Authors: Sujan Dutta, Deepak Pandita, Tharindu Cyril Weerasooriya, Marcos Zampieri, Christopher M. Homan, Ashiqur R. KhudaBukhsh
Abstract: Ensuring annotator quality in training and evaluation data is a key piece of machine learning in NLP. Tasks such as sentiment analysis and offensive speech detection are intrinsically subjective, creating a challenging scenario for traditional quality assessment approaches because it is hard to distinguish disagreement due to poor work from that due to differences of opinions between sincere annotators. With the goal of increasing diverse perspectives in annotation while ensuring consistency, we propose \texttt{ARTICLE}, an in-context learning (ICL) framework to estimate annotation quality through self-consistency. We evaluate this framework on two offensive speech datasets using multiple LLMs and compare its performance with traditional methods. Our findings indicate that \texttt{ARTICLE} can be used as a robust method for identifying reliable annotators, hence improving data quality.
Authors: Muhammad Asif Ali, Nawal Daftardar, Mutayyaba Waheed, Jianbin Qin, Di Wang
Abstract: Large Language Models (LLMs) have demonstrated significant capabilities across numerous application domains. A key challenge is to keep these models updated with latest available information, which limits the true potential of these models for the end-applications. Although, there have been numerous attempts for LLMs Knowledge Editing (KE), i.e., to edit the LLMs prior knowledge and in turn test it via Multi-hop Question Answering (MQA), yet so far these studies are primarily focused on English language. To bridge this gap, in this paper we propose: Multi-hop Questioning Answering under Knowledge Editing for Arabic Language (MQA-KEAL). MQA-KEAL stores knowledge edits as structured knowledge units in the external memory. In order to solve multi-hop question, it first uses task-decomposition to decompose the question into smaller sub-problems. Later for each sub-problem, it iteratively queries the external memory and/or target LLM in order to generate the final response. In addition, we also contribute MQUAKE-AR (Arabic translation of English benchmark MQUAKE), as well as a new benchmark MQA-AEVAL for rigorous performance evaluation of MQA under KE for Arabic language. Experimentation evaluation reveals MQA-KEAL outperforms the baseline models by a significant margin.
Authors: Kaige Xie, Ian Yang, John Gunerli, Mark Riedl
Abstract: World models, which encapsulate the dynamics of how actions affect environments, are foundational to the functioning of intelligent agents. In this work, we explore the potential of Large Language Models (LLMs) to operate as world models. Although LLMs are not inherently designed to model real-world dynamics, we show that they can be induced to perform two critical world model functions: determining the applicability of an action based on a given world state, and predicting the resulting world state upon action execution. This is achieved by fine-tuning two separate LLMs-one for precondition prediction and another for effect prediction-while leveraging synthetic data generation techniques. Through human-participant studies, we validate that the precondition and effect knowledge generated by our models aligns with human understanding of world dynamics. We also analyze the extent to which the world model trained on our synthetic data results in an inferred state space that supports the creation of action chains, a necessary property for planning.
Authors: Wei-Cheng Tseng, Yi-Jen Shih, David Harwath, Raymond Mooney
Abstract: Audio-visual pre-trained models have gained substantial attention recently and demonstrated superior performance on various audio-visual tasks. This study investigates whether pre-trained audio-visual models demonstrate non-arbitrary associations between sounds and visual representations$\unicode{x2013}$known as sound symbolism$\unicode{x2013}$which is also observed in humans. We developed a specialized dataset with synthesized images and audio samples and assessed these models using a non-parametric approach in a zero-shot setting. Our findings reveal a significant correlation between the models' outputs and established patterns of sound symbolism, particularly in models trained on speech data. These results suggest that such models can capture sound-meaning connections akin to human language processing, providing insights into both cognitive architectures and machine learning strategies.
Authors: Bumjun Kim, Kunha Lee, Juyeon Kim, Sangam Lee
Abstract: Chain-of-Thought (CoT) reasoning has enabled Large Language Model (LLM) to achieve remarkable performance in various NLP tasks, including arithmetic problem-solving. However, this success does not generalize to small language model (sLM) like T5, due to their limited capacity and absence of emergent abilities associated with larger models. Recent works to enhance sLM through knowledge distillation have yielded some improvements but still face significant limitations, particularly high ambiguity from the variability in natural language expressions and substantial computational costs. In this paper, we investigate why sLM perform poorly on arithmetic reasoning tasks and hypothesize that natural language format variability introduces high ambiguity for these smaller models. Based on this hypothesis, we conduct experiments with equation-only format, which is a reasoning format that unifies arithmetic reasoning previously expressed in natural language formats into mathematical equations. Experiment results demonstrate that equation-only format effectively boosts the arithmetic reasoning abilities of sLM, especially in very small models like T5-Tiny.
Authors: Jinchuan Tian, Chunlei Zhang, Jiatong Shi, Hao Zhang, Jianwei Yu, Shinji Watanabe, Dong Yu
Abstract: Recent advancements in text-to-speech (TTS) have shown that language model (LM)-based systems offer competitive performance to their counterparts. Further optimization can be achieved through preference alignment algorithms, which adjust LMs to align with the preferences of reward models, enhancing the desirability of the generated content. This study presents a thorough empirical evaluation of how preference alignment algorithms, particularly Direct Preference Optimization (DPO), enhance LM-based TTS. With a 1.15B parameter LM-based TTS model, we demonstrate that preference alignment consistently improves intelligibility, speaker similarity, and proxy subjective evaluation scores, with the latter two metrics surpassing even human speech in certain evaluations. We also show preference alignment is applicable to low-resource scenarios and effectively generalized to out-of-domain applications.
Authors: Fan Qian, Jiqing Han, Jianchen Li, Yongjun He, Tieran Zheng, Guibin Zheng
Abstract: The key challenge in unaligned multimodal language sequences lies in effectively integrating information from various modalities to obtain a refined multimodal joint representation. Recently, the disentangle and fuse methods have achieved the promising performance by explicitly learning modality-agnostic and modality-specific representations and then fusing them into a multimodal joint representation. However, these methods often independently learn modality-agnostic representations for each modality and utilize orthogonal constraints to reduce linear correlations between modality-agnostic and modality-specific representations, neglecting to eliminate their nonlinear correlations. As a result, the obtained multimodal joint representation usually suffers from information redundancy, leading to overfitting and poor generalization of the models. In this paper, we propose a Mutual Information-based Representations Disentanglement (MIRD) method for unaligned multimodal language sequences, in which a novel disentanglement framework is designed to jointly learn a single modality-agnostic representation. In addition, the mutual information minimization constraint is employed to ensure superior disentanglement of representations, thereby eliminating information redundancy within the multimodal joint representation. Furthermore, the challenge of estimating mutual information caused by the limited labeled data is mitigated by introducing unlabeled data. Meanwhile, the unlabeled data also help to characterize the underlying structure of multimodal data, consequently further preventing overfitting and enhancing the performance of the models. Experimental results on several widely used benchmark datasets validate the effectiveness of our proposed approach.
Authors: Chen Liang, Zhifan Feng, Zihe Liu, Wenbin Jiang, Jinan Xu, Yufeng Chen, Yong Wang
Abstract: Chain-of-thought prompting significantly boosts the reasoning ability of large language models but still faces three issues: hallucination problem, restricted interpretability, and uncontrollable generation. To address these challenges, we present AgentCOT, a llm-based autonomous agent framework, which can solve complex problems in an agent-style manner by multiple round LLM generation. At each step, AgentCOT selects an action and executes it to yield an intermediate result with supporting evidence. In addition, we integrate the step's index into the reasoning process to form a graph structure for complex inference logic. We introduce two new strategies to enhance the performance of AgentCOT.We conduct extensive experiments to verify the effectiveness of our method on six common benchmarks. Results exhibit that our method brings in substantial improvements over current competitive approaches.
Authors: Chaoqun Liu, Qin Chao, Wenxuan Zhang, Xiaobao Wu, Boyang Li, Anh Tuan Luu, Lidong Bing
Abstract: Large Language Models (LLMs) have demonstrated remarkable performance through supervised fine-tuning or in-context learning using gold labels. However, this paradigm is limited by the availability of gold labels, while in certain scenarios, LLMs may need to perform tasks that are too complex for humans to provide such labels. To tackle this challenge, this study explores whether solely utilizing unlabeled data can elicit strong model capabilities. We propose a new paradigm termed zero-to-strong generalization. We iteratively prompt LLMs to annotate unlabeled data and retain high-quality labels by filtering. Surprisingly, we obverse that this iterative process gradually unlocks LLMs' potential on downstream tasks. Our experiments on extensive classification and reasoning tasks confirm the effectiveness of our proposed framework. Our analysis indicates that this paradigm is effective for both in-context learning and fine-tuning, and for various model sizes.
Authors: Xinyu Zhou, Delong Chen, Samuel Cahyawijaya, Xufeng Duan, Zhenguang G. Cai
Abstract: We introduce a novel analysis that leverages linguistic minimal pairs to probe the internal linguistic representations of Large Language Models (LLMs). By measuring the similarity between LLM activation differences across minimal pairs, we quantify the and gain insight into the linguistic knowledge captured by LLMs. Our large-scale experiments, spanning 100+ LLMs and 150k minimal pairs in three languages, reveal properties of linguistic similarity from four key aspects: consistency across LLMs, relation to theoretical categorizations, dependency to semantic context, and cross-lingual alignment of relevant phenomena. Our findings suggest that 1) linguistic similarity is significantly influenced by training data exposure, leading to higher cross-LLM agreement in higher-resource languages. 2) Linguistic similarity strongly aligns with fine-grained theoretical linguistic categories but weakly with broader ones. 3) Linguistic similarity shows a weak correlation with semantic similarity, showing its context-dependent nature. 4) LLMs exhibit limited cross-lingual alignment in their understanding of relevant linguistic phenomena. This work demonstrates the potential of minimal pairs as a window into the neural representations of language in LLMs, shedding light on the relationship between LLMs and linguistic theory.
Authors: Jiaming Zhou, Abbas Ghaddar, Ge Zhang, Liheng Ma, Yaochen Hu, Soumyasundar Pal, Mark Coates, Bin Wang, Yingxue Zhang, Jianye Hao
Abstract: Despite recent advances in training and prompting strategies for Large Language Models (LLMs), these models continue to face challenges with complex logical reasoning tasks that involve long reasoning chains. In this work, we explore the potential and limitations of using graph-based synthetic reasoning data as training signals to enhance LLMs' reasoning capabilities. Our extensive experiments, conducted on two established natural language reasoning tasks -- inductive reasoning and spatial reasoning -- demonstrate that supervised fine-tuning (SFT) with synthetic graph-based reasoning data effectively enhances LLMs' reasoning performance without compromising their effectiveness on other standard evaluation benchmarks.
Authors: Xin Lian, Nishant Baglodi, Christopher J. MacLellan
Abstract: This paper introduces Cobweb4L, a novel approach for efficient language model learning that supports masked word prediction. The approach builds on Cobweb, an incremental system that learns a hierarchy of probabilistic concepts. Each concept stores the frequencies of words that appear in instances tagged with that concept label. The system utilizes an attribute value representation to encode words and their surrounding context into instances. Cobweb4L uses the information theoretic variant of category utility and a new performance mechanism that leverages multiple concepts to generate predictions. We demonstrate that with these extensions it significantly outperforms prior Cobweb performance mechanisms that use only a single node to generate predictions. Further, we demonstrate that Cobweb4L learns rapidly and achieves performance comparable to and even superior to Word2Vec. Next, we show that Cobweb4L and Word2Vec outperform BERT in the same task with less training data. Finally, we discuss future work to make our conclusions more robust and inclusive.
Authors: Jiaxin Wen, Jian Guan, Hongning Wang, Wei Wu, Minlie Huang
Abstract: Despite the remarkable success of large language models (LLMs) on traditional natural language processing tasks, their planning ability remains a critical bottleneck in tackling complex multi-step reasoning tasks. Existing approaches mainly rely on prompting or task-specific fine-tuning, often suffering from weak robustness and cross-task generalization. To address the limitation, we introduce CODEPLAN, a scalable paradigm that empowers LLMs to generate and follow code-form plans pseudocode that outlines high-level, structured reasoning processes. By leveraging the structured and versatile nature of code, CODEPLAN effectively captures the rich semantics and control flows inherent to sophisticated reasoning. Importantly, CODEPLAN allows the automatic extraction of code-form plans from massive, wide-ranging text corpora without the need for curated, task-specific datasets. This enables it to scale up efficiently and improve reasoning capabilities across diverse scenarios. To train CODEPLAN, we construct a large-scale dataset of 2M examples that integrate code-form plans with standard prompt-response pairs from existing corpora. With minimal computation overhead during both training and inference, CODEPLAN achieves a 25.1% relative improvement compared with directly generating responses, averaged across 13 challenging multi-step reasoning benchmarks, spanning mathematical reasoning, symbolic reasoning, instruction-following, multi-hop QA, and decision-making tasks. Further analysis reveals CODEPLAN's increasing performance gains on more complex reasoning tasks, as well as significant data efficiency thanks to its generalization ability.
Authors: Dongwon Jung, Qin Liu, Tenghao Huang, Ben Zhou, Muhao Chen
Abstract: Retrieval Augmented Generation (RAG) improves large language models (LMs) by incorporating non-parametric knowledge through evidence retrieval from external sources. However, it often struggles to filter out inconsistent and irrelevant information that can distract the LM from its tasks. While compressing the retrieved evidence with a compression model aims to address this issue, the compressed evidence may still be unfamiliar to the target model used for downstream task, potentially failing to utilize the evidence effectively. We propose FaviComp (Familiarity-aware Evidence Compression), a novel training-free evidence compression technique that makes retrieved evidence more familiar to the target model, while seamlessly integrating parametric knowledge from the model. Specifically, FaviComp proactively lowers the perplexity of the compressed evidence with regard to the target model by combining token probabilities from both the compression model and the target model to generate context that is more familiar to the target model. This approach balances the integration of parametric and non-parametric knowledge, which is especially helpful in complex tasks where the retrieved evidence set may not contain all the necessary information. Experimental results demonstrate that FaviComp consistently outperforms existing baselines in multiple open-domain QA datasets, achieving high compression rates and showcasing the effective integration of both parametric and non-parametric knowledge.
Authors: Ahmet G\"und\"uz, Yunsu Kim, Kamer Ali Yuksel, Mohamed Al-Badrashiny, Thiago Castro Ferreira, Hassan Sawaf
Abstract: We present AutoMode-ASR, a novel framework that effectively integrates multiple ASR systems to enhance the overall transcription quality while optimizing cost. The idea is to train a decision model to select the optimal ASR system for each segment based solely on the audio input before running the systems. We achieve this by ensembling binary classifiers determining the preference between two systems. These classifiers are equipped with various features, such as audio embeddings, quality estimation, and signal properties. Additionally, we demonstrate how using a quality estimator can further improve performance with minimal cost increase. Experimental results show a relative reduction in WER of 16.2%, a cost saving of 65%, and a speed improvement of 75%, compared to using a single-best model for all segments. Our framework is compatible with commercial and open-source black-box ASR systems as it does not require changes in model codes.
Authors: Junlin Lv, Yuan Feng, Xike Xie, Xin Jia, Qirong Peng, Guiming Xie
Abstract: Large language models have achieved notable success across various domains, yet efficient inference is still limited by the quadratic computation complexity of the attention mechanism. The inference consists of prefilling and decoding phases. Although several attempts have been made to accelerate decoding, the inefficiency of the prefilling phase, especially for long-context tasks, remains a challenge. In this paper, we observe a locality in query criticality during the prefilling phase of long-context processing: adjacent query tokens tend to focus on similar subsets of the past Key-Value (KV) cache. Based on this observation, we propose CritiPrefill, a criticality-based segment-wise prefilling method. This method partitions the input sequence's queries and KV cache into segments and blocks, utilizing a segment-wise algorithm to estimate the query criticality. By pruning non-critical computations between query segments and cache blocks in the self-attention mechanism, the prefilling process can be significantly accelerated. Extensive evaluations on multiple long-context datasets show up to 2.7x speedup on Llama3-8B and 3.0x speedup on Yi-9B for 128K context length on a single A100 GPU, with minimal quality degradation.
Authors: Dongheng Li, Yongchang Hao, Lili Mou
Abstract: Large language models have become increasingly popular and demonstrated remarkable performance in various natural language processing (NLP) tasks. However, these models are typically computationally expensive and difficult to be deployed in resource-constrained environments. In this paper, we propose LLMR, a novel knowledge distillation (KD) method based on a reward function induced from large language models. We conducted experiments on multiple datasets in the dialogue generation and summarization tasks. Empirical results demonstrate that our LLMR approach consistently outperforms traditional KD methods in different tasks and datasets.
Authors: Jun Rao, Xuebo Liu, Zepeng Lin, Liang Ding, Jing Li, Dacheng Tao
Abstract: Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. The success of KD in auto-regressive language models mainly relies on Reverse KL for mode-seeking and student-generated output (SGO) to combat exposure bias. Our theoretical analyses and experimental validation reveal that while Reverse KL effectively mimics certain features of the teacher distribution, it fails to capture most of its behaviors. Conversely, SGO incurs higher computational costs and presents challenges in optimization, particularly when the student model is significantly smaller than the teacher model. These constraints are primarily due to the immutable distribution of the teacher model, which fails to adjust adaptively to models of varying sizes. We introduce Online Knowledge Distillation (OKD), where the teacher network integrates small online modules to concurrently train with the student model. This strategy abolishes the necessity for on-policy sampling and merely requires minimal updates to the parameters of the teacher's online module during training, thereby allowing dynamic adaptation to the student's distribution to make distillation better. Extensive results across multiple generation datasets show that OKD achieves or exceeds the performance of leading methods in various model architectures and sizes, reducing training time by up to fourfold.
Authors: Ryuichi Sumida, Koji Inoue, Tatsuya Kawahara
Abstract: While Retrieval-Augmented Generation (RAG) has shown promise in enhancing long-term conversations, the increasing memory load as conversations progress degrades retrieval accuracy. Drawing on psychological insights, we propose LUFY, a simple yet effective method that focuses on emotionally arousing memories and retains less than 10% of the conversation. In the user experiment, participants interacted with three types of RAG chatbots, each for 2 hours over 4 sessions, marking the most extensive assessment of a chatbot's long-term capabilities to date -- more than four times longer than any existing benchmark. The results demonstrate that prioritizing arousing memories while forgetting the majority of the conversation significantly enhances user experience. This study pushes the frontier of long-term conversations and highlights the importance of forgetting unimportant parts of conversations. Code and Dataset: https://github.com/ryuichi-sumida/LUFY
Authors: Chin-Po Chen, Jeng-Lin Li
Abstract: Alzheimer's disease (AD) stands as the predominant cause of dementia, characterized by a gradual decline in speech and language capabilities. Recent deep-learning advancements have facilitated automated AD detection through spontaneous speech. However, common transcript-based detection methods directly model text patterns in each utterance without a global view of the patient's linguistic characteristics, resulting in limited discriminability and interpretability. Despite the enhanced reasoning abilities of large language models (LLMs), there remains a gap in fully harnessing the reasoning ability to facilitate AD detection and model interpretation. Therefore, we propose a patient-level transcript profiling framework leveraging LLM-based reasoning augmentation to systematically elicit linguistic deficit attributes. The summarized embeddings of the attributes are integrated into an Albert model for AD detection. The framework achieves 8.51\% ACC and 8.34\% F1 improvements on the ADReSS dataset compared to the baseline without reasoning augmentation. Our further analysis shows the effectiveness of our identified linguistic deficit attributes and the potential to use LLM for AD detection interpretation.
Authors: Tianyu Peng, Jiajun Zhang
Abstract: Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs causes difficulties for student models to learn. In this paper, we first demonstrate the importance of multi-modal distribution alignment with experiments and then highlight the inefficiency of existing KD approaches in learning multi-modal distributions. To address this problem, we propose Ranking Loss based Knowledge Distillation (RLKD), which encourages the consistency of the ranking of peak predictions between the teacher and student models. By incorporating word-level ranking loss, we ensure excellent compatibility with existing distillation objectives while fully leveraging the fine-grained information between different categories in peaks of two predicted distribution. Experimental results demonstrate that our method enables the student model to better learn the multi-modal distributions of the teacher model, leading to a significant performance improvement in various downstream tasks.
Authors: Tzu-Lin Kuo, Feng-Ting Liao, Mu-Wei Hsieh, Fu-Chieh Chang, Po-Chun Hsu, Da-Shan Shiu
Abstract: In real-world applications with Large Language Models (LLMs), external retrieval mechanisms - such as Search-Augmented Generation (SAG), tool utilization, and Retrieval-Augmented Generation (RAG) - are often employed to enhance the quality of augmented generations in dialogues. These approaches often come with multi-turn dialogue, where each interaction is enriched by relevant information retrieved from external sources. Existing benchmarks either assess LLMs' chat abilities in multi-turn dialogues or their use of retrieval for augmented responses in single-turn settings. However, there is a gap in evaluating LLMs' ability to leverage retrieval for more precise responses across multiple turns. To address this limitation, we introduce RAD-Bench (Retrieval Augmented Dialogue), a benchmark designed to evaluate LLMs' capabilities in multi-turn dialogues following retrievals, essential for their deployment in context-rich applications. RAD-Bench evaluates two key abilities of LLMs: Retrieval Synthesis and Retrieval Reasoning. These are measured using discriminative questions and retrieved contexts, and corresponding reference answers, assessing how effectively LLMs integrate and reason with context to maintain and enhance conversation quality over multiple turns. Our evaluation results on commonly used LLMs reveal that model performance deteriorates as additional layers of conditions or constraints are applied across conversation turns, even when accurate retrieved contexts are provided.
Authors: Mohamad Ballout, Ulf Krumnack, Gunther Heidemann, Kai-Uwe K\"uhnberger
Abstract: Enhancing small language models for real-life application deployment is a significant challenge facing the research community. Due to the difficulties and costs of using large language models, researchers are seeking ways to effectively deploy task-specific small models. In this work, we introduce a simple yet effective knowledge distillation method to improve the performance of small language models. Our approach utilizes a teacher model with approximately 3 billion parameters to identify the most influential tokens in its decision-making process. These tokens are extracted from the input based on their attribution scores relative to the output, using methods like saliency maps. These important tokens are then provided as rationales to a student model, aiming to distill the knowledge of the teacher model. This method has proven to be effective, as demonstrated by testing it on four diverse datasets, where it shows improvement over both standard fine-tuning methods and state-of-the-art knowledge distillation models. Furthermore, we explore explanations of the success of the model by analyzing the important tokens extracted from the teacher model. Our findings reveal that in 68\% of cases, specifically in datasets where labels are part of the answer, such as multiple-choice questions, the extracted tokens are part of the ground truth.
Authors: Tom Pieper, Mohamad Ballout, Ulf Krumnack, Gunther Heidemann, Kai-Uwe K\"uhnberger
Abstract: This paper explores the enhancement of small language models through strategic dataset augmentation via ChatGPT-3.5-Turbo, in the domain of Natural Language Inference (NLI). By employing knowledge distillation-based techniques and synthetic dataset augmentation, we aim to bridge the performance gap between large language models (LLMs) and small language models (SLMs) without the immense cost of human annotation. Our methods involve two forms of rationale generation--information extraction and informed reasoning--to enrich the ANLI dataset. We then fine-tune T5-Small on these augmented datasets, evaluating its performance against an established benchmark. Our findings reveal that the incorporation of synthetic rationales significantly improves the model's ability to comprehend natural language, leading to 1.3\% and 2.3\% higher classification accuracy, respectively, on the ANLI dataset, demonstrating the potential of leveraging LLMs for dataset augmentation. This approach not only enhances the performance of smaller models on complex tasks but also introduces a cost-effective method for fine-tuning smaller language models. By advancing our understanding of knowledge distillation and fine-tuning strategies, this work contributes to the ongoing effort to create more capable and efficient NLP systems.
Authors: Santosh Kumar Radha, Yasamin Nouri Jelyani, Ara Ghukasyan, Oktay Goktas
Abstract: Iterative human engagement is a common and effective means of leveraging the advanced language processing power of large language models (LLMs). Using well-structured prompts in a conversational manner, human users can effectively influence an LLM to develop more thoughtful and accurate responses. Motivated by this insight, we propose the Iteration of Thought (IoT) framework for enhancing LLM responses by generating "thought"-provoking prompts vis a vis an input query and the current iteration of an LLM's response. Unlike static or semi-static approaches, e.g. Chain of Thought (CoT) or Tree of Thoughts (ToT), IoT adapts its reasoning path dynamically, based on evolving context, and without generating alternate explorative thoughts which are ultimately discarded. The three components of the IoT framework are (1) an Inner Dialogue Agent (IDA) responsible for generating instructive, context-specific prompts; (2) an LLM Agent (LLMA) that processes these prompts to refine its responses; and (3) an iterative prompting loop that implements a conversation between the former two components. We introduce two variants of our framework: Autonomous Iteration of Thought (AIoT), where an LLM decides when to stop iterating, and Guided Iteration of Thought (GIoT), which always forces a fixed number iterations. We investigate the performance of IoT across various datasets, spanning complex reasoning tasks from the GPQA dataset, explorative problem-solving in Game of 24, puzzle solving in Mini Crosswords, and multi-hop question answering from the HotpotQA dataset. Our results show that IoT represents a viable paradigm for autonomous response refinement in LLMs, showcasing significant improvements over CoT and thereby enabling more adaptive and efficient reasoning systems that minimize human intervention.
Authors: Zhaozhi Qian, Faroq Altam, Muhammad Saleh Saeed Alqurishi, Riad Souissi
Abstract: Large Language Models (LLMs) are the cornerstones of modern artificial intelligence systems. This paper introduces Juhaina, a Arabic-English bilingual LLM specifically designed to align with the values and preferences of Arabic speakers. Juhaina inherently supports advanced functionalities such as instruction following, open-ended question answering, information provisioning, and text processing. Our model contains 9.24 billion parameters and is trained on a context window of up to 8,192 tokens. This paper details the creation process of Juhaina and provides an extensive empirical evaluation. Furthermore, we identify the limitations of widely-adopted Open Arabic LLM Leaderboard (OALL) and propose a new evaluation benchmark, CamelEval. Our findings demonstrate that Juhaina surpasses existing LLMs of comparable sizes, such as the Llama and Gemma families, in generating helpful responses in Arabic, providing factually accurate information about the region, and understanding nuanced cultural aspects. We aspire for Juhaina to democratize cutting-edge AI technologies, serving over 400 million Arabic speakers by offering LLMs that not only communicate in their language but also comprehend their culture. We publicly release all models on Huggingface \url{https://huggingface.co/elmrc}.
Authors: Kiran Vodrahalli, Santiago Ontanon, Nilesh Tripuraneni, Kelvin Xu, Sanil Jain, Rakesh Shivanna, Jeffrey Hui, Nishanth Dikkala, Mehran Kazemi, Bahare Fatemi, Rohan Anil, Ethan Dyer, Siamak Shakeri, Roopali Vij, Harsh Mehta, Vinay Ramasesh, Quoc Le, Ed Chi, Yifeng Lu, Orhan Firat, Angeliki Lazaridou, Jean-Baptiste Lespiau, Nithya Attaluri, Kate Olszewska
Abstract: We introduce Michelangelo: a minimal, synthetic, and unleaked long-context reasoning evaluation for large language models which is also easy to automatically score. This evaluation is derived via a novel, unifying framework for evaluations over arbitrarily long contexts which measure the model's ability to do more than retrieve a single piece of information from its context. The central idea of the \frameworkname framework (\frameworkshort) is to construct tasks which require a model to ``chisel away'' the irrelevant information in the context, revealing a latent structure in the context. To verify a model's understanding of this latent structure, we query the model for details of the structure. Using \frameworkshort, we produce three diagnostic long-context evaluations across code and natural-language domains intended to provide a stronger signal of long-context language model capabilities. We perform evaluations on several state-of-the-art models and demonstrate both that a) the proposed evaluations are high-signal and b) that there is significant room for improvement in synthesizing long-context information.
Authors: Furkan \c{S}ahinu\c{c}, Thy Thy Tran, Yulia Grishina, Yufang Hou, Bei Chen, Iryna Gurevych
Abstract: Scientific leaderboards are standardized ranking systems that facilitate evaluating and comparing competitive methods. Typically, a leaderboard is defined by a task, dataset, and evaluation metric (TDM) triple, allowing objective performance assessment and fostering innovation through benchmarking. However, the exponential increase in publications has made it infeasible to construct and maintain these leaderboards manually. Automatic leaderboard construction has emerged as a solution to reduce manual labor. Existing datasets for this task are based on the community-contributed leaderboards without additional curation. Our analysis shows that a large portion of these leaderboards are incomplete, and some of them contain incorrect information. In this work, we present SciLead, a manually-curated Scientific Leaderboard dataset that overcomes the aforementioned problems. Building on this dataset, we propose three experimental settings that simulate real-world scenarios where TDM triples are fully defined, partially defined, or undefined during leaderboard construction. While previous research has only explored the first setting, the latter two are more representative of real-world applications. To address these diverse settings, we develop a comprehensive LLM-based framework for constructing leaderboards. Our experiments and analysis reveal that various LLMs often correctly identify TDM triples while struggling to extract result values from publications. We make our code and data publicly available.
Authors: ALEJANDRO BUITRAGO LOPEZ, Javier Pastor-Galindo, Jos\'e Antonio Ruip\'erez-Valiente
Abstract: In the digital era, the internet and social media have transformed communication but have also facilitated the spread of hate speech and disinformation, leading to radicalization, polarization, and toxicity. This is especially concerning for media outlets due to their significant role in shaping public discourse. This study examines the topics, sentiments, and hate prevalence in 337,807 response messages (website comments and tweets) to news from five Spanish media outlets (La Vanguardia, ABC, El Pa\'is, El Mundo, and 20 Minutos) in January 2021. These public reactions were originally labeled as distinct types of hate by experts following an original procedure, and they are now classified into three sentiment values (negative, neutral, or positive) and main topics. The BERTopic unsupervised framework was used to extract 81 topics, manually named with the help of Large Language Models (LLMs) and grouped into nine primary categories. Results show social issues (22.22%), expressions and slang (20.35%), and political issues (11.80%) as the most discussed. Content is mainly negative (62.7%) and neutral (28.57%), with low positivity (8.73%). Toxic narratives relate to conversation expressions, gender, feminism, and COVID-19. Despite low levels of hate speech (3.98%), the study confirms high toxicity in online responses to social and political topics.
Authors: Hikaru Asano, Ryo Yonetani, Taiki Sekii, Hiroki Ouchi
Abstract: This paper presents Text2Traj2Text, a novel learning-by-synthesis framework for captioning possible contexts behind shopper's trajectory data in retail stores. Our work will impact various retail applications that need better customer understanding, such as targeted advertising and inventory management. The key idea is leveraging large language models to synthesize a diverse and realistic collection of contextual captions as well as the corresponding movement trajectories on a store map. Despite learned from fully synthesized data, the captioning model can generalize well to trajectories/captions created by real human subjects. Our systematic evaluation confirmed the effectiveness of the proposed framework over competitive approaches in terms of ROUGE and BERT Score metrics.
Authors: Aditya Joshi, Diptesh Kanojia, Heather Lent, Hour Kaing, Haiyue Song
Abstract: Despite excellent results on benchmarks over a small subset of languages, large language models struggle to process text from languages situated in `lower-resource' scenarios such as dialects/sociolects (national or social varieties of a language), Creoles (languages arising from linguistic contact between multiple languages) and other low-resource languages. This introductory tutorial will identify common challenges, approaches, and themes in natural language processing (NLP) research for confronting and overcoming the obstacles inherent to data-poor contexts. By connecting past ideas to the present field, this tutorial aims to ignite collaboration and cross-pollination between researchers working in these scenarios. Our notion of `lower-resource' broadly denotes the outstanding lack of data required for model training - and may be applied to scenarios apart from the three covered in the tutorial.
Authors: Kassem Sabeh, Mouna Kacimi, Johann Gamper, Robert Litschko, Barbara Plank
Abstract: Product attribute value identification (PAVI) involves automatically identifying attributes and their values from product information, enabling features like product search, recommendation, and comparison. Existing methods primarily rely on fine-tuning pre-trained language models, such as BART and T5, which require extensive task-specific training data and struggle to generalize to new attributes. This paper explores large language models (LLMs), such as LLaMA and Mistral, as data-efficient and robust alternatives for PAVI. We propose various strategies: comparing one-step and two-step prompt-based approaches in zero-shot settings and utilizing parametric and non-parametric knowledge through in-context learning examples. We also introduce a dense demonstration retriever based on a pre-trained T5 model and perform instruction fine-tuning to explicitly train LLMs on task-specific instructions. Extensive experiments on two product benchmarks show that our two-step approach significantly improves performance in zero-shot settings, and instruction fine-tuning further boosts performance when using training data, demonstrating the practical benefits of using LLMs for PAVI.
Authors: Yi Yang, Hanyu Duan, Jiaxin Liu, Kar Yan Tam
Abstract: The increasing use of text as data in social science research necessitates the development of valid, consistent, reproducible, and efficient methods for generating text-based concept measures. This paper presents a novel method that leverages the internal hidden states of large language models (LLMs) to generate these concept measures. Specifically, the proposed method learns a concept vector that captures how the LLM internally represents the target concept, then estimates the concept value for text data by projecting the text's LLM hidden states onto the concept vector. Three replication studies demonstrate the method's effectiveness in producing highly valid, consistent, and reproducible text-based measures across various social science research contexts, highlighting its potential as a valuable tool for the research community.
Authors: Jo\~ao Maria Janeiro, Benjamin Piwowarski, Patrick Gallinari, Lo\"ic Barrault
Abstract: Current pre-trained cross-lingual sentence encoders approaches use sentence-level objectives only. This can lead to loss of information, especially for tokens, which then degrades the sentence representation. We propose MEXMA, a novel approach that integrates both sentence-level and token-level objectives. The sentence representation in one language is used to predict masked tokens in another language, with both the sentence representation and all tokens directly updating the encoder. We show that adding token-level objectives greatly improves the sentence representation quality across several tasks. Our approach outperforms current pre-trained cross-lingual sentence encoders on bi-text mining as well as several downstream tasks. We also analyse the information encoded in our tokens, and how the sentence representation is built from them.
Authors: Peiyi Zhang, Yazhou Zhang, Bo Wang, Lu Rong, Jing Qin
Abstract: With the recent evolution of large language models (LLMs), concerns about aligning such models with human values have grown. Previous research has primarily focused on assessing LLMs' performance in terms of the Helpful, Honest, Harmless (3H) basic principles, while often overlooking their alignment with educational values in the Chinese context. To fill this gap, we present Edu-Values, the first Chinese education values evaluation benchmark designed to measure LLMs' alignment ability across seven dimensions: professional ideology, cultural literacy, educational knowledge and skills, education laws and regulations, teachers' professional ethics, basic competencies, and subject knowledge. We meticulously design and compile 1,418 questions, including multiple-choice, multi-modal question answering, subjective analysis, adversarial prompts, and questions on traditional Chinese culture. We conduct both human evaluation and automatic evaluation over 11 state-of-the-art (SoTA) LLMs, and highlight three main findings: (1) due to differences in educational culture, Chinese LLMs significantly outperform English LLMs, with Qwen 2 ranking the first with a score of 81.37; (2) LLMs perform well in subject knowledge and teaching skills but struggle with teachers' professional ethics and basic competencies; (3) LLMs excel at multiple-choice questions but perform poorly on subjective analysis and multi-modal tasks. This demonstrates the effectiveness and potential of the proposed benchmark. Our dataset is available at https://github.com/zhangpeii/Edu-Values.git.
Authors: Thomas Savage, Stephen Ma, Abdessalem Boukil, Vishwesh Patel, Ekanath Rangan, Ivan Rodriguez, Jonathan H Chen
Abstract: Large Language Model (LLM) fine tuning is underutilized in the field of medicine. Two of the most common methods of fine tuning are Supervised Fine Tuning (SFT) and Direct Parameter Optimization (DPO), but there is little guidance informing users when to use either technique. In this investigation, we compare the performance of SFT and DPO for five common natural language tasks in medicine: Classification with text data, Classification with numeric data, Clinical Reasoning, Summarization, and Clinical Triage. We find that SFT alone is sufficient for Classification with text data, whereas DPO improves performance for the more complex tasks of Clinical Reasoning, Summarization and Clinical Triage. Our results establish the role and importance of DPO fine tuning within medicine, and consequently call attention to current software gaps that prevent widespread deployment of this technique.
Authors: Eva S\'anchez Salido, Roser Morante, Julio Gonzalo, Guillermo Marco, Jorge Carrillo-de-Albornoz, Laura Plaza, Enrique Amig\'o, Andr\'es Fern\'andez, Alejandro Benito-Santos, Adri\'an Ghajari Espinosa, Victor Fresno
Abstract: In this article we present UNED-ACCESS 2024, a bilingual dataset that consists of 1003 multiple-choice questions of university entrance level exams in Spanish and English. Questions are originally formulated in Spanish and translated manually into English, and have not ever been publicly released. A selection of current open-source and proprietary models are evaluated in a uniform zero-shot experimental setting both on the UNED-ACCESS 2024 dataset and on an equivalent subset of MMLU questions. Results show that (i) reasoning questions are challenging for models, (ii) smaller models perform worse than larger models and degrade faster in Spanish than in English and (iii) the performance gap between languages is negligible for the best models and grows up to 37% for smaller models. Model ranking on UNED-ACCESS 2024 is almost identical in English and Spanish, and has also a high correlation (0.98 Pearson) with ranking on MMLU, suggesting that a small dataset is sufficiently diverse and representative to measure performance by discipline.
Authors: Jiaxin Wen, Ruiqi Zhong, Akbir Khan, Ethan Perez, Jacob Steinhardt, Minlie Huang, Samuel R. Boman, He He, Shi Feng
Abstract: Language models (LMs) can produce errors that are hard to detect for humans, especially when the task is complex. RLHF, the most popular post-training method, may exacerbate this problem: to achieve higher rewards, LMs might get better at convincing humans that they are right even when they are wrong. We study this phenomenon under a standard RLHF pipeline, calling it "U-SOPHISTRY" since it is Unintended by model developers. Specifically, we ask time-constrained (e.g., 3-10 minutes) human subjects to evaluate the correctness of model outputs and calculate humans' accuracy against gold labels. On a question-answering task (QuALITY) and programming task (APPS), RLHF makes LMs better at convincing our subjects but not at completing the task correctly. RLHF also makes the model harder to evaluate: our subjects' false positive rate increases by 24.1% on QuALITY and 18.3% on APPS. Finally, we show that probing, a state-of-the-art approach for detecting Intended Sophistry (e.g. backdoored LMs), does not generalize to U-SOPHISTRY. Our results highlight an important failure mode of RLHF and call for more research in assisting humans to align them.
Authors: Tenghao Huang, Donghee Lee, John Sweeney, Jiatong Shi, Emily Steliotes, Matthew Lange, Jonathan May, Muhao Chen
Abstract: Flavor development in the food industry is increasingly challenged by the need for rapid innovation and precise flavor profile creation. Traditional flavor research methods typically rely on iterative, subjective testing, which lacks the efficiency and scalability required for modern demands. This paper presents three contributions to address the challenges. Firstly, we define a new problem domain for scientific agents in flavor science, conceptualized as the generation of hypotheses for flavor profile sourcing and understanding. To facilitate research in this area, we introduce the FoodPuzzle, a challenging benchmark consisting of 978 food items and 1,766 flavor molecules profiles. We propose a novel Scientific Agent approach, integrating in-context learning and retrieval augmented techniques to generate grounded hypotheses in the domain of food science. Experimental results indicate that our model significantly surpasses traditional methods in flavor profile prediction tasks, demonstrating its potential to transform flavor development practices.
Authors: Muhammad Raees, Samina Fazilat
Abstract: Sentiment analysis possesses the potential of diverse applicability on digital platforms. Sentiment analysis extracts the polarity to understand the intensity and subjectivity in the text. This work uses a lexicon-based method to perform sentiment analysis and shows an evaluation of classification models trained over textual data. The lexicon-based methods identify the intensity of emotion and subjectivity at word levels. The categorization identifies the informative words inside a text and specifies the quantitative ranking of the polarity of words. This work is based on a multi-class problem of text being labeled as positive, negative, or neutral. Twitter sentiment dataset containing 1.6 million unprocessed tweets is used with lexicon-based methods like Text Blob and Vader Sentiment to introduce the neutrality measure on text. The analysis of lexicons shows how the word count and the intensity classify the text. A comparative analysis of machine learning models, Naiive Bayes, Support Vector Machines, Multinomial Logistic Regression, Random Forest, and Extreme Gradient (XG) Boost performed across multiple performance metrics. The best estimations are achieved through Random Forest with an accuracy score of 81%. Additionally, sentiment analysis is applied for a personality judgment case against a Twitter profile based on online activity.
Authors: Bryan Zhang, Taichi Nakatani, Stephan Walter
Abstract: E-commerce stores enable multilingual product discovery which require accurate product title translation. Multilingual large language models (LLMs) have shown promising capacity to perform machine translation tasks, and it can also enhance and translate product titles cross-lingually in one step. However, product title translation often requires more than just language conversion because titles are short, lack context, and contain specialized terminology. This study proposes a retrieval-augmented generation (RAG) approach that leverages existing bilingual product information in e-commerce by retrieving similar bilingual examples and incorporating them as few-shot prompts to enhance LLM-based product title translation. Experiment results show that our proposed RAG approach improve product title translation quality with chrF score gains of up to 15.3% for language pairs where the LLM has limited proficiency.
Authors: Peichao Lai, Zhengfeng Zhang, Bin Cui
Abstract: Recently, unsupervised sentence embedding models have received significant attention in downstream natural language processing tasks. Using large language models (LLMs) for data augmentation has led to considerable improvements in previous studies. Nevertheless, these strategies emphasize data augmentation with extensive generic corpora, neglecting the consideration of few-shot domain data. The synthesized data lacks fine-grained information and may introduce negative sample noise. This study introduces a novel pipeline-based data augmentation method that leverages LLM to synthesize the domain-specific dataset. It produces both positive and negative samples through entity- and quantity-aware augmentation, utilizing an entity knowledge graph to synthesize samples with fine-grained semantic distinctions, increasing training sample diversity and relevance. We then present a Gaussian-decayed gradient-assisted Contrastive Sentence Embedding (GCSE) model to reduce synthetic data noise and improve model discrimination to reduce negative sample noise. Experimental results demonstrate that our approach achieves state-of-the-art semantic textual similarity performance with fewer synthetic data samples and lesser LLM parameters, demonstrating its efficiency and robustness in varied backbones.
Authors: Mohammad Samragh, Iman Mirzadeh, Keivan Alizadeh Vahid, Fartash Faghri, Minsik Cho, Moin Nabi, Devang Naik, Mehrdad Farajtabar
Abstract: The pre-training phase of language models often begins with randomly initialized parameters. With the current trends in scaling models, training their large number of parameters can be extremely slow and costly. In contrast, small language models are less expensive to train, but they often cannot achieve the accuracy of large models. In this paper, we explore an intriguing idea to connect these two different regimes: Can we develop a method to initialize large language models using smaller pre-trained models? Will such initialization bring any benefits in terms of training time and final accuracy? In this paper, we introduce HyperCloning, a method that can expand the parameters of a pre-trained language model to those of a larger model with increased hidden dimensions. Our method ensures that the larger model retains the functionality of the smaller model. As a result, the larger model already inherits the predictive power and accuracy of the smaller model before the training starts. We demonstrate that training such an initialized model results in significant savings in terms of GPU hours required for pre-training large language models.
Authors: Jin Jiang, Yuchen Yan, Yang Liu, Yonggang Jin, Shuai Peng, Mengdi Zhang, Xunliang Cai, Yixin Cao, Liangcai Gao, Zhi Tang
Abstract: In this paper, we present a novel approach, called LogicPro, to enhance Large Language Models (LLMs) complex Logical reasoning through Program Examples. We do this effectively by simply utilizing widely available algorithmic problems and their code solutions. First, we constructed diverse test samples input based on algorithmic questions and code solutions. Then, we designed different complex reasoning questions based on algorithmic problems and test samples. Finally, combining the intermediate variable outputs of the code solutions and the complex reasoning questions, we derived the reasoning process and the final answer. With this approach, we can construct a dataset that is sufficiently difficult (all models are ineffective), diverse (synthesized from 2,360 different algorithmic questions), and scalable (building different test samples and collecting more algorithmic questions). In addition, we obtain a high-quality reasoning process guided by the values of intermediate variables. As a result, our approach achieves significant improvements in multiple models for the BBH$^{27}$, GSM8K, HellSwag, Logicqa, Reclor, and RTE datasets, outperforming a wide range of existing reasoning datasets.
Authors: Satyapriya Krishna, Kalpesh Krishna, Anhad Mohananey, Steven Schwarcz, Adam Stambler, Shyam Upadhyay, Manaal Faruqui
Abstract: Large Language Models (LLMs) have demonstrated significant performance improvements across various cognitive tasks. An emerging application is using LLMs to enhance retrieval-augmented generation (RAG) capabilities. These systems require LLMs to understand user queries, retrieve relevant information, and synthesize coherent and accurate responses. Given the increasing real-world deployment of such systems, comprehensive evaluation becomes crucial. To this end, we propose FRAMES (Factuality, Retrieval, And reasoning MEasurement Set), a high-quality evaluation dataset designed to test LLMs' ability to provide factual responses, assess retrieval capabilities, and evaluate the reasoning required to generate final answers. While previous work has provided datasets and benchmarks to evaluate these abilities in isolation, FRAMES offers a unified framework that provides a clearer picture of LLM performance in end-to-end RAG scenarios. Our dataset comprises challenging multi-hop questions that require the integration of information from multiple sources. We present baseline results demonstrating that even state-of-the-art LLMs struggle with this task, achieving 0.40 accuracy with no retrieval. The accuracy is significantly improved with our proposed multi-step retrieval pipeline, achieving an accuracy of 0.66 (>50% improvement). We hope our work will help bridge evaluation gaps and assist in developing more robust and capable RAG systems.
Authors: Abdullatif K\"oksal, Marion Thaler, Ayyoob Imani, Ahmet \"Ust\"un, Anna Korhonen, Hinrich Sch\"utze
Abstract: Instruction tuning enhances large language models (LLMs) by aligning them with human preferences across diverse tasks. Traditional approaches to create instruction tuning datasets face serious challenges for low-resource languages due to their dependence on data annotation. This work introduces a novel method, Multilingual Reverse Instructions (MURI), which generates high-quality instruction tuning datasets for low-resource languages without requiring human annotators or pre-existing multilingual models. Utilizing reverse instructions and a translation pipeline, MURI produces instruction-output pairs from existing human-written texts in low-resource languages. This method ensures cultural relevance and diversity by sourcing texts from different native domains and applying filters to eliminate inappropriate content. Our dataset, MURI-IT, includes more than 2 million instruction-output pairs across 200 languages. Evaluation by native speakers and fine-tuning experiments with mT5 models demonstrate the approach's effectiveness for both NLU and open-ended generation. We publicly release datasets and models at https://github.com/akoksal/muri.
Authors: Tsung-Han Wu, Joseph E. Gonzalez, Trevor Darrell, David M. Chan
Abstract: The Automated Audio Captioning (AAC) task asks models to generate natural language descriptions of an audio input. Evaluating these machine-generated audio captions is a complex task that requires considering diverse factors, among them, auditory scene understanding, sound-object inference, temporal coherence, and the environmental context of the scene. While current methods focus on specific aspects, they often fail to provide an overall score that aligns well with human judgment. In this work, we propose CLAIR-A, a simple and flexible method that leverages the zero-shot capabilities of large language models (LLMs) to evaluate candidate audio captions by directly asking LLMs for a semantic distance score. In our evaluations, CLAIR-A better predicts human judgements of quality compared to traditional metrics, with a 5.8% relative accuracy improvement compared to the domain-specific FENSE metric and up to 11% over the best general-purpose measure on the Clotho-Eval dataset. Moreover, CLAIR-A offers more transparency by allowing the language model to explain the reasoning behind its scores, with these explanations rated up to 30% better by human evaluators than those provided by baseline methods. CLAIR-A is made publicly available at https://github.com/DavidMChan/clair-a.
Authors: Abhinav Jain, Chris Jermaine, Vaibhav Unhelkar
Abstract: Large language models (LLMs) have recently emerged as promising tools for solving challenging robotic tasks, even in the presence of action and observation uncertainties. Recent LLM-based decision-making methods (also referred to as LLM-based agents), when paired with appropriate critics, have demonstrated potential in solving complex, long-horizon tasks with relatively few interactions. However, most existing LLM-based agents lack the ability to retain and learn from past interactions - an essential trait of learning-based robotic systems. We propose RAG-Modulo, a framework that enhances LLM-based agents with a memory of past interactions and incorporates critics to evaluate the agents' decisions. The memory component allows the agent to automatically retrieve and incorporate relevant past experiences as in-context examples, providing context-aware feedback for more informed decision-making. Further by updating its memory, the agent improves its performance over time, thereby exhibiting learning. Through experiments in the challenging BabyAI and AlfWorld domains, we demonstrate significant improvements in task success rates and efficiency, showing that the proposed RAG-Modulo framework outperforms state-of-the-art baselines.
Authors: Yihan Wu, Yifan Peng, Yichen Lu, Xuankai Chang, Ruihua Song, Shinji Watanabe
Abstract: Visual signals can enhance audiovisual speech recognition accuracy by providing additional contextual information. Given the complexity of visual signals, an audiovisual speech recognition model requires robust generalization capabilities across diverse video scenarios, presenting a significant challenge. In this paper, we introduce EVA, leveraging the mixture-of-Experts for audioVisual ASR to perform robust speech recognition for ``in-the-wild'' videos. Specifically, we first encode visual information into visual tokens sequence and map them into speech space by a lightweight projection. Then, we build EVA upon a robust pretrained speech recognition model, ensuring its generalization ability. Moreover, to incorporate visual information effectively, we inject visual information into the ASR model through a mixture-of-experts module. Experiments show our model achieves state-of-the-art results on three benchmarks, which demonstrates the generalization ability of EVA across diverse video domains.
Authors: Chien-Chun Wang, Li-Wei Chen, Cheng-Kang Chou, Hung-Shin Lee, Berlin Chen, Hsin-Min Wang
Abstract: While pre-trained automatic speech recognition (ASR) systems demonstrate impressive performance on matched domains, their performance often degrades when confronted with channel mismatch stemming from unseen recording environments and conditions. To mitigate this issue, we propose a novel channel-aware data simulation method for robust ASR training. Our method harnesses the synergistic power of channel-extractive techniques and generative adversarial networks (GANs). We first train a channel encoder capable of extracting embeddings from arbitrary audio. On top of this, channel embeddings are extracted using a minimal amount of target-domain data and used to guide a GAN-based speech synthesizer. This synthesizer generates speech that faithfully preserves the phonetic content of the input while mimicking the channel characteristics of the target domain. We evaluate our method on the challenging Hakka Across Taiwan (HAT) and Taiwanese Across Taiwan (TAT) corpora, achieving relative character error rate (CER) reductions of 20.02% and 9.64%, respectively, compared to the baselines. These results highlight the efficacy of our channel-aware data simulation method for bridging the gap between source- and target-domain acoustics.
Authors: Hakan T. Otal, Stephen V. Faraone, M. Abdullah Canbaz
Abstract: Attention-Deficit/Hyperactivity Disorder (ADHD) is a challenging disorder to study due to its complex symptomatology and diverse contributing factors. To explore how we can gain deeper insights on this topic, we performed a network analysis on a comprehensive knowledge graph (KG) of ADHD, constructed by integrating scientific literature and clinical data with the help of cutting-edge large language models. The analysis, including k-core techniques, identified critical nodes and relationships that are central to understanding the disorder. Building on these findings, we developed a context-aware chatbot using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), enabling accurate and informed interactions. Our knowledge graph not only advances the understanding of ADHD but also provides a powerful tool for research and clinical applications.
Authors: Domenic Rosati, Giles Edkins, Harsh Raj, David Atanasov, Subhabrata Majumdar, Janarthanan Rajendran, Frank Rudzicz, Hassan Sajjad
Abstract: While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety-aligned LLMs are known to be vulnerable to training-time attacks such as supervised fine-tuning (SFT) on harmful datasets. In this paper, we ask if LLMs are vulnerable to adversarial reinforcement learning. Motivated by this goal, we propose Reverse Preference Attacks (RPA), a class of attacks to make LLMs learn harmful behavior using adversarial reward during reinforcement learning from human feedback (RLHF). RPAs expose a critical safety gap of safety-aligned LLMs in RL settings: they easily explore the harmful text generation policies to optimize adversarial reward. To protect against RPAs, we explore a host of mitigation strategies. Leveraging Constrained Markov-Decision Processes, we adapt a number of mechanisms to defend against harmful fine-tuning attacks into the RL setting. Our experiments show that ``online" defenses that are based on the idea of minimizing the negative log likelihood of refusals -- with the defender having control of the loss function -- can effectively protect LLMs against RPAs. However, trying to defend model weights using ``offline" defenses that operate under the assumption that the defender has no control over the loss function are less effective in the face of RPAs. These findings show that attacks done using RL can be used to successfully undo safety alignment in open-weight LLMs and use them for malicious purposes.
Authors: Prateek Verma
Abstract: Large Language Models (LLMs) have ushered in a new wave of artificial intelligence advancements impacting every scientific field and discipline. They are trained on a simple objective: to predict the next token given the previous context. We live in a world where most of the data around us, e.g., text, audio, and music, has a multi-scale structure associated with it. This paper infuses LLMs with traditional signal processing ideas, namely wavelets, during pre-training to take advantage of the structure. Without adding \textbf{any extra parameters} to a GPT-style LLM architecture, we achieve the same pre-training performance almost twice as fast in text, raw audio, and symbolic music. This is achieved by imposing a structure on intermediate embeddings. When trained for the same number of training steps, we achieve significant gains in performance, which is comparable to pre-training a larger neural architecture. Our architecture allows every next token prediction access to intermediate embeddings at different temporal resolutions in every Transformer decoder block. This work will hopefully pave the way for incorporating multi-rate signal processing ideas into traditional LLM pre-training. Further, we showcase pushing model performance by improving internal structure instead of just going after scale.
Authors: Akshat Gupta, Atahan Ozdemir, Gopala Anumanchipalli
Abstract: Layer normalization is a pivotal step in the transformer architecture. This paper delves into the less explored geometric implications of this process, examining how LayerNorm influences the norm and orientation of hidden vectors in the representation space. We show that the definition of LayerNorm is innately linked to the uniform vector, defined as $\boldsymbol{1} = [1, 1, 1, 1, \cdots, 1]^T \in \mathbb{R}^d$. We then show that the standardization step in LayerNorm can be understood in three simple steps: (i) remove the component of a vector along the uniform vector, (ii) normalize the remaining vector, and (iii) scale the resultant vector by $\sqrt{d}$, where $d$ is the dimensionality of the representation space. We also introduce the property of "irreversibility" for LayerNorm, where we show that the information lost during the normalization process cannot be recovered. In other words, unlike batch normalization, LayerNorm cannot learn an identity transform. While we present possible arguments for removing the component along the uniform vector, the choice of removing this component seems arbitrary and not well motivated by the original authors. To evaluate the usefulness of this step, we compare the hidden representations of LayerNorm-based LLMs with models trained using RMSNorm and show that all LLMs naturally align representations orthogonal to the uniform vector, presenting the first mechanistic evidence that removing the component along the uniform vector in LayerNorm is a redundant step. Our findings support the use of RMSNorm over LayerNorm as it is not only more computationally efficient with comparable downstream performance, but also learns a similar distribution of hidden representations that operate orthogonal to the uniform vector.
Authors: Dongzhi Jiang, Renrui Zhang, Ziyu Guo, Yanmin Wu, Jiayi Lei, Pengshuo Qiu, Pan Lu, Zehui Chen, Guanglu Song, Peng Gao, Yu Liu, Chunyuan Li, Hongsheng Li
Abstract: The advent of Large Language Models (LLMs) has paved the way for AI search engines, e.g., SearchGPT, showcasing a new paradigm in human-internet interaction. However, most current AI search engines are limited to text-only settings, neglecting the multimodal user queries and the text-image interleaved nature of website information. Recently, Large Multimodal Models (LMMs) have made impressive strides. Yet, whether they can function as AI search engines remains under-explored, leaving the potential of LMMs in multimodal search an open question. To this end, we first design a delicate pipeline, MMSearch-Engine, to empower any LMMs with multimodal search capabilities. On top of this, we introduce MMSearch, a comprehensive evaluation benchmark to assess the multimodal search performance of LMMs. The curated dataset contains 300 manually collected instances spanning 14 subfields, which involves no overlap with the current LMMs' training data, ensuring the correct answer can only be obtained within searching. By using MMSearch-Engine, the LMMs are evaluated by performing three individual tasks (requery, rerank, and summarization), and one challenging end-to-end task with a complete searching process. We conduct extensive experiments on closed-source and open-source LMMs. Among all tested models, GPT-4o with MMSearch-Engine achieves the best results, which surpasses the commercial product, Perplexity Pro, in the end-to-end task, demonstrating the effectiveness of our proposed pipeline. We further present error analysis to unveil current LMMs still struggle to fully grasp the multimodal search tasks, and conduct ablation study to indicate the potential of scaling test-time computation for AI search engine. We hope MMSearch may provide unique insights to guide the future development of multimodal AI search engine. Project Page: https://mmsearch.github.io
Authors: Bing Wang, Xinnian Liang, Jian Yang, Hui Huang, Shuangzhi Wu, Peihao Wu, Lu Lu, Zejun Ma, Zhoujun Li
Abstract: Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information. To address this limitation, in this paper, we propose the Self-Controlled Memory (SCM) framework to enhance the ability of LLMs to maintain long-term memory and recall relevant information. Our SCM framework comprises three key components: an LLM-based agent serving as the backbone of the framework, a memory stream storing agent memories, and a memory controller updating memories and determining when and how to utilize memories from memory stream. Additionally, the proposed SCM is able to process ultra-long texts without any modification or fine-tuning, which can integrate with any instruction following LLMs in a plug-and-play paradigm. Furthermore, we annotate a dataset to evaluate the effectiveness of SCM for handling lengthy inputs. The annotated dataset covers three tasks: long-term dialogues, book summarization, and meeting summarization. Experimental results demonstrate that our method achieves better retrieval recall and generates more informative responses compared to competitive baselines in long-term dialogues. (https://github.com/wbbeyourself/SCM4LLMs)
Authors: Letitia Parcalabescu, Anette Frank
Abstract: Large language models (LLMs) can explain their predictions through post-hoc or Chain-of-Thought (CoT) explanations. But an LLM could make up reasonably sounding explanations that are unfaithful to its underlying reasoning. Recent work has designed tests that aim to judge the faithfulness of post-hoc or CoT explanations. In this work we argue that these faithfulness tests do not measure faithfulness to the models' inner workings -- but rather their self-consistency at output level. Our contributions are three-fold: i) We clarify the status of faithfulness tests in view of model explainability, characterising them as self-consistency tests instead. This assessment we underline by ii) constructing a Comparative Consistency Bank for self-consistency tests that for the first time compares existing tests on a common suite of 11 open LLMs and 5 tasks -- including iii) our new self-consistency measure CC-SHAP. CC-SHAP is a fine-grained measure (not a test) of LLM self-consistency. It compares how a model's input contributes to the predicted answer and to generating the explanation. Our fine-grained CC-SHAP metric allows us iii) to compare LLM behaviour when making predictions and to analyse the effect of other consistency tests at a deeper level, which takes us one step further towards measuring faithfulness by bringing us closer to the internals of the model than strictly surface output-oriented tests. Our code is available at \url{https://github.com/Heidelberg-NLP/CC-SHAP}
Authors: Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, Linzheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xing Sun, Zhoujun Li
Abstract: Recent LLM-based Text-to-SQL methods usually suffer from significant performance degradation on "huge" databases and complex user questions that require multi-step reasoning. Moreover, most existing methods neglect the crucial significance of LLMs utilizing external tools and model collaboration. To address these challenges, we introduce MAC-SQL, a novel LLM-based multi-agent collaborative framework. Our framework comprises a core decomposer agent for Text-to-SQL generation with few-shot chain-of-thought reasoning, accompanied by two auxiliary agents that utilize external tools or models to acquire smaller sub-databases and refine erroneous SQL queries. The decomposer agent collaborates with auxiliary agents, which are activated as needed and can be expanded to accommodate new features or tools for effective Text-to-SQL parsing. In our framework, We initially leverage GPT-4 as the strong backbone LLM for all agent tasks to determine the upper bound of our framework. We then fine-tune an open-sourced instruction-followed model, SQL-Llama, by leveraging Code Llama 7B, to accomplish all tasks as GPT-4 does. Experiments show that SQL-Llama achieves a comparable execution accuracy of 43.94, compared to the baseline accuracy of 46.35 for vanilla GPT-4. At the time of writing, MAC-SQL+GPT-4 achieves an execution accuracy of 59.59 when evaluated on the BIRD benchmark, establishing a new state-of-the-art (SOTA) on its holdout test set (https://github.com/wbbeyourself/MAC-SQL).
Authors: Hongru Wang, Wenyu Huang, Yang Deng, Rui Wang, Zezhong Wang, Yufei Wang, Fei Mi, Jeff Z. Pan, Kam-Fai Wong
Abstract: Large Language Models (LLMs) has shown exceptional capabilities in many natual language understanding and generation tasks. However, the personalization issue still remains a much-coveted property, especially when it comes to the multiple sources involved in the dialogue system. To better plan and incorporate the use of multiple sources in generating personalized response, we firstly decompose it into three sub-tasks: Knowledge Source Selection, Knowledge Retrieval, and Response Generation. We then propose a novel Unified Multi-Source Retrieval-Augmented Generation system (UniMS-RAG) Specifically, we unify these three sub-tasks with different formulations into the same sequence-to-sequence paradigm during the training, to adaptively retrieve evidences and evaluate the relevance on-demand using special tokens, called acting tokens and evaluation tokens. Enabling language models to generate acting tokens facilitates interaction with various knowledge sources, allowing them to adapt their behavior to diverse task requirements. Meanwhile, evaluation tokens gauge the relevance score between the dialogue context and the retrieved evidence. In addition, we carefully design a self-refinement mechanism to iteratively refine the generated response considering 1) the consistency scores between the generated response and retrieved evidence; and 2) the relevance scores. Experiments on two personalized datasets (DuLeMon and KBP) show that UniMS-RAG achieves state-of-the-art performance on the knowledge source selection and response generation task with itself as a retriever in a unified manner. Extensive analyses and discussions are provided for shedding some new perspectives for personalized dialogue systems.
Authors: Zihan Zhao, Da Ma, Lu Chen, Liangtai Sun, Zihao Li, Yi Xia, Bo Chen, Hongshen Xu, Zichen Zhu, Su Zhu, Shuai Fan, Guodong Shen, Kai Yu, Xin Chen
Abstract: Artificial intelligence (AI) has played an increasingly important role in chemical research. However, most models currently used in chemistry are specialist models that require training and tuning for specific tasks. A more generic and efficient solution would be an AI model that could address many tasks and support free-form dialogue in the broad field of chemistry. In its utmost form, such a generalist AI chemist could be referred to as Chemical General Intelligence. Large language models (LLMs) have recently logged tremendous success in the general domain of natural language processing, showing emerging task generalization and free-form dialogue capabilities. However, domain knowledge of chemistry is largely missing when training general-domain LLMs. The lack of such knowledge greatly hinders the performance of generalist LLMs in the field of chemistry. To this end, we develop ChemDFM, a pioneering LLM for chemistry trained on 34B tokens from chemical literature and textbooks, and fine-tuned using 2.7M instructions. As a result, it can understand and reason with chemical knowledge in free-form dialogue. Quantitative evaluations show that ChemDFM significantly surpasses most representative open-source LLMs. It outperforms GPT-4 on a great portion of chemical tasks, despite the substantial size difference. We will open-source ChemDFM for the broader community of AI and chemistry.
Authors: Yinghui Li, Shang Qin, Haojing Huang, Yangning Li, Libo Qin, Xuming Hu, Wenhao Jiang, Hai-Tao Zheng, Philip S. Yu
Abstract: Recently, Large Language Models (LLMs) have been widely studied by researchers for their roles in various downstream NLP tasks. As a fundamental task in the NLP field, Chinese Grammatical Error Correction (CGEC) aims to correct all potential grammatical errors in the input sentences. Previous studies have shown that LLMs' performance as correctors on CGEC remains unsatisfactory due to its challenging task focus. To promote the CGEC field to better adapt to the era of LLMs, we rethink the roles of LLMs in the CGEC task so that they can be better utilized and explored in CGEC. Considering the rich grammatical knowledge stored in LLMs and their powerful semantic understanding capabilities, we utilize LLMs as explainers to provide explanation information for the CGEC small models during error correction to enhance performance. We also use LLMs as evaluators to bring more reasonable CGEC evaluations, thus alleviating the troubles caused by the subjectivity of the CGEC task. In particular, our work is also an active exploration of how LLMs and small models better collaborate in downstream tasks. Extensive experiments and detailed analyses on widely used datasets verify the effectiveness of our thinking intuition and the proposed methods.
Authors: Xu Zhang, Dinghao Jing, Xiaojun Wan
Abstract: As large language models(LLMs) become commonplace in practical applications, the security issues of LLMs have attracted societal concerns. Although extensive efforts have been made to safety alignment, LLMs remain vulnerable to jailbreak attacks. We find that redundant computations limit the performance of existing jailbreak attack methods. Therefore, we propose DPP-based Stochastic Trigger Searching (DSTS), a new optimization algorithm for jailbreak attacks. DSTS incorporates diversity guidance through techniques including stochastic gradient search and DPP selection during optimization. Detailed experiments and ablation studies demonstrate the effectiveness of the algorithm. Moreover, we use the proposed algorithm to compute the risk boundaries for different LLMs, providing a new perspective on LLM safety evaluation.
Authors: Truman Yuen, Graham A. Watt, Yuri Lawryshyn
Abstract: Generative Large Language Models enable efficient analytics across knowledge domains, rivalling human experts in information comparisons. However, the applications of LLMs for information comparisons face scalability challenges due to the difficulties in maintaining information across large contexts and overcoming model token limitations. To address these challenges, we developed the novel Abstractive Summarization & Criteria-driven Comparison Endpoint (ASC$^2$End) system to automate information comparison at scale. Our system employs Semantic Text Similarity comparisons for generating evidence-supported analyses. We utilize proven data-handling strategies such as abstractive summarization and retrieval augmented generation to overcome token limitations and retain relevant information during model inference. Prompts were designed using zero-shot strategies to contextualize information for improved model reasoning. We evaluated abstractive summarization using ROUGE scoring and assessed the generated comparison quality using survey responses. Models evaluated on the ASC$^2$End system show desirable results providing insights on the expected performance of the system. ASC$^2$End is a novel system and tool that enables accurate, automated information comparison at scale across knowledge domains, overcoming limitations in context length and retrieval.
Authors: Wei Wang, Zhaowei Li, Qi Xu, Yiqing Cai, Hang Song, Qi Qi, Ran Zhou, Zhida Huang, Tao Wang, Li Xiao
Abstract: The deployment of large language models (LLMs) faces considerable challenges concerning resource constraints and inference efficiency. Recent research has increasingly focused on smaller, task-specific models enhanced by distilling knowledge from LLMs. However, prior studies have often overlooked the diversity and quality of knowledge, especially the untapped potential of negative knowledge. Constructing effective negative knowledge remains severely understudied. In this paper, we introduce a novel framework called quality-guided contrastive rationale distillation aimed at enhancing reasoning capabilities through contrastive knowledge learning. For positive knowledge, we enrich its diversity through temperature sampling and employ self-consistency for further denoising and refinement. For negative knowledge, we propose an innovative self-adversarial approach that generates low-quality rationales by sampling previous iterations of smaller language models, embracing the idea that one can learn from one's own weaknesses. A contrastive loss is developed to distill both positive and negative knowledge into smaller language models, where an online-updating discriminator is integrated to assess qualities of rationales and assign them appropriate weights, optimizing the training process. Through extensive experiments across multiple reasoning tasks, we demonstrate that our method consistently outperforms existing distillation techniques, yielding higher-quality rationales.
Authors: Devang Kulshreshtha, Saket Dingliwal, Brady Houston, Nikolaos Pappas, Srikanth Ronanki
Abstract: Automatic Speech Recognition (ASR) traditionally assumes known domains, but adding data from a new domain raises concerns about computational inefficiencies linked to retraining models on both existing and new domains. Fine-tuning solely on new domain risks Catastrophic Forgetting (CF). To address this, Lifelong Learning (LLL) algorithms have been proposed for ASR. Prior research has explored techniques such as Elastic Weight Consolidation, Knowledge Distillation, and Replay, all of which necessitate either additional parameters or access to prior domain data. We propose Sequential Model Editing as a novel method to continually learn new domains in ASR systems. Different than previous methods, our approach does not necessitate access to prior datasets or the introduction of extra parameters. Our study demonstrates up to 15% Word Error Rate Reduction (WERR) over fine-tuning baseline, and superior efficiency over other LLL techniques on CommonVoice English multi-accent dataset.
Authors: Sohini Roychowdhury, Marko Krema, Brian Moore, Xingjian Lai, Dike Effedua, Bharat Jethwani
Abstract: Financial report generation using general purpose large language models (LLMs) pose two major challenges namely, the lack of compound sentences and hallucinations. Advanced prompt engineering and retrieval augmented generation (RAG) techniques are limited in scope for curing these writing style discrepancies. In this work we propose a novel two-stage fine-tuning (FT) process wherein public domain financial reports are processed into prompt-completions and augmented using simple LLM prompts to then enable sectional financial report generation using minimal instructions and tabular data inputs. The proposed fine-tuning process exploits the self-learning capability of LLMs by allowing hallucinations in the first stage and showing the corrections in the second stage. Our proposed fine-tuning framework results doubles the number of correct questions answers and reduces hallucinations by over 50%. Additionally, the two-stage FT model has lower perplexity, improved ROUGE, TER and BLEU scores, higher creativity and knowledge density with lower uncertainty and cross entropy. Thus, the proposed framework can be generalized to domain specific fine-tuning tasks at minimized tuning costs.
Authors: Abdullah Al Imran, Md Farhan Ishmam
Abstract: In resource constraint settings, adaptation to downstream classification tasks involves fine-tuning the final layer of a classifier (i.e. classification head) while keeping rest of the model weights frozen. Multi-Layer Perceptron (MLP) heads fine-tuned with pre-trained transformer backbones have long been the de facto standard for text classification head fine-tuning. However, the fixed non-linearity of MLPs often struggles to fully capture the nuances of contextual embeddings produced by pre-trained models, while also being computationally expensive. In our work, we investigate the efficacy of KAN and its variant, Fourier KAN (FR-KAN), as alternative text classification heads. Our experiments reveal that FR-KAN significantly outperforms MLPs with an average improvement of 10% in accuracy and 11% in F1-score across seven pre-trained transformer models and four text classification tasks. Beyond performance gains, FR-KAN is more computationally efficient and trains faster with fewer parameters. These results underscore the potential of FR-KAN to serve as a lightweight classification head, with broader implications for advancing other Natural Language Processing (NLP) tasks.
Authors: Yuankai Zhang, Lingxiao Kong, Haozhao Wang, Ruixuan Li, Jun Wang, Yuhua Li, Wei Liu
Abstract: Rationalization models, which select a subset of input text as rationale-crucial for humans to understand and trust predictions-have recently emerged as a prominent research area in eXplainable Artificial Intelligence. However, most of previous studies mainly focus on improving the quality of the rationale, ignoring its robustness to malicious attack. Specifically, whether the rationalization models can still generate high-quality rationale under the adversarial attack remains unknown. To explore this, this paper proposes UAT2E, which aims to undermine the explainability of rationalization models without altering their predictions, thereby eliciting distrust in these models from human users. UAT2E employs the gradient-based search on triggers and then inserts them into the original input to conduct both the non-target and target attack. Experimental results on five datasets reveal the vulnerability of rationalization models in terms of explanation, where they tend to select more meaningless tokens under attacks. Based on this, we make a series of recommendations for improving rationalization models in terms of explanation.
Authors: Shuang Zhou, Zidu Xu, Mian Zhang, Chunpu Xu, Yawen Guo, Zaifu Zhan, Sirui Ding, Jiashuo Wang, Kaishuai Xu, Yi Fang, Liqiao Xia, Jeremy Yeung, Daochen Zha, Genevieve B. Melton, Mingquan Lin, Rui Zhang
Abstract: Automatic disease diagnosis has become increasingly valuable in clinical practice. The advent of large language models (LLMs) has catalyzed a paradigm shift in artificial intelligence, with growing evidence supporting the efficacy of LLMs in diagnostic tasks. Despite the increasing attention in this field, a holistic view is still lacking. Many critical aspects remain unclear, such as the diseases and clinical data to which LLMs have been applied, the LLM techniques employed, and the evaluation methods used. In this article, we perform a comprehensive review of LLM-based methods for disease diagnosis. Our review examines the existing literature across various dimensions, including disease types and associated clinical specialties, clinical data, LLM techniques, and evaluation methods. Additionally, we offer recommendations for applying and evaluating LLMs for diagnostic tasks. Furthermore, we assess the limitations of current research and discuss future directions. To our knowledge, this is the first comprehensive review for LLM-based disease diagnosis.
Authors: Abu Ubaida Akash, Ahmed Fahmy, Amine Trabelsi
Abstract: Stance detection (SD) identifies a text's position towards a target, typically labeled as favor, against, or none. We introduce Open-Target Stance Detection (OTSD), the most realistic task where targets are neither seen during training nor provided as input. We evaluate Large Language Models (LLMs) GPT-4o, GPT-3.5, Llama-3, and Mistral, comparing their performance to the only existing work, Target-Stance Extraction (TSE), which benefits from predefined targets. Unlike TSE, OTSD removes the dependency of a predefined list, making target generation and evaluation more challenging. We also provide a metric for evaluating target quality that correlates well with human judgment. Our experiments reveal that LLMs outperform TSE in target generation when the real target is explicitly and not explicitly mentioned in the text. Likewise, for stance detection, LLMs excel in explicit cases with comparable performance in non-explicit in general.
Authors: Tiansheng Huang, Sihao Hu, Fatih Ilhan, Selim Furkan Tekin, Ling Liu
Abstract: Harmful fine-tuning issue \citep{qi2023fine} poses serious safety concerns for Large language models' fine-tuning-as-a-service. While existing defenses \citep{huang2024vaccine,rosati2024representation} have been proposed to mitigate the issue, their performances are still far away from satisfactory, and the root cause of the problem has not been fully recovered. For the first time in the literature, we in this paper show that \textit{harmful perturbation} over the model weights should be the root cause of alignment-broken of harmful fine-tuning. In order to attenuate the negative impact of harmful perturbation, we propose an alignment-stage solution, dubbed Booster. Technically, along with the original alignment loss, we append a loss regularizer in the alignment stage's optimization. The regularizer ensures that the model's harmful loss reduction before/after simulated harmful perturbation is attenuated, thereby mitigating the subsequent fine-tuning risk. Empirical results show that Booster can effectively reduce the harmful score of the fine-tuned models while maintaining the performance of downstream tasks. Our code is available at \url{https://github.com/git-disl/Booster}.
Authors: Leyi Pan, Aiwei Liu, Yijian Lu, Zitian Gao, Yichen Di, Lijie Wen, Irwin King, Philip S. Yu
Abstract: Watermarking algorithms for large language models (LLMs) have attained high accuracy in detecting LLM-generated text. However, existing methods primarily focus on distinguishing fully watermarked text from non-watermarked text, overlooking real-world scenarios where LLMs generate only small sections within large documents. In this scenario, balancing time complexity and detection performance poses significant challenges. This paper presents WaterSeeker, a novel approach to efficiently detect and locate watermarked segments amid extensive natural text. It first applies an efficient anomaly extraction method to preliminarily locate suspicious watermarked regions. Following this, it conducts a local traversal and performs full-text detection for more precise verification. Theoretical analysis and experimental results demonstrate that WaterSeeker achieves a superior balance between detection accuracy and computational efficiency. Moreover, WaterSeeker's localization ability supports the development of interpretable AI detection systems. This work pioneers a new direction in watermarked segment detection, facilitating more reliable AI-generated content identification.Our code is available at https://github.com/THU-BPM/WaterSeeker.
Authors: Run Luo, Haonan Zhang, Longze Chen, Ting-En Lin, Xiong Liu, Yuchuan Wu, Min Yang, Minzheng Wang, Pengpeng Zeng, Lianli Gao, Heng Tao Shen, Yunshui Li, Xiaobo Xia, Fei Huang, Jingkuan Song, Yongbin Li
Abstract: The development of Multimodal Large Language Models (MLLMs) has seen significant advancements with increasing demands in various fields (e.g., multimodal agents, embodied intelligence). While model-driven approaches attempt to enhance MLLMs capabilities through diverse architectures, the gains have become increasingly marginal. Conversely, data-driven methods, which scale up image-text instruction data, are more effective but face limited data diversity and complexity challenges. The absence of high-quality data constitutes a significant development barrier for MLLMs. To address the data quality bottleneck, we propose MMEvol, a novel multimodal instruction data evolution framework. This framework iteratively improve data quality through a refined combination of fine-grained perception, cognitive reasoning, and interaction evolution, generating a more complex and diverse image-text instruction dataset that empowers MLLMs with enhanced capabilities. Beginning with an initial set of instructions, SEED-163K, we utilize MMEvol to systematically broaden the diversity of instruction types, extend visual reasoning steps to improve cognitive reasoning abilities, and thoroughly explore fine-grained information within images to enhance visual understanding and robustness. To comprehensively evaluate the effectiveness of our approach, we conduct extensive qualitative analysis and quantitative experiments across 13 vision-language tasks. Compared to baseline models trained with the initial seed data, the results demonstrate that our method achieves an average accuracy improvement of 3.1 percentage points. Furthermore, our approach reaches state-of-the-art (SOTA) performance in nine tasks using significantly less data compared to state-of-the-art models.
Authors: Faiz Ali Shah, Ahmed Sabir, Rajesh Sharma
Abstract: Analyzing user reviews for sentiment towards app features can provide valuable insights into users' perceptions of app functionality and their evolving needs. Given the volume of user reviews received daily, an automated mechanism to generate feature-level sentiment summaries of user reviews is needed. Recent advances in Large Language Models (LLMs) such as ChatGPT have shown impressive performance on several new tasks without updating the model's parameters i.e. using zero or a few labeled examples. Despite these advancements, LLMs' capabilities to perform feature-specific sentiment analysis of user reviews remain unexplored. This study compares the performance of state-of-the-art LLMs, including GPT-4, ChatGPT, and LLama-2-chat variants, for extracting app features and associated sentiments under 0-shot, 1-shot, and 5-shot scenarios. Results indicate the best-performing GPT-4 model outperforms rule-based approaches by 23.6% in f1-score with zero-shot feature extraction; 5-shot further improving it by 6%. GPT-4 achieves a 74% f1-score for predicting positive sentiment towards correctly predicted app features, with 5-shot enhancing it by 7%. Our study suggests that LLM models are promising for generating feature-specific sentiment summaries of user reviews.
Authors: Sumera Anjum, Hanzhi Zhang, Wenjun Zhou, Eun Jin Paek, Xiaopeng Zhao, Yunhe Feng
Abstract: Large language models (LLMs) have significantly advanced natural language processing tasks, yet they are susceptible to generating inaccurate or unreliable responses, a phenomenon known as hallucination. In critical domains such as health and medicine, these hallucinations can pose serious risks. This paper introduces HALO, a novel framework designed to enhance the accuracy and reliability of medical question-answering (QA) systems by focusing on the detection and mitigation of hallucinations. Our approach generates multiple variations of a given query using LLMs and retrieves relevant information from external open knowledge bases to enrich the context. We utilize maximum marginal relevance scoring to prioritize the retrieved context, which is then provided to LLMs for answer generation, thereby reducing the risk of hallucinations. The integration of LangChain further streamlines this process, resulting in a notable and robust increase in the accuracy of both open-source and commercial LLMs, such as Llama-3.1 (from 44% to 65%) and ChatGPT (from 56% to 70%). This framework underscores the critical importance of addressing hallucinations in medical QA systems, ultimately improving clinical decision-making and patient care. The open-source HALO is available at: https://github.com/ResponsibleAILab/HALO.
Authors: Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram, Michael G\"unther, Bo Wang, Markus Krimmel, Feng Wang, Georgios Mastrapas, Andreas Koukounas, Nan Wang, Han Xiao
Abstract: We introduce jina-embeddings-v3, a novel text embedding model with 570 million parameters, achieves state-of-the-art performance on multilingual data and long-context retrieval tasks, supporting context lengths of up to 8192 tokens. The model includes a set of task-specific Low-Rank Adaptation (LoRA) adapters to generate high-quality embeddings for query-document retrieval, clustering, classification, and text matching. Evaluation on the MTEB benchmark shows that jina-embeddings-v3 outperforms the latest proprietary embeddings from OpenAI and Cohere on English tasks, while achieving superior performance compared to multilingual-e5-large-instruct across all multilingual tasks. With a default output dimension of 1024, users can flexibly reduce the embedding dimensions to as low as 32 without compromising performance, enabled by Matryoshka Representation Learning.
Authors: Samee Arif, Taimoor Arif, Muhammad Saad Haroon, Aamina Jamal Khan, Agha Ali Raza, Awais Athar
Abstract: This paper introduces the concept of an education tool that utilizes Generative Artificial Intelligence (GenAI) to enhance storytelling for children. The system combines GenAI-driven narrative co-creation, text-to-speech conversion, and text-to-video generation to produce an engaging experience for learners. We describe the co-creation process, the adaptation of narratives into spoken words using text-to-speech models, and the transformation of these narratives into contextually relevant visuals through text-to-video technology. Our evaluation covers the linguistics of the generated stories, the text-to-speech conversion quality, and the accuracy of the generated visuals.
Authors: Nikit Srivastava, Denis Kuchelev, Tatiana Moteu Ngoli, Kshitij Shetty, Michael R\"oder, Diego Moussallem, Hamada Zahera, Axel-Cyrille Ngonga Ngomo
Abstract: This paper presents LOLA, a massively multilingual large language model trained on more than 160 languages using a sparse Mixture-of-Experts Transformer architecture. Our architectural and implementation choices address the challenge of harnessing linguistic diversity while maintaining efficiency and avoiding the common pitfalls of multilinguality. Our analysis of the evaluation results shows competitive performance in natural language generation and understanding tasks. Additionally, we demonstrate how the learned expert-routing mechanism exploits implicit phylogenetic linguistic patterns to potentially alleviate the curse of multilinguality. We provide an in-depth look at the training process, an analysis of the datasets, and a balanced exploration of the model's strengths and limitations. As an open-source model, LOLA promotes reproducibility and serves as a robust foundation for future research. Our findings enable the development of compute-efficient multilingual models with strong, scalable performance across languages.
Authors: Kanishk Gandhi, Zoe Lynch, Jan-Philipp Fr\"anken, Kayla Patterson, Sharon Wambu, Tobias Gerstenberg, Desmond C. Ong, Noah D. Goodman
Abstract: Understanding emotions is fundamental to human interaction and experience. Humans easily infer emotions from situations or facial expressions, situations from emotions, and do a variety of other affective cognition. How adept is modern AI at these inferences? We introduce an evaluation framework for testing affective cognition in foundation models. Starting from psychological theory, we generate 1,280 diverse scenarios exploring relationships between appraisals, emotions, expressions, and outcomes. We evaluate the abilities of foundation models (GPT-4, Claude-3, Gemini-1.5-Pro) and humans (N = 567) across carefully selected conditions. Our results show foundation models tend to agree with human intuitions, matching or exceeding interparticipant agreement. In some conditions, models are ``superhuman'' -- they better predict modal human judgements than the average human. All models benefit from chain-of-thought reasoning. This suggests foundation models have acquired a human-like understanding of emotions and their influence on beliefs and behavior.
Authors: Yumeng Yang, Peter Krusche, Kristyn Pantoja, Cheng Shi, Ethan Ludmir, Kirk Roberts, Gen Zhu
Abstract: Tables, figures, and listings (TFLs) are essential tools for summarizing clinical trial data. Creation of TFLs for reporting activities is often a time-consuming task encountered routinely during the execution of clinical trials. This study explored the use of large language models (LLMs) to automate the generation of TFLs through prompt engineering and few-shot transfer learning. Using public clinical trial data in ADaM format, our results demonstrated that LLMs can efficiently generate TFLs with prompt instructions, showcasing their potential in this domain. Furthermore, we developed a conservational agent named Clinical Trial TFL Generation Agent: An app that matches user queries to predefined prompts that produce customized programs to generate specific predefined TFLs.
Authors: Warren Jouanneau, Marc Palyart, Emma Jouffroy
Abstract: Finding the perfect match between a job proposal and a set of freelancers is not an easy task to perform at scale, especially in multiple languages. In this paper, we propose a novel neural retriever architecture that tackles this problem in a multilingual setting. Our method encodes project descriptions and freelancer profiles by leveraging pre-trained multilingual language models. The latter are used as backbone for a custom transformer architecture that aims to keep the structure of the profiles and project. This model is trained with a contrastive loss on historical data. Thanks to several experiments, we show that this approach effectively captures skill matching similarity and facilitates efficient matching, outperforming traditional methods.
Authors: Somonnoy Banerjee, Sujan Dutta, Soumyajit Datta, Ashiqur R. KhudaBukhsh
Abstract: This paper makes three key contributions. First, via a substantial corpus of 51,278 interview questions sourced from 888 YouTube videos of mock interviews of Indian civil service candidates, we demonstrate stark gender bias in the broad nature of questions asked to male and female candidates. Second, our experiments with large language models show a strong presence of gender bias in explanations provided by the LLMs on the gender inference task. Finally, we present a novel dataset of 51,278 interview questions that can inform future social science studies.
Authors: Letitia Parcalabescu, Anette Frank
Abstract: Vision and language models (VL) are known to exploit unrobust indicators in individual modalities (e.g., introduced by distributional biases) instead of focusing on relevant information in each modality. That a unimodal model achieves similar accuracy on a VL task to a multimodal one, indicates that so-called unimodal collapse occurred. However, accuracy-based tests fail to detect e.g., when the model prediction is wrong, while the model used relevant information from a modality. Instead, we propose MM-SHAP, a performance-agnostic multimodality score based on Shapley values that reliably quantifies in which proportions a multimodal model uses individual modalities. We apply MM-SHAP in two ways: (1) to compare models for their average degree of multimodality, and (2) to measure for individual models the contribution of individual modalities for different tasks and datasets. Experiments with six VL models -- LXMERT, CLIP and four ALBEF variants -- on four VL tasks highlight that unimodal collapse can occur to different degrees and in different directions, contradicting the wide-spread assumption that unimodal collapse is one-sided. Based on our results, we recommend MM-SHAP for analysing multimodal tasks, to diagnose and guide progress towards multimodal integration. Code available at \url{https://github.com/Heidelberg-NLP/MM-SHAP}.
Authors: Renrui Zhang, Jiaming Han, Chris Liu, Peng Gao, Aojun Zhou, Xiangfei Hu, Shilin Yan, Pan Lu, Hongsheng Li, Yu Qiao
Abstract: We present LLaMA-Adapter, a lightweight adaption method to efficiently fine-tune LLaMA into an instruction-following model. Using 52K self-instruct demonstrations, LLaMA-Adapter only introduces 1.2M learnable parameters upon the frozen LLaMA 7B model, and costs less than one hour for fine-tuning on 8 A100 GPUs. Specifically, we adopt a set of learnable adaption prompts, and prepend them to the word tokens at higher transformer layers. Then, a zero-initialized attention mechanism with zero gating is proposed, which adaptively injects the new instructional cues into LLaMA, while effectively preserves its pre-trained knowledge. With our efficient training, LLaMA-Adapter can generate high-quality responses, comparable to Alpaca with fully fine-tuned 7B parameters. Besides language commands, our approach can be simply extended to multi-modal instructions for learning image-conditioned LLaMA model, which achieves superior reasoning performance on ScienceQA and COCO Caption benchmarks. Furthermore, we also evaluate the zero-initialized attention mechanism for fine-tuning other pre-trained models (ViT, RoBERTa) on traditional vision and language tasks, demonstrating the superior generalization capacity of our approach. Code is released at https://github.com/OpenGVLab/LLaMA-Adapter.
Authors: Yang Li, Cheng Yu, Guangzhi Sun, Weiqin Zu, Zheng Tian, Ying Wen, Wei Pan, Chao Zhang, Jun Wang, Yang Yang, Fanglei Sun
Abstract: Speech synthesis systems powered by neural networks hold promise for multimedia production, but frequently face issues with producing expressive speech and seamless editing. In response, we present the Cross-Utterance Conditioned Variational Autoencoder speech synthesis (CUC-VAE S2) framework to enhance prosody and ensure natural speech generation. This framework leverages the powerful representational capabilities of pre-trained language models and the re-expression abilities of variational autoencoders (VAEs). The core component of the CUC-VAE S2 framework is the cross-utterance CVAE, which extracts acoustic, speaker, and textual features from surrounding sentences to generate context-sensitive prosodic features, more accurately emulating human prosody generation. We further propose two practical algorithms tailored for distinct speech synthesis applications: CUC-VAE TTS for text-to-speech and CUC-VAE SE for speech editing. The CUC-VAE TTS is a direct application of the framework, designed to generate audio with contextual prosody derived from surrounding texts. On the other hand, the CUC-VAE SE algorithm leverages real mel spectrogram sampling conditioned on contextual information, producing audio that closely mirrors real sound and thereby facilitating flexible speech editing based on text such as deletion, insertion, and replacement. Experimental results on the LibriTTS datasets demonstrate that our proposed models significantly enhance speech synthesis and editing, producing more natural and expressive speech.
Authors: Yanjie Li, Jingyi Liu, Weijun Li, Lina Yu, Min Wu, Wenqiang Li, Meilan Hao, Su Wei, Yusong Deng
Abstract: Mathematical formulas are the crystallization of human wisdom in exploring the laws of nature for thousands of years. Describing the complex laws of nature with a concise mathematical formula is a constant pursuit of scientists and a great challenge for artificial intelligence. This field is called symbolic regression (SR). Symbolic regression was originally formulated as a combinatorial optimization problem, and Genetic Programming (GP) and Reinforcement Learning algorithms were used to solve it. However, GP is sensitive to hyperparameters, and these two types of algorithms are inefficient. To solve this problem, researchers treat the mapping from data to expressions as a translation problem. And the corresponding large-scale pre-trained model is introduced. However, the data and expression skeletons do not have very clear word correspondences as the two languages do. Instead, they are more like two modalities (e.g., image and text). Therefore, in this paper, we proposed MMSR. The SR problem is solved as a pure multi-modal problem, and contrastive learning is also introduced in the training process for modal alignment to facilitate later modal feature fusion. It is worth noting that to better promote the modal feature fusion, we adopt the strategy of training contrastive learning loss and other losses at the same time, which only needs one-step training, instead of training contrastive learning loss first and then training other losses. Because our experiments prove training together can make the feature extraction module and feature fusion module wearing-in better. Experimental results show that compared with multiple large-scale pre-training baselines, MMSR achieves the most advanced results on multiple mainstream datasets including SRBench. Our code is open source at https://github.com/1716757342/MMSR
Authors: Eugene Bagdasarian, Ren Yi, Sahra Ghalebikesabi, Peter Kairouz, Marco Gruteser, Sewoong Oh, Borja Balle, Daniel Ramage
Abstract: The growing use of large language model (LLM)-based conversational agents to manage sensitive user data raises significant privacy concerns. While these agents excel at understanding and acting on context, this capability can be exploited by malicious actors. We introduce a novel threat model where adversarial third-party apps manipulate the context of interaction to trick LLM-based agents into revealing private information not relevant to the task at hand. Grounded in the framework of contextual integrity, we introduce AirGapAgent, a privacy-conscious agent designed to prevent unintended data leakage by restricting the agent's access to only the data necessary for a specific task. Extensive experiments using Gemini, GPT, and Mistral models as agents validate our approach's effectiveness in mitigating this form of context hijacking while maintaining core agent functionality. For example, we show that a single-query context hijacking attack on a Gemini Ultra agent reduces its ability to protect user data from 94% to 45%, while an AirGapAgent achieves 97% protection, rendering the same attack ineffective.
Authors: Jeff Shrager
Abstract: ELIZA, often considered the world's first chatbot, was written by Joseph Weizenbaum in the early 1960s. Weizenbaum did not intend to invent the chatbot, but rather to build a platform for research into human-machine conversation and the important cognitive processes of interpretation and misinterpretation. His purpose was obscured by ELIZA's fame, resulting in large part from the fortuitous timing of it's creation, and it's escape into the wild. In this paper I provide a rich historical context for ELIZA's creation, demonstrating that ELIZA arose from the intersection of some of the central threads in the technical history of AI. I also briefly discuss how ELIZA escaped into the world, and how its accidental escape, along with several coincidental turns of the programming language screws, led both to the misapprehension that ELIZA was intended as a chatbot, and to the loss of the original ELIZA to history for over 50 years.
Authors: Heng Yang, Ke Li
Abstract: The alignment between RNA sequences and structures in foundation models (FMs) has yet to be thoroughly investigated. Existing FMs have struggled to establish sequence-structure alignment, hindering the free flow of genomic information between RNA sequences and structures. In this study, we introduce OmniGenome, an RNA FM trained to align RNA sequences with respect to secondary structures based on structure-contextualised modelling. The alignment enables free and bidirectional mappings between sequences and structures by utilising the flexible RNA modelling paradigm that supports versatile input and output modalities, i.e., sequence and/or structure as input/output. We implement RNA design and zero-shot secondary structure prediction as case studies to evaluate the Seq2Str and Str2Seq mapping capacity of OmniGenome. Results on the EternaV2 benchmark show that OmniGenome solved 74% of puzzles, whereas existing FMs only solved up to 3% of the puzzles due to the oversight of sequence-structure alignment. We leverage four comprehensive in-silico genome modelling benchmarks to evaluate performance across a diverse set of genome downstream tasks, where the results show that OmniGenome achieves state-of-the-art performance on RNA and DNA benchmarks, even without any training on DNA genomes.
Authors: Lefan Zhang, Xiaodan Wang, Yanhua Huang, Ruiwen Xu
Abstract: Speculative sampling is a promising approach to accelerate the decoding stage for Large Language Models (LLMs). Recent advancements that leverage target LLM's contextual information, such as hidden states and KV cache, have shown significant practical improvements. However, these approaches suffer from inconsistent context between training and decoding. We also observe another discrepancy between the training and decoding objectives in existing speculative sampling methods. In this work, we propose a solution named HArmonized Speculative Sampling (HASS) that learns harmonized representations to address these issues. HASS accelerates the decoding stage without adding inference overhead through harmonized objective distillation and harmonized context alignment. Experiments on four LLaMA models demonstrate that HASS achieves 2.81x-4.05x wall-clock time speedup ratio averaging across three datasets, surpassing EAGLE-2 by 8%-20%.
Authors: Zhen Ye, Peiwen Sun, Jiahe Lei, Hongzhan Lin, Xu Tan, Zheqi Dai, Qiuqiang Kong, Jianyi Chen, Jiahao Pan, Qifeng Liu, Yike Guo, Wei Xue
Abstract: Recent advancements in audio generation have been significantly propelled by the capabilities of Large Language Models (LLMs). The existing research on audio LLM has primarily focused on enhancing the architecture and scale of audio language models, as well as leveraging larger datasets, and generally, acoustic codecs, such as EnCodec, are used for audio tokenization. However, these codecs were originally designed for audio compression, which may lead to suboptimal performance in the context of audio LLM. Our research aims to address the shortcomings of current audio LLM codecs, particularly their challenges in maintaining semantic integrity in generated audio. For instance, existing methods like VALL-E, which condition acoustic token generation on text transcriptions, often suffer from content inaccuracies and elevated word error rates (WER) due to semantic misinterpretations of acoustic tokens, resulting in word skipping and errors. To overcome these issues, we propose a straightforward yet effective approach called X-Codec. X-Codec incorporates semantic features from a pre-trained semantic encoder before the Residual Vector Quantization (RVQ) stage and introduces a semantic reconstruction loss after RVQ. By enhancing the semantic ability of the codec, X-Codec significantly reduces WER in speech synthesis tasks and extends these benefits to non-speech applications, including music and sound generation. Our experiments in text-to-speech, music continuation, and text-to-sound tasks demonstrate that integrating semantic information substantially improves the overall performance of language models in audio generation. Our code and demo are available (Demo: https://x-codec-audio.github.io Code: https://github.com/zhenye234/xcodec)
URLs: https://x-codec-audio.github.io, https://github.com/zhenye234/xcodec)
Authors: Nirmalya Thakur
Abstract: The world is currently experiencing an outbreak of mpox, which has been declared a Public Health Emergency of International Concern by WHO. No prior work related to social media mining has focused on the development of a dataset of Instagram posts about the mpox outbreak. The work presented in this paper aims to address this research gap and makes two scientific contributions to this field. First, it presents a multilingual dataset of 60,127 Instagram posts about mpox, published between July 23, 2022, and September 5, 2024. The dataset, available at https://dx.doi.org/10.21227/7fvc-y093, contains Instagram posts about mpox in 52 languages. For each of these posts, the Post ID, Post Description, Date of publication, language, and translated version of the post (translation to English was performed using the Google Translate API) are presented as separate attributes in the dataset. After developing this dataset, sentiment analysis, hate speech detection, and anxiety or stress detection were performed. This process included classifying each post into (i) one of the sentiment classes, i.e., fear, surprise, joy, sadness, anger, disgust, or neutral, (ii) hate or not hate, and (iii) anxiety/stress detected or no anxiety/stress detected. These results are presented as separate attributes in the dataset. Second, this paper presents the results of performing sentiment analysis, hate speech analysis, and anxiety or stress analysis. The variation of the sentiment classes - fear, surprise, joy, sadness, anger, disgust, and neutral were observed to be 27.95%, 2.57%, 8.69%, 5.94%, 2.69%, 1.53%, and 50.64%, respectively. In terms of hate speech detection, 95.75% of the posts did not contain hate and the remaining 4.25% of the posts contained hate. Finally, 72.05% of the posts did not indicate any anxiety/stress, and the remaining 27.95% of the posts represented some form of anxiety/stress.
Authors: Dong Huang, Jie M. Zhang, Mingzhe Du, Mark Harman, Heming Cui
Abstract: Large language models (LLMs) have been widely applied to assist test generation with the source code under test provided as the context. This paper aims to answer the question: If the source code under test is incorrect, will LLMs be misguided when generating tests? The effectiveness of test cases is measured by their accuracy, coverage, and bug detection effectiveness. Our evaluation results with five open- and six closed-source LLMs on four datasets demonstrate that incorrect code can significantly mislead LLMs in generating correct, high-coverage, and bug-revealing tests. For instance, in the HumanEval dataset, LLMs achieve 80.45% test accuracy when provided with task descriptions and correct code, but only 57.12% when given task descriptions and incorrect code. For the APPS dataset, prompts with correct code yield tests that detect 39.85% of the bugs, while prompts with incorrect code detect only 19.61%. These findings have important implications for the deployment of LLM-based testing: using it on mature code may help protect against future regression, but on early-stage immature code, it may simply bake in errors. Our findings also underscore the need for further research to improve LLMs resilience against incorrect code in generating reliable and bug-revealing tests.
Authors: Qiliang Chen, Sepehr Ilami, Nunzio Lore, Babak Heydari
Abstract: This paper introduces a novel framework combining LLM agents as proxies for human strategic behavior with reinforcement learning (RL) to engage these agents in evolving strategic interactions within team environments. Our approach extends traditional agent-based simulations by using strategic LLM agents (SLA) and introducing dynamic and adaptive governance through a pro-social promoting RL agent (PPA) that modulates information access across agents in a network, optimizing social welfare and promoting pro-social behavior. Through validation in iterative games, including the prisoner dilemma, we demonstrate that SLA agents exhibit nuanced strategic adaptations. The PPA agent effectively learns to adjust information transparency, resulting in enhanced cooperation rates. This framework offers significant insights into AI-mediated social dynamics, contributing to the deployment of AI in real-world team settings.