended questions test a more thorough understanding than closed-ended questions and are often a preferred assessment method. However, open-ended questions are tedious to grade and subject to personal bias. Therefore, there have been efforts to speed up the grading process through automation. Short Answer Grading (SAG) systems aim to automatically score students' answers. Despite growth in SAG methods and capabilities, there exists no comprehensive short-answer grading benchmark across different subjects, grading scales, and distributions. Thus, it is hard to assess the capabilities of current automated grading methods in terms of their generalizability. In this preliminary work, we introduce the combined ASAG2024 benchmark to facilitate the comparison of automated grading systems. Combining seven commonly used short-answer grading datasets in a common structure and grading scale. For our benchmark, we evaluate a set of recent SAG methods, revealing that while LLM-based approaches reach new high scores, they still are far from reaching human performance. This opens up avenues for future research on human-machine SAG systems.
Authors: Yiming Chen, Xianghu Yue, Xiaoxue Gao, Chen Zhang, Luis Fernando D'Haro, Robby T. Tan, Haizhou Li
Abstract: Various audio-LLMs (ALLMs) have been explored recently for tackling different audio tasks simultaneously using a single, unified model. While existing evaluations of ALLMs primarily focus on single-audio tasks, real-world applications often involve processing multiple audio streams simultaneously. To bridge this gap, we propose the first multi-audio evaluation (MAE) benchmark that consists of 20 datasets from 11 multi-audio tasks encompassing both speech and sound scenarios. Comprehensive experiments on MAE demonstrate that the existing ALLMs, while being powerful in comprehending primary audio elements in individual audio inputs, struggling to handle multi-audio scenarios. To this end, we propose a novel multi-audio-LLM (MALLM) to capture audio context among multiple similar audios using discriminative learning on our proposed synthetic data. The results demonstrate that the proposed MALLM outperforms all baselines and achieves high data efficiency using synthetic data without requiring human annotations. The proposed MALLM opens the door for ALLMs towards multi-audio processing era and brings us closer to replicating human auditory capabilities in machines.
Authors: Weichen Dai, Yezeng Chen, Zijie Dai, Zhijie Huang, Yubo Liu, Yixuan Pan, Baiyang Song, Chengli Zhong, Xinhe Li, Zeyu Wang, Zhuoying Feng, Yi Zhou
Abstract: Artificial intelligence is gradually demonstrating its immense potential, and increasing attention is being given to how AI can be harnessed to advance scientific research. In this vision paper, we present our perspectives on how AI can better assist scientific inquiry and explore corresponding technical approach. We have proposed and open-sourced a large model of our KALE-LM model series, Llama3-KALE-LM-Chem-8B, which has achieved outstanding performance in tasks related to the field of chemistry. We hope that our work serves as a strong starting point, helping to realize more intelligent AI and promoting the advancement of human science and technology, as well as societal development.
Authors: Dongmei Zhou, Xuri Tang
Abstract: Domain dependence and annotation subjectivity pose challenges for supervised keyword extraction. Based on the premises that second-order keyness patterns are existent at the community level and learnable from annotated keyword extraction datasets, this paper proposes a supervised ranking approach to keyword extraction that ranks keywords with keyness patterns consisting of independent features (such as sublanguage domain and term length) and three categories of dependent features -- heuristic features, specificity features, and representavity features. The approach uses two convolutional-neural-network based models to learn keyness patterns from keyword datasets and overcomes annotation subjectivity by training the two models with bootstrap sampling strategy. Experiments demonstrate that the approach not only achieves state-of-the-art performance on ten keyword datasets in general supervised keyword extraction with an average top-10-F-measure of 0.316 , but also robust cross-domain performance with an average top-10-F-measure of 0.346 on four datasets that are excluded in the training process. Such cross-domain robustness is attributed to the fact that community-level keyness patterns are limited in number and temperately independent of language domains, the distinction between independent features and dependent features, and the sampling training strategy that balances excess risk and lack of negative training data.
Authors: James Ford, Xingmeng Zhao, Dan Schumacher, Anthony Rios
Abstract: We propose a novel framework that leverages Visual Question Answering (VQA) models to automate the evaluation of LLM-generated data visualizations. Traditional evaluation methods often rely on human judgment, which is costly and unscalable, or focus solely on data accuracy, neglecting the effectiveness of visual communication. By employing VQA models, we assess data representation quality and the general communicative clarity of charts. Experiments were conducted using two leading VQA benchmark datasets, ChartQA and PlotQA, with visualizations generated by OpenAI's GPT-3.5 Turbo and Meta's Llama 3.1 70B-Instruct models. Our results indicate that LLM-generated charts do not match the accuracy of the original non-LLM-generated charts based on VQA performance measures. Moreover, while our results demonstrate that few-shot prompting significantly boosts the accuracy of chart generation, considerable progress remains to be made before LLMs can fully match the precision of human-generated graphs. This underscores the importance of our work, which expedites the research process by enabling rapid iteration without the need for human annotation, thus accelerating advancements in this field.
Authors: Ayush Maheshwari, Preethi Jyothi, Ganesh Ramakrishnan
Abstract: Domain-specific neural machine translation (NMT) systems (e.g., in educational applications) are socially significant with the potential to help make information accessible to a diverse set of users in multilingual societies. It is desirable that such NMT systems be lexically constrained and draw from domain-specific dictionaries. Dictionaries could present multiple candidate translations for a source word/phrase due to the polysemous nature of words. The onus is then on the NMT model to choose the contextually most appropriate candidate. Prior work has largely ignored this problem and focused on the single candidate constraint setting wherein the target word or phrase is replaced by a single constraint. In this work we present DictDis, a lexically constrained NMT system that disambiguates between multiple candidate translations derived from dictionaries. We achieve this by augmenting training data with multiple dictionary candidates to actively encourage disambiguation during training by implicitly aligning multiple candidate constraints. We demonstrate the utility of DictDis via extensive experiments on English-Hindi and English-German sentences in a variety of domains including regulatory, finance, engineering. We also present comparisons on standard benchmark test datasets. In comparison with existing approaches for lexically constrained and unconstrained NMT, we demonstrate superior performance with respect to constraint copy and disambiguation related measures on all domains while also obtaining improved fluency of up to 2-3 BLEU points on some domains.
Authors: Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Jingyuan Ma, Rui Li, Heming Xia, Jingjing Xu, Zhiyong Wu, Tianyu Liu, Baobao Chang, Xu Sun, Lei Li, Zhifang Sui
Abstract: With the increasing capabilities of large language models (LLMs), in-context learning (ICL) has emerged as a new paradigm for natural language processing (NLP), where LLMs make predictions based on contexts augmented with a few examples. It has been a significant trend to explore ICL to evaluate and extrapolate the ability of LLMs. In this paper, we aim to survey and summarize the progress and challenges of ICL. We first present a formal definition of ICL and clarify its correlation to related studies. Then, we organize and discuss advanced techniques, including training strategies, prompt designing strategies, and related analysis. Additionally, we explore various ICL application scenarios, such as data engineering and knowledge updating. Finally, we address the challenges of ICL and suggest potential directions for further research. We hope that our work can encourage more research on uncovering how ICL works and improving ICL.
Authors: Vil\'em Zouhar, Sunit Bhattacharya, Ond\v{r}ej Bojar
Abstract: The Shannon game has long been used as a thought experiment in linguistics and NLP, asking participants to guess the next letter in a sentence based on its preceding context. We extend the game by introducing an optional extra modality in the form of image information. To investigate the impact of multimodal information in this game, we use human participants and a language model (LM, GPT-2). We show that the addition of image information improves both self-reported confidence and accuracy for both humans and LM. Certain word classes, such as nouns and determiners, benefit more from the additional modality information. The priming effect in both humans and the LM becomes more apparent as the context size (extra modality information + sentence context) increases. These findings highlight the potential of multimodal information in improving language understanding and modeling.
Authors: Hongcheng Guo, Jian Yang, Jiaheng Liu, Liqun Yang, Linzheng Chai, Jiaqi Bai, Junran Peng, Xiaorong Hu, Chao Chen, Dongfeng Zhang, Xu Shi, Tieqiao Zheng, Liangfan Zheng, Bo Zhang, Ke Xu, Zhoujun Li
Abstract: With the rapid development of IT operations, it has become increasingly crucial to efficiently manage and analyze large volumes of data for practical applications. The techniques of Natural Language Processing (NLP) have shown remarkable capabilities for various tasks, including named entity recognition, machine translation and dialogue systems. Recently, Large Language Models (LLMs) have achieved significant improvements across various NLP downstream tasks. However, there is a lack of specialized LLMs for IT operations. In this paper, we introduce the OWL, a large language model trained on our collected OWL-Instruct dataset with a wide range of IT-related information, where the mixture-of-adapter strategy is proposed to improve the parameter-efficient tuning across different domains or tasks. Furthermore, we evaluate the performance of our OWL on the OWL-Bench established by us and open IT-related benchmarks. OWL demonstrates superior performance results on IT tasks, which outperforms existing models by significant margins. Moreover, we hope that the findings of our work will provide more insights to revolutionize the techniques of IT operations with specialized LLMs.
Authors: Griffin Adams, Jason Zucker, No\'emie Elhadad
Abstract: Clinician must write a lengthy summary each time a patient is discharged from the hospital. This task is time-consuming due to the sheer number of unique clinical concepts covered in the admission. Identifying and covering salient entities is vital for the summary to be clinically useful. We fine-tune open-source LLMs (Mistral-7B-Instruct and Zephyr-7B-beta) on the task and find that they generate incomplete and unfaithful summaries. To increase entity coverage, we train a smaller, encoder-only model to predict salient entities, which are treated as content-plans to guide the LLM. To encourage the LLM to focus on specific mentions in the source notes, we propose SPEER: Sentence-level Planning via Embedded Entity Retrieval. Specifically, we mark each salient entity span with special "{{ }}" boundary tags and instruct the LLM to retrieve marked spans before generating each sentence. Sentence-level planning acts as a form of state tracking in that the model is explicitly recording the entities it uses. We fine-tune Mistral and Zephyr variants on a large-scale, diverse dataset of ~167k in-patient hospital admissions and evaluate on 3 datasets. SPEER shows gains in both coverage and faithfulness metrics over non-guided and guided baselines.
Authors: Saptarshi Sengupta, Connor Heaton, Suhan Cui, Soumalya Sarkar, Prasenjit Mitra
Abstract: In Natural Language Processing (NLP), Machine Reading Comprehension (MRC) is the task of answering a question based on a given context. To handle questions in the medical domain, modern language models such as BioBERT, SciBERT and even ChatGPT are trained on vast amounts of in-domain medical corpora. However, in-domain pre-training is expensive in terms of time and resources. In this paper, we propose a resource-efficient approach for injecting domain knowledge into a model without relying on such domain-specific pre-training. Knowledge graphs are powerful resources for accessing medical information. Building on existing work, we introduce a method using Multi-Layer Perceptrons (MLPs) for aligning and integrating embeddings extracted from medical knowledge graphs with the embedding spaces of pre-trained language models (LMs). The aligned embeddings are fused with open-domain LMs BERT and RoBERTa that are fine-tuned for two MRC tasks, span detection (COVID-QA) and multiple-choice questions (PubMedQA). We compare our method to prior techniques that rely on a vocabulary overlap for embedding alignment and show how our method circumvents this requirement to deliver better performance. On both datasets, our method allows BERT/RoBERTa to either perform on par (occasionally exceeding) with stronger domain-specific models or show improvements in general over prior techniques. With the proposed approach, we signal an alternative method to in-domain pre-training to achieve domain proficiency.
Authors: Guoxin Chen, Kexin Tang, Chao Yang, Fuying Ye, Yu Qiao, Yiming Qian
Abstract: Elucidating the reasoning process with structured explanations from question to answer is crucial, as it significantly enhances the interpretability, traceability, and trustworthiness of question-answering (QA) systems. However, structured explanations demand models to perform intricately structured reasoning, which poses great challenges. Most existing methods focus on single-step reasoning through supervised learning, ignoring logical dependencies between steps. Moreover, existing reinforcement learning (RL) based methods overlook the structured relationships, underutilizing the potential of RL in structured reasoning. In this paper, we propose SEER, a novel method that maximizes a structure-based return to facilitate structured reasoning and explanation. Our proposed structure-based return precisely describes the hierarchical and branching structure inherent in structured reasoning, effectively capturing the intricate relationships between different reasoning steps. In addition, we introduce a fine-grained reward function to meticulously delineate diverse reasoning steps. Extensive experiments show that SEER significantly outperforms state-of-the-art methods, achieving an absolute improvement of 6.9% over RL-based methods on EntailmentBank, a 4.4% average improvement on STREET benchmark, and exhibiting outstanding efficiency and cross-dataset generalization performance. Our code is available at https://github.com/Chen-GX/SEER.
Authors: William Jongwon Han, Diana Gomez, Avi Alok, Chaojing Duan, Michael A. Rosenberg, Douglas Weber, Emerson Liu, Ding Zhao
Abstract: Understanding the irregular electrical activity of atrial fibrillation (AFib) has been a key challenge in electrocardiography. For serious cases of AFib, catheter ablations are performed to collect intracardiac electrograms (EGMs). EGMs offer intricately detailed and localized electrical activity of the heart and are an ideal modality for interpretable cardiac studies. Recent advancements in artificial intelligence (AI) has allowed some works to utilize deep learning frameworks to interpret EGMs during AFib. Additionally, language models (LMs) have shown exceptional performance in being able to generalize to unseen domains, especially in healthcare. In this study, we are the first to leverage pretrained LMs for finetuning of EGM interpolation and AFib classification via masked language modeling. We formulate the EGM as a textual sequence and present competitive performances on AFib classification compared against other representations. Lastly, we provide a comprehensive interpretability study to provide a multi-perspective intuition of the model's behavior, which could greatly benefit the clinical use.
Authors: Gyeongman Kim, Doohyuk Jang, Eunho Yang
Abstract: Recent advancements in large language models (LLMs) have raised concerns about inference costs, increasing the need for research into model compression. While knowledge distillation (KD) is a prominent method for this, research on KD for generative language models like LLMs is relatively sparse, and the approach of distilling student-friendly knowledge, which has shown promising performance in KD for classification models, remains unexplored in generative language models. To explore this approach, we propose PromptKD, a simple yet effective method that utilizes prompt tuning - for the first time in KD - to enable generative language models to transfer student-friendly knowledge. Unlike previous works in classification that require fine-tuning the entire teacher model for extracting student-friendly knowledge, PromptKD achieves similar effects by adding a small number of prompt tokens and tuning only the prompt with student guidance. Extensive experiments on instruction-following datasets show that PromptKD achieves state-of-the-art performance while adding only 0.0007% of the teacher's parameters as prompts. Further analysis suggests that distilling student-friendly knowledge alleviates exposure bias effectively throughout the entire training process, leading to performance enhancements.
Authors: Bryan R Christ, Jonathan Kropko, Thomas Hartvigsen
Abstract: Math word problems are critical K-8 educational tools, but writing them is time consuming and requires extensive expertise. To be educational, problems must be solvable, have accurate answers, and, most importantly, be educationally appropriate. We propose that language models have potential to support K-8 math education by automatically generating word problems. However, evaluating educational appropriateness is hard to quantify. We fill this gap by having teachers evaluate problems generated by LLMs, who find existing models and data often fail to be educationally appropriate. We then explore automatically generating educational word problems, ultimately using our expert annotations to finetune a 70B language model. Our model, MATHWELL, is the first K-8 word problem generator targeted at educational appropriateness. Further expert studies find MATHWELL generates problems far more solvable, accurate, and appropriate than public models. MATHWELL also matches GPT-4's problem quality while attaining more appropriate reading levels for K-8 students and avoiding generating harmful questions.
Authors: Huy Quoc To, Ming Liu, Guangyan Huang, Hung-Nghiep Tran, Andr'e Greiner-Petter, Felix Beierle, Akiko Aizawa
Abstract: Summarization for scientific text has shown significant benefits both for the research community and human society. Given the fact that the nature of scientific text is distinctive and the input of the multi-document summarization task is substantially long, the task requires sufficient embedding generation and text truncation without losing important information. To tackle these issues, in this paper, we propose SKT5SciSumm - a hybrid framework for multi-document scientific summarization (MDSS). We leverage the Sentence-Transformer version of Scientific Paper Embeddings using Citation-Informed Transformers (SPECTER) to encode and represent textual sentences, allowing for efficient extractive summarization using k-means clustering. We employ the T5 family of models to generate abstractive summaries using extracted sentences. SKT5SciSumm achieves state-of-the-art performance on the Multi-XScience dataset. Through extensive experiments and evaluation, we showcase the benefits of our model by using less complicated models to achieve remarkable results, thereby highlighting its potential in advancing the field of multi-document summarization for scientific text.
Authors: Heydar Soudani, Evangelos Kanoulas, Faegheh Hasibi
Abstract: Language Models (LMs) memorize a vast amount of factual knowledge, exhibiting strong performance across diverse tasks and domains. However, it has been observed that the performance diminishes when dealing with less-popular or low-frequency concepts and entities, for example in domain specific applications. The two prominent approaches to enhance the performance of LMs on low-frequent topics are: Retrieval Augmented Generation (RAG) and fine-tuning (FT) over synthetic data. This paper explores and evaluates the impact of RAG and FT on customizing LMs in handling low-frequency entities on question answering tasks. We conduct extensive experiments on twelve LMs of varying size and type and different fine tuning, data augmentation, and retrieval models. Our findings indicate that while FT boosts the performance across entities of varying popularity, RAG surpasses FT by a large margin particularly for least popular factual knowledge. Additionally, the success of both RAG and FT approaches is amplified by improving retrieval and data augmentation techniques. Fine tuning, while beneficial for small LMs, requires extensive resources. To address this issue, we propose the new Stimulus RAG approach that surpasses the effectiveness of fine tuning based approaches, thereby eliminating the need for the costly data augmentation and fine tuning step for enriching LMs with less popular factual knowledge.
Authors: Hui Huang, Yingqi Qu, Jing Liu, Muyun Yang, Bing Xu, Tiejun Zhao, Wenpeng Lu
Abstract: The proliferation of open-source Large Language Models (LLMs) underscores the pressing need for evaluation methods. Existing works primarily rely on external evaluators, focusing on training and prompting strategies. However, a crucial aspect, model-aware glass-box features, is overlooked. In this study, we explore the utility of glass-box features under the scenario of self-evaluation, namely applying an LLM to evaluate its own output. We investigate various glass-box feature groups and discovered that the softmax distribution serves as a reliable quality indicator for self-evaluation. Experimental results on public benchmarks validate the feasibility of self-evaluation of LLMs using glass-box features.
Authors: Moxin Li, Wenjie Wang, Fuli Feng, Fengbin Zhu, Qifan Wang, Tat-Seng Chua
Abstract: Self-detection for Large Language Models (LLMs) seeks to evaluate the trustworthiness of the LLM's output by leveraging its own capabilities, thereby alleviating the issue of output hallucination. However, existing self-detection approaches only retrospectively evaluate answers generated by LLM, typically leading to the over-trust in incorrectly generated answers. To tackle this limitation, we propose a novel self-detection paradigm that considers the comprehensive answer space beyond LLM-generated answers. It thoroughly compares the trustworthiness of multiple candidate answers to mitigate the over-trust in LLM-generated incorrect answers. Building upon this paradigm, we introduce a two-step framework, which firstly instructs LLM to reflect and provide justifications for each candidate answer, and then aggregates the justifications for comprehensive target answer evaluation. This framework can be seamlessly integrated with existing approaches for superior self-detection. Extensive experiments on six datasets spanning three tasks demonstrate the effectiveness of the proposed framework.
Authors: Farnaz Kohankhaki, D. B. Emerson, Jacob-Junqi Tian, Laleh Seyyed-Kalantari, Faiza Khan Khattak
Abstract: Bias in large language models (LLMs) has many forms, from overt discrimination to implicit stereotypes. Counterfactual bias evaluation is a widely used approach to quantifying bias and often relies on template-based probes that explicitly state group membership. It measures whether the outcome of a task, performed by an LLM, is invariant to a change of group membership. In this work, we find that template-based probes can lead to unrealistic bias measurements. For example, LLMs appear to mistakenly cast text associated with White race as negative at higher rates than other groups. We hypothesize that this arises artificially via a mismatch between commonly unstated norms, in the form of markedness, in the pretraining text of LLMs (e.g., Black president vs. president) and templates used for bias measurement (e.g., Black president vs. White president). The findings highlight the potential misleading impact of varying group membership through explicit mention in counterfactual bias quantification.
Authors: Bo Peng, Daniel Goldstein, Quentin Anthony, Alon Albalak, Eric Alcaide, Stella Biderman, Eugene Cheah, Xingjian Du, Teddy Ferdinan, Haowen Hou, Przemys{\l}aw Kazienko, Kranthi Kiran GV, Jan Koco\'n, Bart{\l}omiej Koptyra, Satyapriya Krishna, Ronald McClelland Jr., Jiaju Lin, Niklas Muennighoff, Fares Obeid, Atsushi Saito, Guangyu Song, Haoqin Tu, Cahya Wirawan, Stanis{\l}aw Wo\'zniak, Ruichong Zhang, Bingchen Zhao, Qihang Zhao, Peng Zhou, Jian Zhu, Rui-Jie Zhu
Abstract: We present Eagle (RWKV-5) and Finch (RWKV-6), sequence models improving upon the RWKV (RWKV-4) architecture. Our architectural design advancements include multi-headed matrix-valued states and a dynamic recurrence mechanism that improve expressivity while maintaining the inference efficiency characteristics of RNNs. We introduce a new multilingual corpus with 1.12 trillion tokens and a fast tokenizer based on greedy matching for enhanced multilinguality. We trained four Eagle models, ranging from 0.46 to 7.5 billion parameters, and two Finch models with 1.6 and 3.1 billion parameters and find that they achieve competitive performance across a wide variety of benchmarks. We release all our models on HuggingFace under the Apache 2.0 license. Models at: https://huggingface.co/RWKV Training code at: https://github.com/RWKV/RWKV-LM Inference code at: https://github.com/RWKV/ChatRWKV Time-parallel training code at: https://github.com/RWKV/RWKV-infctx-trainer
URLs: https://huggingface.co/RWKV, https://github.com/RWKV/RWKV-LM, https://github.com/RWKV/ChatRWKV, https://github.com/RWKV/RWKV-infctx-trainer
Authors: Tianhui Zhang, Bei Peng, Danushka Bollegala
Abstract: Generative Commonsense Reasoning (GCR) requires a model to reason about a situation using commonsense knowledge, while generating coherent sentences. Although the quality of the generated sentences is crucial, the diversity of the generation is equally important because it reflects the model's ability to use a range of commonsense knowledge facts. Large Language Models (LLMs) have shown proficiency in enhancing the generation quality across various tasks through in-context learning (ICL) using given examples without the need for any fine-tuning. However, the diversity aspect in LLM outputs has not been systematically studied before. To address this, we propose a simple method that diversifies the LLM generations, while preserving their quality. Experimental results on three benchmark GCR datasets show that our method achieves an ideal balance between the quality and diversity. Moreover, the sentences generated by our proposed method can be used as training data to improve diversity in existing commonsense generators.
Authors: Guoxin Chen, Minpeng Liao, Chengxi Li, Kai Fan
Abstract: Although recent advancements in large language models (LLMs) have significantly improved their performance on various tasks, they still face challenges with complex and symbolic multi-step reasoning, particularly in mathematical reasoning. To bolster the mathematical reasoning capabilities of LLMs, most existing efforts concentrate on seeking assistance from either domain experts or GPT-4 for high-quality process-supervised data, which is not only expensive but also labor-intensive. In our study, we propose an innovative framework, AlphaMath, that bypasses the need for process annotations (from humans or GPTs) by leveraging Monte Carlo Tree Search (MCTS). This framework focuses on unleashing the potential of a well-pretrained LLM to autonomously enhance its mathematical reasoning. Specifically, we integrate a value model with the LLM, automatically generating both process supervision and step-level evaluation signals in MCTS. Furthermore, we propose an efficient inference strategy, step-level beam search, where the value model is crafted to assist the policy model (i.e., LLM) in navigating more effective reasoning paths, rather than solely relying on prior probabilities. The experimental results on both in-domain and out-of-domain datasets demonstrate that even without GPT-4 or human-annotated process supervision, our AlphaMath framework achieves comparable or superior results to previous state-of-the-art methods.
Authors: Sander Land, Max Bartolo
Abstract: The disconnect between tokenizer creation and model training in language models allows for specific inputs, such as the infamous SolidGoldMagikarp token, to induce unwanted model behaviour. Although such `glitch tokens', tokens present in the tokenizer vocabulary but that are nearly or entirely absent during model training, have been observed across various models, a reliable method to identify and address them has been missing. We present a comprehensive analysis of Large Language Model tokenizers, specifically targeting this issue of detecting under-trained tokens. Through a combination of tokenizer analysis, model weight-based indicators, and prompting techniques, we develop novel and effective methods for automatically detecting these problematic tokens. Our findings demonstrate the prevalence of such tokens across a diverse set of models and provide insights into improving the efficiency and safety of language models.
Authors: Raul Salles de Padua, Imran Qureshi
Abstract: Patient hand-off and triage are two fundamental problems in health care. Often doctors must painstakingly summarize complex findings to efficiently communicate with specialists and quickly make decisions on which patients have the most urgent cases. In pursuit of these challenges, we present (1) a model with state-of-art radiology report summarization performance using (2) a novel method for augmenting medical data, and (3) an analysis of the model limitations and radiology knowledge gain. We also provide a data processing pipeline for future models developed on the the MIMIC CXR dataset. Our best performing model was a fine-tuned BERT-to-BERT encoder-decoder with 58.75/100 ROUGE-L F1, which outperformed specialized checkpoints with more sophisticated attention mechanisms. We investigate these aspects in this work.
Authors: Peng Hu, Changjiang Gao, Ruiqi Gao, Jiajun Chen, Shujian Huang
Abstract: Large Language Models (LLMs) possess extensive knowledge and strong capabilities in performing in-context reasoning. However, previous work challenges their out-of-context reasoning ability, i.e., the ability to infer information from their training data, instead of from the context or prompt. This paper focuses on a significant aspect of out-of-context reasoning: Out-of-Context Knowledge Reasoning (OCKR), which is to combine multiple knowledge to infer new knowledge. We designed a synthetic dataset with seven representative OCKR tasks to systematically assess the OCKR capabilities of LLMs. Using this dataset, we evaluated several LLMs and discovered that their proficiency in this aspect is limited, regardless of whether the knowledge is trained in a separate or adjacent training settings. Moreover, training the model to reason with reasoning examples does not result in significant improvement, while training the model to perform explicit knowledge retrieval helps for retrieving attribute knowledge but not the relation knowledge, indicating that the model's limited OCKR capabilities are due to difficulties in knowledge retrieval. Furthermore, we treat cross-lingual knowledge transfer as a distinct form of OCKR, and evaluate this ability. Our results show that the evaluated model also exhibits limited ability in transferring knowledge across languages.
Authors: Dojun Park, Jiwoo Lee, Seohyun Park, Hyeyun Jeong, Youngeun Koo, Soonha Hwang, Seonwoo Park, Sungeun Lee
Abstract: As the capabilities of Large Language Models (LLMs) expand, it becomes increasingly important to evaluate them beyond basic knowledge assessment, focusing on higher-level language understanding. This study introduces MultiPragEval, the first multilingual pragmatic evaluation of LLMs, designed for English, German, Korean, and Chinese. Comprising 1200 question units categorized according to Grice's Cooperative Principle and its four conversational maxims, MultiPragEval enables an in-depth assessment of LLMs' contextual awareness and their ability to infer implied meanings. Our findings demonstrate that Claude3-Opus significantly outperforms other models in all tested languages, establishing a state-of-the-art in the field. Among open-source models, Solar-10.7B and Qwen1.5-14B emerge as strong competitors. By analyzing pragmatic inference, we provide valuable insights into the capabilities essential for advanced language comprehension in AI systems.
Authors: Guoxin Chen, Minpeng Liao, Chengxi Li, Kai Fan
Abstract: Direct Preference Optimization (DPO) using an implicit reward model has proven to be an effective alternative to reinforcement learning from human feedback (RLHF) for fine-tuning preference aligned large language models (LLMs). However, the overall preference annotations of responses do not fully capture the fine-grained quality of model outputs in complex multi-step reasoning tasks, such as mathematical reasoning. To address this limitation, we introduce a novel algorithm called Step-level Value Preference Optimization (SVPO). Our approach employs Monte Carlo Tree Search (MCTS) to automatically annotate step-level preferences for multi-step reasoning. Furthermore, from the perspective of learning-to-rank, we train an explicit value model to replicate the behavior of the implicit reward model, complementing standard preference optimization. This value model enables the LLM to generate higher reward responses with minimal cost during inference. Experimental results demonstrate that our method achieves state-of-the-art performance on both in-domain and out-of-domain mathematical reasoning benchmarks. Our code is available at \url{https://github.com/MARIO-Math-Reasoning/Super_MARIO}.
Authors: Akshay Paruchuri, Jake Garrison, Shun Liao, John Hernandez, Jacob Sunshine, Tim Althoff, Xin Liu, Daniel McDuff
Abstract: Language models (LM) are capable of remarkably complex linguistic tasks; however, numerical reasoning is an area in which they frequently struggle. An important but rarely evaluated form of reasoning is understanding probability distributions. In this paper, we focus on evaluating the probabilistic reasoning capabilities of LMs using idealized and real-world statistical distributions. We perform a systematic evaluation of state-of-the-art LMs on three tasks: estimating percentiles, drawing samples, and calculating probabilities. We evaluate three ways to provide context to LMs 1) anchoring examples from within a distribution or family of distributions, 2) real-world context, 3) summary statistics on which to base a Normal approximation. Models can make inferences about distributions, and can be further aided by the incorporation of real-world context, example shots and simplified assumptions, even if these assumptions are incorrect or misspecified. To conduct this work, we developed a comprehensive benchmark distribution dataset with associated question-answer pairs that we will release publicly.
Authors: Mahammed Kamruzzaman, Hieu Minh Nguyen, Gene Louis Kim
Abstract: Many recent studies have investigated social biases in LLMs but brand bias has received little attention. This research examines the biases exhibited by LLMs towards different brands, a significant concern given the widespread use of LLMs in affected use cases such as product recommendation and market analysis. Biased models may perpetuate societal inequalities, unfairly favoring established global brands while marginalizing local ones. Using a curated dataset across four brand categories, we probe the behavior of LLMs in this space. We find a consistent pattern of bias in this space -- both in terms of disproportionately associating global brands with positive attributes and disproportionately recommending luxury gifts for individuals in high-income countries. We also find LLMs are subject to country-of-origin effects which may boost local brand preference in LLM outputs in specific contexts.
Authors: Minsang Kim, Cheoneum Park, Seungjun Baek
Abstract: Retrieval-augmented generation (RAG) has received much attention for Open-domain question-answering (ODQA) tasks as a means to compensate for the parametric knowledge of large language models (LLMs). While previous approaches focused on processing retrieved passages to remove irrelevant context, they still rely heavily on the quality of retrieved passages which can degrade if the question is ambiguous or complex. In this paper, we propose a simple yet efficient method called question and passage augmentation (QPaug) via LLMs for open-domain QA. QPaug first decomposes the original questions into multiple-step sub-questions. By augmenting the original question with detailed sub-questions and planning, we are able to make the query more specific on what needs to be retrieved, improving the retrieval performance. In addition, to compensate for the case where the retrieved passages contain distracting information or divided opinions, we augment the retrieved passages with self-generated passages by LLMs to guide the answer extraction. Experimental results show that QPaug outperforms the previous state-of-the-art and achieves significant performance gain over existing RAG methods. The source code is available at \url{https://github.com/kmswin1/QPaug}.
Authors: Jan Philip Wahle, Terry Ruas, Yang Xu, Bela Gipp
Abstract: Much of the success of modern language models depends on finding a suitable prompt to instruct the model. Until now, it has been largely unknown how variations in the linguistic expression of prompts affect these models. This study systematically and empirically evaluates which linguistic features influence models through paraphrase types, i.e., different linguistic changes at particular positions. We measure behavioral changes for five models across 120 tasks and six families of paraphrases (i.e., morphology, syntax, lexicon, lexico-syntax, discourse, and others). We also control for other prompt engineering factors (e.g., prompt length, lexical diversity, and proximity to training data). Our results show a potential for language models to improve tasks when their prompts are adapted in specific paraphrase types (e.g., 6.7% median gain in Mixtral 8x7B; 5.5% in LLaMA 3 8B). In particular, changes in morphology and lexicon, i.e., the vocabulary used, showed promise in improving prompts. These findings contribute to developing more robust language models capable of handling variability in linguistic expression.
Authors: Chin Yuen Kwok, Jia Qi Yip, Eng Siong Chng
Abstract: Continual Learning (CL) involves fine-tuning pre-trained models with new data while maintaining the performance on the pre-trained data. This is particularly relevant for expanding multilingual ASR (MASR) capabilities. However, existing CL methods, mainly designed for computer vision and reinforcement learning tasks, often yield sub-optimal results when directly applied to MASR. We hypothesise that this is because CL of the auto-regressive decoder in the MASR model is difficult. To verify this, we propose four optimizations on the decoder. They include decoder-layer gradient surgery, freezing unused token embeddings, suppressing output of newly added tokens, and learning rate re-scaling. Our experiments on adapting Whisper to 10 unseen languages from the Common Voice dataset demonstrate that these optimizations reduce the Average Word Error Rate (AWER) of pretrained languages from 14.2% to 12.4% compared with Experience Replay, without compromising the AWER of new languages.
Authors: Xijie Huang, Zechun Liu, Shih-Yang Liu, Kwang-Ting Cheng
Abstract: Low-Rank Adaptation (LoRA), as a representative Parameter-Efficient Fine-Tuning (PEFT)method, significantly enhances the training efficiency by updating only a small portion of the weights in Large Language Models (LLMs). Recently, weight-only quantization techniques have also been applied to LoRA methods to reduce the memory footprint of fine-tuning. However, applying weight-activation quantization to the LoRA pipeline is under-explored, and we observe substantial performance degradation primarily due to the presence of activation outliers. In this work, we propose RoLoRA, the first LoRA-based scheme for effective weight-activation quantization. RoLoRA utilizes rotation for outlier elimination and proposes rotation-aware fine-tuning to preserve the outlier-free characteristics in rotated LLMs. Experimental results show RoLoRA consistently improves low-bit LoRA convergence and post-training quantization robustness in weight-activation settings. We evaluate RoLoRA across LLaMA2-7B/13B, LLaMA3-8B models, achieving up to 29.5% absolute accuracy gain of 4-bit weight-activation quantized LLaMA2- 13B on commonsense reasoning tasks compared to LoRA baseline. We further demonstrate its effectiveness on Large Multimodal Models (LLaVA-1.5-7B). Codes are available at https://github.com/HuangOwen/RoLoRA
Authors: Ishita Kumar, Snigdha Viswanathan, Sushrita Yerra, Alireza Salemi, Ryan A. Rossi, Franck Dernoncourt, Hanieh Deilamsalehy, Xiang Chen, Ruiyi Zhang, Shubham Agarwal, Nedim Lipka, Chein Van Nguyen, Thien Huu Nguyen, Hamed Zamani
Abstract: Long-text generation is seemingly ubiquitous in real-world applications of large language models such as generating an email or writing a review. Despite the fundamental importance and prevalence of long-text generation in many practical applications, existing work on personalized generation has focused on the generation of very short text. To overcome these limitations, we study the problem of personalized long-text generation, that is, generating long-text that is personalized for a specific user while being practically useful for the vast majority of real-world applications that naturally require the generation of longer text. In this work, we demonstrate the importance of user-specific personalization for long-text generation tasks and develop the Long-text Language Model Personalization (LongLaMP) Benchmark. LongLaMP provides a comprehensive and diverse evaluation framework for personalized long-text generation. Extensive experiments on LongLaMP for zero-shot and fine-tuned language tasks demonstrate the effectiveness of the proposed benchmark and its utility for developing and evaluating techniques for personalized long-text generation across a wide variety of long-text generation tasks. The results highlight the importance of personalization across a wide variety of long-text generation tasks. Finally, we release the benchmark for others to use for this important problem.
Authors: Henrique Da Silva Gameiro, Andrei Kucharavy, Ljiljana Dolamic
Abstract: With the emergence of widely available powerful LLMs, disinformation generated by large Language Models (LLMs) has become a major concern. Historically, LLM detectors have been touted as a solution, but their effectiveness in the real world is still to be proven. In this paper, we focus on an important setting in information operations -- short news-like posts generated by moderately sophisticated attackers. We demonstrate that existing LLM detectors, whether zero-shot or purpose-trained, are not ready for real-world use in that setting. All tested zero-shot detectors perform inconsistently with prior benchmarks and are highly vulnerable to sampling temperature increase, a trivial attack absent from recent benchmarks. A purpose-trained detector generalizing across LLMs and unseen attacks can be developed, but it fails to generalize to new human-written texts. We argue that the former indicates domain-specific benchmarking is needed, while the latter suggests a trade-off between the adversarial evasion resilience and overfitting to the reference human text, with both needing evaluation in benchmarks and currently absent. We believe this suggests a re-consideration of current LLM detector benchmarking approaches and provides a dynamically extensible benchmark to allow it (https://github.com/Reliable-Information-Lab-HEVS/benchmark_llm_texts_detection).
URLs: https://github.com/Reliable-Information-Lab-HEVS/benchmark_llm_texts_detection).
Authors: Wei Wang, Qing Li
Abstract: Memory is the foundation of all human activities; without memory, it would be nearly impossible for people to perform any task in daily life. With the development of Large Language Models (LLMs), their language capabilities are becoming increasingly comparable to those of humans. But do LLMs have memory? Based on current performance, LLMs do appear to exhibit memory. So, what is the underlying mechanism of this memory? Previous research has lacked a deep exploration of LLMs' memory capabilities and the underlying theory. In this paper, we use Universal Approximation Theorem (UAT) to explain the memory mechanism in LLMs. We also conduct experiments to verify the memory capabilities of various LLMs, proposing a new method to assess their abilities based on these memory ability. We argue that LLM memory operates like Schr\"odinger's memory, meaning that it only becomes observable when a specific memory is queried. We can only determine if the model retains a memory based on its output in response to the query; otherwise, it remains indeterminate. Finally, we expand on this concept by comparing the memory capabilities of the human brain and LLMs, highlighting the similarities and differences in their operational mechanisms.
Authors: Ningyuan Xi, Xiaoyu Wang, Yetao Wu, Teng Chen, Qingqing Gu, Jinxian Qu, Zhonglin Jiang, Yong Chen, Luo Ji
Abstract: Large Language Model can reasonably understand and generate human expressions but may lack of thorough thinking and reasoning mechanisms. Recently there have been several studies which enhance the thinking ability of language models but most of them are not data-driven or training-based. In this paper, we are motivated by the cognitive mechanism in the natural world, and design a novel model architecture called TaS which allows it to first consider the thoughts and then express the response based upon the query. We design several pipelines to annotate or generate the thought contents from prompt-response samples, then add language heads in a middle layer which behaves as the thinking layer. We train the language model by the thoughts-augmented data and successfully let the thinking layer automatically generate reasonable thoughts and finally output more reasonable responses. Both qualitative examples and quantitative results validate the effectiveness and performance of TaS. Our code is available at https://anonymous.4open.science/r/TadE.
Authors: Zhenhong Zhang, Jiajing Chen, Weiyan Shi, Lingjie Yi, Chihang Wang, Qian Yu
Abstract: With the rapid development of artificial intelligence technology, especially the increasingly widespread application of question-and-answer systems, high-quality question generation has become a key component in supporting the development of these systems. This article focuses on knowledge-based question generation technology, which aims to enable computers to simulate the human questioning process based on understanding specific texts or knowledge bases. In light of the issues of hallucination and knowledge gaps present in large-scale language models when applied to knowledge-intensive tasks, this paper proposes an enhanced question generation method that incorporates contrastive learning. This method utilizes multiple models to jointly mine domain knowledge and uses contrastive learning to guide the model in reducing noise and hallucinations in generation. Experimental results show that by designing prompts containing contrasting examples, the model's performance in question generation improves considerably, particularly when contrasting instructions and examples are used simultaneously, leading to the highest quality of generated questions and improved accuracy. These results demonstrate that the method proposed in this study, which combines contrasting context and chain-of-thought prompts, can effectively improve both the quality and the practicality of question generation.
Authors: Runsong Zhao, Pengcheng Huang, Xinyu Liu, Chunyang Xiao, Tong Xiao, Jingbo Zhu
Abstract: Compressing Transformer inputs into compressd tokens allows running LLMs with improved speed and cost efficiency. Based on the compression method ICAE, we carefully examine the position identifier choices for compressed tokens and also propose a new compression loss. We demonstrate empirically that our proposed methods achieve significantly higher compression ratios (15x compared to 4x for ICAE), while being able to attain comparable reconstruction performance.
Authors: Ioannis Panagiotopoulos, Giorgos Filandrianos, Maria Lymperaiou, Giorgos Stamou
Abstract: Riddle-solving requires advanced reasoning skills, pushing LLMs to engage in abstract thinking and creative problem-solving, often revealing limitations in their cognitive abilities. In this paper, we examine the riddle-solving capabilities of LLMs using a multiple-choice format, exploring how different prompting techniques impact performance on riddles that demand diverse reasoning skills. To enhance results, we introduce RISCORE (RIddle Solving with COntext REcontruciton) a novel fully automated prompting method that generates and utilizes contextually reconstructed sentence-based puzzles in conjunction with the original examples to create few-shot exemplars. Our experiments demonstrate that RISCORE significantly improves the performance of language models in both vertical and lateral thinking tasks, surpassing traditional exemplar selection strategies across a variety of few-shot settings.
Authors: Pritika Ramu, Koustava Goswami, Apoorv Saxena, Balaji Vasan Srinivavsan
Abstract: Accurately attributing answer text to its source document is crucial for developing a reliable question-answering system. However, attribution for long documents remains largely unexplored. Post-hoc attribution systems are designed to map answer text back to the source document, yet the granularity of this mapping has not been addressed. Furthermore, a critical question arises: What exactly should be attributed? This involves identifying the specific information units within an answer that require grounding. In this paper, we propose and investigate a novel approach to the factual decomposition of generated answers for attribution, employing template-based in-context learning. To accomplish this, we utilize the question and integrate negative sampling during few-shot in-context learning for decomposition. This approach enhances the semantic understanding of both abstractive and extractive answers. We examine the impact of answer decomposition by providing a thorough examination of various attribution approaches, ranging from retrieval-based techniques to LLM-based attributors.
Authors: Joshua Ashkinaze, Emily Fry, Narendra Edara, Eric Gilbert, Ceren Budak
Abstract: Recent debates raised concerns that language models may favor certain viewpoints. But what if the solution is not to aim for a 'view from nowhere' but rather to leverage different viewpoints? We introduce Plurals, a system and Python library for pluralistic AI deliberation. Plurals consists of Agents (LLMs, optionally with personas) which deliberate within customizable Structures, with Moderators overseeing deliberation. Plurals is a generator of simulated social ensembles. Plurals integrates with government datasets to create nationally representative personas, includes deliberation templates inspired by democratic deliberation theory, and allows users to customize both information-sharing structures and deliberation behavior within Structures. Six case studies demonstrate fidelity to theoretical constructs and efficacy. Three randomized experiments show simulated focus groups produced output resonant with an online sample of the relevant audiences (chosen over zero-shot generation in 75% of trials). Plurals is both a paradigm and a concrete system for pluralistic AI. The Plurals library is available at https://github.com/josh-ashkinaze/plurals and will be continually updated.
Authors: Robin Shing-Hei Yuen, Timothy Tin-Long Tse, Jian Zhu
Abstract: Current speech-based LLMs are predominantly trained on extensive ASR and TTS datasets, excelling in tasks related to these domains. However, their ability to handle direct speech-to-speech conversations remains notably constrained. These models often rely on an ASR-to-TTS chain-of-thought pipeline, converting speech into text for processing before generating audio responses, which introduces latency and loses audio features. We propose a method that implicitly internalizes ASR chain of thought into a speech LLM, enhancing its native speech understanding capabilities. Our approach reduces latency and improves the model's native understanding of speech, paving the way for more efficient and natural real-time audio interactions. We also release a large-scale synthetic conversational dataset to facilitate further research.
Authors: Zhejian Zhou, Jiayu Wang, Dahua Lin, Kai Chen
Abstract: Though Large Language Models (LLMs) have shown remarkable abilities in mathematics reasoning, they are still struggling with performing numeric operations accurately, such as addition and multiplication. Numbers can be tokenized into tokens in various ways by different LLMs and affect the numeric operations performance. Currently, there are two representatives: 1) Tokenize into $1$-digit, and 2) Tokenize into $1\sim 3$ digit. The difference is roughly equivalent to using different numeral systems (namely base $10$ or base $10^{3}$). In light of this, we study the scaling behavior of different numeral systems in the context of transformer-based large language models. We empirically show that a base $10$ system is consistently more data-efficient than a base $10^{2}$ or $10^{3}$ system across training data scale, model sizes under from-scratch training settings, while different number systems have very similar fine-tuning performances. We attribute this to higher token frequencies of a base $10$ system. Additionally, we reveal extrapolation behavior patterns on addition and multiplication. We identify that base $100$ and base $1000$ systems struggle on token-level discernment and token-level operations. We also sheds light on the mechanism learnt by the models.
Authors: Cheolhun Jang
Abstract: Preference optimization methods typically begin training with a well-trained SFT model as a reference model. In RLHF and DPO, a regularization term is used during the preference optimization process to prevent the policy model from deviating too far from the reference model's distribution, thereby avoiding the generation of anomalous responses. When the reference model is already well-aligned with the given data or only requires slight adjustments, this approach can produce a well-aligned model. However, if the reference model is not aligned with the given data and requires significant deviation from its current state, a regularization term may actually hinder the model alignment. In this study, we propose \textbf{Modulated Intervention Preference Optimization (MIPO)} to address this issue. MIPO modulates the degree of intervention from the reference model based on how well the given data is aligned with it. If the data is well-aligned, the intervention is increased to prevent the policy model from diverging significantly from reference model. Conversely, if the alignment is poor, the interference is reduced to facilitate more extensive training. We compare the performance of MIPO and DPO using Mistral-7B and Llama3-8B in Alpaca Eval 2.0 and MT-Bench. The experimental results demonstrate that MIPO consistently outperforms DPO across various evaluation scenarios.
Authors: Siyan Wang, Bradford Levy
Abstract: Many of the recent breakthroughs in language modeling have resulted from scaling effectively the same model architecture to larger datasets. In this vein, recent work has highlighted performance gains from increasing training dataset size and quality, suggesting a need for novel sources of large-scale datasets. In this work, we introduce BeanCounter, a public dataset consisting of more than 159B tokens extracted from businesses' disclosures. We show that this data is indeed novel: less than 0.1% of BeanCounter appears in Common Crawl-based datasets and it is an order of magnitude larger than datasets relying on similar sources. Given the data's provenance, we hypothesize that BeanCounter is comparatively more factual and less toxic than web-based datasets. Exploring this hypothesis, we find that many demographic identities occur with similar prevalence in BeanCounter but with significantly less toxic context relative to other datasets. To demonstrate the utility of BeanCounter, we evaluate and compare two LLMs continually pre-trained on BeanCounter with their base models. We find an 18-33% reduction in toxic generation and improved performance within the finance domain for the continually pretrained models. Collectively, our work suggests that BeanCounter is a novel source of low-toxicity and high-quality domain-specific data with sufficient scale to train multi-billion parameter LLMs.
Authors: Naoki Wake, Atsushi Kanehira, Kazuhiro Sasabuchi, Jun Takamatsu, Katsushi Ikeuchi
Abstract: We introduce a pipeline that enhances a general-purpose Vision Language Model, GPT-4V(ision), to facilitate one-shot visual teaching for robotic manipulation. This system analyzes videos of humans performing tasks and outputs executable robot programs that incorporate insights into affordances. The process begins with GPT-4V analyzing the videos to obtain textual explanations of environmental and action details. A GPT-4-based task planner then encodes these details into a symbolic task plan. Subsequently, vision systems spatially and temporally ground the task plan in the videos. Objects are identified using an open-vocabulary object detector, and hand-object interactions are analyzed to pinpoint moments of grasping and releasing. This spatiotemporal grounding allows for the gathering of affordance information (e.g., grasp types, waypoints, and body postures) critical for robot execution. Experiments across various scenarios demonstrate the method's efficacy in enabling real robots to operate from one-shot human demonstrations. Meanwhile, quantitative tests have revealed instances of hallucination in GPT-4V, highlighting the importance of incorporating human supervision within the pipeline. The prompts of GPT-4V/GPT-4 are available at this project page: https://microsoft.github.io/GPT4Vision-Robot-Manipulation-Prompts/
URLs: https://microsoft.github.io/GPT4Vision-Robot-Manipulation-Prompts/
Authors: Saman Motamed, Danda Pani Paudel, Luc Van Gool
Abstract: Text-to-Image (T2I) models excel at synthesizing concepts such as nouns, appearances, and styles. To enable customized content creation based on a few example images of a concept, methods such as Textual Inversion and DreamBooth invert the desired concept and enable synthesizing it in new scenes. However, inverting personalized concepts that go beyond object appearance and style (adjectives and verbs) through natural language remains a challenge. Two key characteristics of these concepts contribute to the limitations of current inversion methods. 1) Adjectives and verbs are entangled with nouns (subject) and can hinder appearance-based inversion methods, where the subject appearance leaks into the concept embedding, and 2) describing such concepts often extends beyond single word embeddings. In this study, we introduce Lego, a textual inversion method designed to invert subject-entangled concepts from a few example images. Lego disentangles concepts from their associated subjects using a simple yet effective Subject Separation step and employs a Context Loss that guides the inversion of single/multi-embedding concepts. In a thorough user study, Lego-generated concepts were preferred over 70% of the time when compared to the baseline in terms of authentically generating concepts according to a reference. Additionally, visual question answering using an LLM suggested Lego-generated concepts are better aligned with the text description of the concept.
Authors: Adri\'an Bazaga, Pietro Li\`o, Gos Micklem
Abstract: Hypergraphs are characterized by complex topological structure, representing higher-order interactions among multiple entities through hyperedges. Lately, hypergraph-based deep learning methods to learn informative data representations for the problem of node classification on text-attributed hypergraphs have garnered increasing research attention. However, existing methods struggle to simultaneously capture the full extent of hypergraph structural information and the rich linguistic attributes inherent in the nodes attributes, which largely hampers their effectiveness and generalizability. To overcome these challenges, we explore ways to further augment a pretrained BERT model with specialized hypergraph-aware layers for the task of node classification. Such layers introduce higher-order structural inductive bias into the language model, thus improving the model's capacity to harness both higher-order context information from the hypergraph structure and semantic information present in text. In this paper, we propose a new architecture, HyperBERT, a mixed text-hypergraph model which simultaneously models hypergraph relational structure while maintaining the high-quality text encoding capabilities of a pre-trained BERT. Notably, HyperBERT presents results that achieve a new state-of-the-art on five challenging text-attributed hypergraph node classification benchmarks.
Authors: Wen-Shuo Chao, Zhi Zheng, Hengshu Zhu, Hao Liu
Abstract: Large Language Models (LLMs) demonstrate robust capabilities across various fields, leading to a paradigm shift in LLM-enhanced Recommender System (RS). Research to date focuses on point-wise and pair-wise recommendation paradigms, which are inefficient for LLM-based recommenders due to high computational costs. However, existing list-wise approaches also fall short in ranking tasks due to misalignment between ranking objectives and next-token prediction. Moreover, these LLM-based methods struggle to effectively address the order relation among candidates, particularly given the scale of ratings. To address these challenges, this paper introduces the large language model framework with Aligned Listwise Ranking Objectives (ALRO). ALRO is designed to bridge the gap between the capabilities of LLMs and the nuanced requirements of ranking tasks. Specifically, ALRO employs explicit feedback in a listwise manner by introducing soft lambda loss, a customized adaptation of lambda loss designed for optimizing order relations. This mechanism provides more accurate optimization goals, enhancing the ranking process. Additionally, ALRO incorporates a permutation-sensitive learning mechanism that addresses position bias, a prevalent issue in generative models, without imposing additional computational burdens during inference. Our evaluative studies reveal that ALRO outperforms both existing embedding-based recommendation methods and LLM-based recommendation baselines.
Authors: Lara J. Martin, Malathy Nagalakshmi
Abstract: Natural Language Processing (NLP) techniques are being used more frequently to improve high-tech Augmentative and Alternative Communication (AAC), but many of these techniques are integrated without the inclusion of the users' perspectives. Autistic adults are particularly neglected in the design of AAC tools. We conducted in-depth interviews with 12 autistic adults to find the pain points of current AAC and determine what technological advances they might find helpful. We found that in addition to technological issues, there are many societal issues as well. We found 9 different categories of themes from our interviews: input flexibility, output flexibility, selecting or adapting AAC for a good fit, when to start or swap AAC, benefits, access as an adult, stumbling blocks for continued use, social concerns, and control of communication. In this paper, we go through these categories in depth and then suggest possible guidelines for developers, NLP researchers, and policy makers.
Authors: Gary A. McCully, John D. Hastings, Shengjie Xu, Adam Fortier
Abstract: Detecting vulnerabilities within compiled binaries is challenging due to lost high-level code structures and other factors such as architectural dependencies, compilers, and optimization options. To address these obstacles, this research explores vulnerability detection using natural language processing (NLP) embedding techniques with word2vec, BERT, and RoBERTa to learn semantics from intermediate representation (LLVM IR) code. Long short-term memory (LSTM) neural networks were trained on embeddings from encoders created using approximately 48k LLVM functions from the Juliet dataset. This study is pioneering in its comparison of word2vec models with multiple bidirectional transformers (BERT, RoBERTa) embeddings built using LLVM code to train neural networks to detect vulnerabilities in compiled binaries. Word2vec Skip-Gram models achieved 92% validation accuracy in detecting vulnerabilities, outperforming word2vec Continuous Bag of Words (CBOW), BERT, and RoBERTa. This suggests that complex contextual embeddings may not provide advantages over simpler word2vec models for this task when a limited number (e.g. 48K) of data samples are used to train the bidirectional transformer-based models. The comparative results provide novel insights into selecting optimal embeddings for learning compiler-independent semantic code representations to advance machine learning detection of vulnerabilities in compiled binaries.
Authors: Kamalkumar Rathinasamy, Jayarama Nettar, Amit Kumar, Vishal Manchanda, Arun Vijayakumar, Ayush Kataria, Venkateshprasanna Manjunath, Chidambaram GS, Jaskirat Singh Sodhi, Shoeb Shaikh, Wasim Akhtar Khan, Prashant Singh, Tanishq Dattatray Ige, Vipin Tiwari, Rajab Ali Mondal, Harshini K, S Reka, Chetana Amancharla, Faiz ur Rahman, Harikrishnan P A, Indraneel Saha, Bhavya Tiwary, Navin Shankar Patel, Pradeep T S, Balaji A J, Priyapravas, Mohammed Rafee Tarafdar
Abstract: Enterprises grapple with the significant challenge of managing proprietary unstructured data, hindering efficient information retrieval. This has led to the emergence of AI-driven information retrieval solutions, designed to adeptly extract relevant insights to address employee inquiries. These solutions often leverage pre-trained embedding models and generative models as foundational components. While pre-trained embeddings may exhibit proximity or disparity based on their original training objectives, they might not fully align with the unique characteristics of enterprise-specific data, leading to suboptimal alignment with the retrieval goals of enterprise environments. In this paper, we propose a comprehensive methodology for contextualizing pre-trained embedding models to enterprise environments, covering the entire process from data preparation to model fine-tuning and evaluation. By adapting the embeddings to better suit the retrieval tasks prevalent in enterprises, we aim to enhance the performance of information retrieval solutions. We discuss the process of fine-tuning, its effect on retrieval accuracy, and the potential benefits for enterprise information management. Our findings demonstrate the efficacy of fine-tuned embedding models in improving the precision and relevance of search results in enterprise settings.
Authors: Bettina Fazzinga, Elena Palmieri, Margherita Vestoso, Luca Bolognini, Andrea Galassi, Filippo Furfaro, Paolo Torroni
Abstract: We present ACME: A Chatbot for asylum-seeking Migrants in Europe. ACME relies on computational argumentation and aims to help migrants identify the highest level of protection they can apply for. This would contribute to a more sustainable migration by reducing the load on territorial commissions, Courts, and humanitarian organizations supporting asylum applicants. We describe the background context, system architecture, underlying technologies, and a case study used to validate the tool with domain experts.
Authors: Suvajit Patra, Arkadip Maitra, Megha Tiwari, K. Kumaran, Swathy Prabhu, Swami Punyeshwarananda, Soumitra Samanta
Abstract: Automatic Sign Language (SL) recognition is an important task in the computer vision community. To build a robust SL recognition system, we need a considerable amount of data which is lacking particularly in Indian sign language (ISL). In this paper, we introduce a large-scale isolated ISL dataset and a novel SL recognition model based on skeleton graph structure. The dataset covers 2002 daily used common words in the deaf community recorded by 20 (10 male and 10 female) deaf adult signers (contains 40033 videos). We propose a SL recognition model namely Hierarchical Windowed Graph Attention Network (HWGAT) by utilizing the human upper body skeleton graph. The HWGAT tries to capture distinctive motions by giving attention to different body parts induced by the human skeleton graph. The utility of the proposed dataset and the usefulness of our model are evaluated through extensive experiments. We pre-trained the proposed model on the presented dataset and fine-tuned it across different sign language datasets further boosting the performance of 1.10, 0.46, 0.78, and 6.84 percentage points on INCLUDE, LSA64, AUTSL and WLASL respectively compared to the existing state-of-the-art keypoints-based models.
Authors: T\'eo Guichoux, Laure Soulier, Nicolas Obin, Catherine Pelachaud
Abstract: Co-speech gestures are fundamental for communication. The advent of recent deep learning techniques has facilitated the creation of lifelike, synchronous co-speech gestures for Embodied Conversational Agents. "In-the-wild" datasets, aggregating video content from platforms like YouTube via human pose detection technologies, provide a feasible solution by offering 2D skeletal sequences aligned with speech. Concurrent developments in lifting models enable the conversion of these 2D sequences into 3D gesture databases. However, it is important to note that the 3D poses estimated from the 2D extracted poses are, in essence, approximations of the ground-truth, which remains in the 2D domain. This distinction raises questions about the impact of gesture representation dimensionality on the quality of generated motions - a topic that, to our knowledge, remains largely unexplored. Our study examines the effect of using either 2D or 3D joint coordinates as training data on the performance of speech-to-gesture deep generative models. We employ a lifting model for converting generated 2D pose sequences into 3D and assess how gestures created directly in 3D stack up against those initially generated in 2D and then converted to 3D. We perform an objective evaluation using widely used metrics in the gesture generation field as well as a user study to qualitatively evaluate the different approaches.
Authors: Zhanglin Wu, Yuanchang Luo, Daimeng Wei, Jiawei Zheng, Bin Wei, Zongyao Li, Hengchao Shang, Jiaxin Guo, Shaojun Li, Weidong Zhang, Ning Xie, Hao Yang
Abstract: This paper presents the submission of Huawei Translation Services Center (HW-TSC) to machine translation tasks of the 20th China Conference on Machine Translation (CCMT 2024). We participate in the bilingual machine translation task and multi-domain machine translation task. For these two translation tasks, we use training strategies such as regularized dropout, bidirectional training, data diversification, forward translation, back translation, alternated training, curriculum learning, and transductive ensemble learning to train neural machine translation (NMT) models based on the deep Transformer-big architecture. Furthermore, to explore whether large language model (LLM) can help improve the translation quality of NMT systems, we use supervised fine-tuning to train llama2-13b as an Automatic post-editing (APE) model to improve the translation results of the NMT model on the multi-domain machine translation task. By using these plyometric strategies, our submission achieves a competitive result in the final evaluation.
Authors: Yuzi Yan, Xingzhou Lou, Jialian Li, Yiping Zhang, Jian Xie, Chao Yu, Yu Wang, Dong Yan, Yuan Shen
Abstract: As Large Language Models (LLMs) continue to progress toward more advanced forms of intelligence, Reinforcement Learning from Human Feedback (RLHF) is increasingly seen as a key pathway toward achieving Artificial General Intelligence (AGI). However, the reliance on reward-model-based (RM-based) alignment methods introduces significant challenges due to the inherent instability and imperfections of Reward Models (RMs), which can lead to critical issues such as reward hacking and misalignment with human intentions. In this paper, we introduce a reward-robust RLHF framework aimed at addressing these fundamental challenges, paving the way for more reliable and resilient learning in LLMs. Our approach introduces a novel optimization objective that carefully balances performance and robustness by incorporating Bayesian Reward Model Ensembles (BRME) to model the uncertainty set of reward functions. This allows the framework to integrate both nominal performance and minimum reward signals, ensuring more stable learning even with imperfect RMs. Empirical results demonstrate that our framework consistently outperforms baselines across diverse benchmarks, showing improved accuracy and long-term stability. We also provide a theoretical analysis, demonstrating that reward-robust RLHF approaches the stability of constant reward settings, which proves to be acceptable even in a stochastic-case analysis. Together, these contributions highlight the framework potential to enhance both the performance and stability of LLM alignment.
Authors: Yuanchao Li, Azalea Gui, Dimitra Emmanouilidou, Hannes Gamper
Abstract: The subjective nature of music emotion introduces inherent bias in both recognition and generation, especially when relying on a single audio encoder, emotion classifier, or evaluation metric. In this work, we conduct a study on Music Emotion Recognition (MER) and Emotional Music Generation (EMG), employing diverse audio encoders alongside the Frechet Audio Distance (FAD), a reference-free evaluation metric. Our study begins with a benchmark evaluation of MER, highlighting the limitations associated with using a single audio encoder and the disparities observed across different measurements. We then propose assessing MER performance using FAD from multiple encoders to provide a more objective measure of music emotion. Furthermore, we introduce an enhanced EMG approach designed to improve both the variation and prominence of generated music emotion, thus enhancing realism. Additionally, we investigate the realism disparities between the emotions conveyed in real and synthetic music, comparing our EMG model against two baseline models. Experimental results underscore the emotion bias problem in both MER and EMG and demonstrate the potential of using FAD and diverse audio encoders to evaluate music emotion objectively.
Authors: Taowen Wang, Yiyang Liu, James Chenhao Liang, junhan zhao, Yiming Cui, Yuning Mao, Shaoliang Nie, Jiahao Liu, Fuli Feng, Zenglin Xu, Cheng Han, Lifu Huang, Qifan Wang, Dongfang Liu
Abstract: Multimodal Large Language Models (MLLMs) demonstrate remarkable performance across a wide range of domains, with increasing emphasis on enhancing their zero-shot generalization capabilities for unseen tasks across various modalities. Instruction tuning has emerged as an effective strategy for achieving zero-shot generalization by finetuning pretrained models on diverse multimodal tasks. As the scale of MLLMs continues to grow, parameter-efficient finetuning becomes increasingly critical. However, most existing parameter-efficient approaches focus only on single modalities and often overlook the multimodal characteristics during finetuning. In this work, we introduce a novel Multimodal Prompt Tuning (M$^2$PT) approach for efficient instruction tuning of MLLMs. M$^2$PT effectively integrates visual and textual prompts into the vision encoder and language processor respectively during finetuning, facilitating the extraction and alignment of features across modalities. Empirical results on various multimodal evaluation datasets demonstrate the superior performance of our approach compared to several state-of-the-art baselines. A comprehensive set of ablation studies validates the effectiveness of our prompt design and the efficiency of our approach.
Authors: Yuanchao Li, Zixing Zhang, Jing Han, Peter Bell, Catherine Lai
Abstract: The lack of labeled data is a common challenge in speech classification tasks, particularly those requiring extensive subjective assessment, such as cognitive state classification. In this work, we propose a Semi-Supervised Learning (SSL) framework, introducing a novel multi-view pseudo-labeling method that leverages both acoustic and linguistic characteristics to select the most confident data for training the classification model. Acoustically, unlabeled data are compared to labeled data using the Frechet audio distance, calculated from embeddings generated by multiple audio encoders. Linguistically, large language models are prompted to revise automatic speech recognition transcriptions and predict labels based on our proposed task-specific knowledge. High-confidence data are identified when pseudo-labels from both sources align, while mismatches are treated as low-confidence data. A bimodal classifier is then trained to iteratively label the low-confidence data until a predefined criterion is met. We evaluate our SSL framework on emotion recognition and dementia detection tasks. Experimental results demonstrate that our method achieves competitive performance compared to fully supervised learning using only 30% of the labeled data and significantly outperforms two selected baselines.
Authors: Nilanjan Sinhababu, Andrew Parry, Debasis Ganguly, Debasis Samanta, Pabitra Mitra
Abstract: A supervised ranking model, despite its advantage of being effective, usually involves complex processing - typically multiple stages of task-specific pre-training and fine-tuning. This has motivated researchers to explore simpler pipelines leveraging large language models (LLMs) that are capable of working in a zero-shot manner. However, since zero-shot inference does not make use of a training set of pairs of queries and their relevant documents, its performance is mostly worse than that of supervised models, which are trained on such example pairs. Motivated by the existing findings that training examples generally improve zero-shot performance, in our work, we explore if this also applies to ranking models. More specifically, given a query and a pair of documents, the preference prediction task is improved by augmenting examples of preferences for similar queries from a training set. Our proposed pairwise few-shot ranker demonstrates consistent improvements over the zero-shot baseline on both in-domain (TREC DL) and out-domain (BEIR subset) retrieval benchmarks. Our method also achieves a close performance to that of a supervised model without requiring any complex training pipeline.