Authors: Gibson Nkhata Shi Yin Hong, Susan Gauch
Abstract: Stance Detection (SD) has become a critical area of interest due to its applications in various contexts leading to increased research within NLP. Yet the subtlety and complexity of texts sourced from online platforms often containing sarcastic language pose significant challenges for SD algorithms in accurately determining the authors stance. This paper addresses this by employing sarcasm for SD. It also tackles the issue of insufficient annotated data for training SD models on new targets by conducting Cross-Target SD (CTSD). The proposed approach involves fine-tuning BERT and RoBERTa models followed by concatenating additional deep learning layers. The approach is assessed against various State-Of-The-Art baselines for SD demonstrating superior performance using publicly available datasets. Notably our model outperforms the best SOTA models on both in-domain SD and CTSD tasks even before the incorporation of sarcasm-detection pre-training. The integration of sarcasm knowledge into the model significantly reduces misclassifications of sarcastic text elements in SD allowing our model to accurately predict 85% of texts that were previously misclassified without sarcasm-detection pre-training on in-domain SD. This enhancement contributes to an increase in the models average macro F1-score. The CTSD task achieves performance comparable to that of the in-domain task despite using a zero-shot finetuning. We also reveal that the success of the transfer-learning framework relies on the correlation between the lexical attributes of sarcasm detection and SD. This study represents the first exploration of sarcasm detection as an intermediate transfer-learning task within the context of SD while also leveraging the concatenation of BERT or RoBERTa with other deep-learning techniques. The proposed approach establishes a foundational baseline for future research in this domain.
Authors: I\~nigo Alonso, Ander Salaberria, Gorka Azkune, Jeremy Barnes, Oier Lopez de Lacalle
Abstract: Cross-modal entity linking refers to the ability to align entities and their attributes across different modalities. While cross-modal entity linking is a fundamental skill needed for real-world applications such as multimodal code generation, fake news detection, or scene understanding, it has not been thoroughly studied in the literature. In this paper, we introduce a new task and benchmark to address this gap. Our benchmark, MATE, consists of 5.5k evaluation instances featuring visual scenes aligned with their textual representations. To evaluate cross-modal entity linking performance, we design a question-answering task that involves retrieving one attribute of an object in one modality based on a unique attribute of that object in another modality. We evaluate state-of-the-art Vision-Language Models (VLMs) and humans on this task, and find that VLMs struggle significantly compared to humans, particularly as the number of objects in the scene increases. Our analysis also shows that, while chain-of-thought prompting can improve VLM performance, models remain far from achieving human-level proficiency. These findings highlight the need for further research in cross-modal entity linking and show that MATE is a strong benchmark to support that progress.
Authors: Emmy Liu, Amanda Bertsch, Lintang Sutawika, Lindia Tjuatja, Patrick Fernandes, Lara Marinov, Michael Chen, Shreya Singhal, Carolin Lawrence, Aditi Raghunathan, Kiril Gashteovski, Graham Neubig
Abstract: Improvements in language model capabilities are often attributed to increasing model size or training data, but in some cases smaller models trained on curated data or with different architectural decisions can outperform larger ones trained on more tokens. What accounts for this? To quantify the impact of these design choices, we meta-analyze 92 open-source pretrained models across a wide array of scales, including state-of-the-art open-weights models as well as less performant models and those with less conventional design decisions. We find that by incorporating features besides model size and number of training tokens, we can achieve a relative 3-28% increase in ability to predict downstream performance compared with using scale alone. Analysis of model design decisions reveal insights into data composition, such as the trade-off between language and code tasks at 15-25\% code, as well as the better performance of some architectural decisions such as choosing rotary over learned embeddings. Broadly, our framework lays a foundation for more systematic investigation of how model development choices shape final capabilities.
Authors: Faiz Surani, Mirac Suzgun, Vyoma Raman, Christopher D. Manning, Peter Henderson, Daniel E. Ho
Abstract: Many jurisdictions have moved to identify and strike these provisions, including California, which mandated in 2021 that all counties implement such a process. Yet the scale can be overwhelming, with Santa Clara County (SCC) alone having over 24 million property deed documents, making purely manual review infeasible. We present a novel approach to addressing this pressing issue, developed through a partnership with the SCC Clerk-Recorder's Office. First, we leverage an open large language model, fine-tuned to detect racial covenants with high precision and recall. We estimate that this system reduces manual efforts by 86,500 person hours and costs less than 2% of the cost for a comparable off-the-shelf closed model. Second, we illustrate the County's integration of this model into responsible operational practice, including legal review and the creation of a historical registry, and release our model to assist the hundreds of jurisdictions engaged in similar efforts. Finally, our results reveal distinct periods of utilization of racial covenants, sharp geographic clustering, and the disproportionate role of a small number of developers in maintaining housing discrimination. We estimate that by 1950, one in four properties across the County were subject to racial covenants.
Authors: Sabur Butt, Hector G. Ceballos, Diana P. Madera
Abstract: Job application and assessment processes have evolved significantly in recent years, largely due to advancements in technology and changes in the way companies operate. Skill extraction and classification remain an important component of the modern hiring process as it provides a more objective way to evaluate candidates and automatically align their skills with the job requirements. However, to effectively evaluate the skills, the skill extraction tools must recognize varied mentions of skills on resumes, including direct mentions, implications, synonyms, acronyms, phrases, and proficiency levels, and differentiate between hard and soft skills. While tools like LLMs (Large Model Models) help extract and categorize skills from job applications, there's a lack of comprehensive datasets for evaluating the effectiveness of these models in accurately identifying and classifying skills in Spanish-language job applications. This gap hinders our ability to assess the reliability and precision of the models, which is crucial for ensuring that the selected candidates truly possess the required skills for the job. In this paper, we develop a Spanish language dataset for skill extraction and classification, provide annotation methodology to distinguish between knowledge, skill, and abilities, and provide deep learning baselines to advance robust solutions for skill classification.
Authors: In Hak Moon
Abstract: This paper presents an in-depth analysis of the performance of seven different Large Language Models (LLMs) in solving a diverse set of math advanced calculus problems. The study aims to evaluate these models' accuracy, reliability, and problem-solving capabilities, including ChatGPT 4o, Gemini Advanced with 1.5 Pro, Copilot Pro, Claude 3.5 Sonnet, Meta AI, Mistral AI, and Perplexity. The assessment was conducted through a series of thirty-two test problems, encompassing a total of 320 points. The problems covered various topics, from vector calculations and geometric interpretations to integral evaluations and optimization tasks. The results highlight significant trends and patterns in the models' performance, revealing both their strengths and weaknesses - for instance, models like ChatGPT 4o and Mistral AI demonstrated consistent accuracy across various problem types, indicating their robustness and reliability in mathematical problem-solving, while models such as Gemini Advanced with 1.5 Pro and Meta AI exhibited specific weaknesses, particularly in complex problems involving integrals and optimization, suggesting areas for targeted improvements. The study also underscores the importance of re-prompting in achieving accurate solutions, as seen in several instances where models initially provided incorrect answers but corrected them upon re-prompting. Overall, this research provides valuable insights into the current capabilities and limitations of LLMs in the domain of math calculus, with the detailed analysis of each model's performance on specific problems offering a comprehensive understanding of their strengths and areas for improvement, contributing to the ongoing development and refinement of LLM technology. The findings are particularly relevant for educators, researchers, and developers seeking to leverage LLMs for educational and practical applications in mathematics.
Authors: Catherine Arnett, Tyler A. Chang, James A. Michaelov, Benjamin K. Bergen
Abstract: While crosslingual transfer is crucial to contemporary language models' multilingual capabilities, how it occurs is not well understood. In this paper, we ask what happens to a monolingual language model when it begins to be trained on a second language. Specifically, we train small bilingual models for which we control the amount of data for each language and the order of language exposure. To find evidence of shared multilingual representations, we turn to structural priming, a method used to study grammatical representations in humans. We first replicate previous crosslingual structural priming results and find that after controlling for training data quantity and language exposure, there are asymmetrical effects across language pairs and directions. We argue that this asymmetry may shape hypotheses about human structural priming effects. We also find that structural priming effects are less robust for less similar language pairs, highlighting potential limitations of crosslingual transfer learning and shared representations for typologically diverse languages.
Authors: Zongqian Li, Ehsan Shareghi, Nigel Collier
Abstract: Large Language Models (LLMs) reasoning processes are challenging to analyze due to their complexity and the lack of organized visualization tools. We present ReasonGraph, a web-based platform for visualizing and analyzing LLM reasoning processes. It supports both sequential and tree-based reasoning methods while integrating with major LLM providers and over fifty state-of-the-art models. ReasonGraph incorporates an intuitive UI with meta reasoning method selection, configurable visualization parameters, and a modular framework that facilitates efficient extension. Our evaluation shows high parsing reliability, efficient processing, and strong usability across various downstream applications. By providing a unified visualization framework, ReasonGraph reduces cognitive load in analyzing complex reasoning paths, improves error detection in logical processes, and enables more effective development of LLM-based applications. The platform is open-source, promoting accessibility and reproducibility in LLM reasoning analysis.
Authors: Jiyue Jiang, Pengan Chen, Jiuming Wang, Dongchen He, Ziqin Wei, Liang Hong, Licheng Zong, Sheng Wang, Qinze Yu, Zixian Ma, Yanyu Chen, Yimin Fan, Xiangyu Shi, Jiawei Sun, Chuan Wu, Yu Li
Abstract: Large language models (LLMs) have become important tools in solving biological problems, offering improvements in accuracy and adaptability over conventional methods. Several benchmarks have been proposed to evaluate the performance of these LLMs. However, current benchmarks can hardly evaluate the performance of these models across diverse tasks effectively. In this paper, we introduce a comprehensive prompting-based benchmarking framework, termed Bio-benchmark, which includes 30 key bioinformatics tasks covering areas such as proteins, RNA, drugs, electronic health records, and traditional Chinese medicine. Using this benchmark, we evaluate six mainstream LLMs, including GPT-4o and Llama-3.1-70b, etc., using 0-shot and few-shot Chain-of-Thought (CoT) settings without fine-tuning to reveal their intrinsic capabilities. To improve the efficiency of our evaluations, we demonstrate BioFinder, a new tool for extracting answers from LLM responses, which increases extraction accuracy by round 30% compared to existing methods. Our benchmark results show the biological tasks suitable for current LLMs and identify specific areas requiring enhancement. Furthermore, we propose targeted prompt engineering strategies for optimizing LLM performance in these contexts. Based on these findings, we provide recommendations for the development of more robust LLMs tailored for various biological applications. This work offers a comprehensive evaluation framework and robust tools to support the application of LLMs in bioinformatics.
Authors: Chenglong Wang, Haoyu Tang, Xiyuan Yang, Yueqi Xie, Jina Suh, Sunayana Sitaram, Junming Huang, Yu Xie, Zhaoya Gong, Xing Xie, Fangzhao Wu
Abstract: As large language models (LLMs) gradually become integral tools for problem solving in daily life worldwide, understanding linguistic inequality is becoming increasingly important. Existing research has primarily focused on static analyses that assess the disparities in the existing knowledge and capabilities of LLMs across languages. However, LLMs are continuously evolving, acquiring new knowledge to generate up-to-date, domain-specific responses. Investigating linguistic inequalities within this dynamic process is, therefore, also essential. In this paper, we explore inequalities in new knowledge learning by LLMs across different languages and four key dimensions: effectiveness, transferability, prioritization, and robustness. Through extensive experiments under two settings (in-context learning and fine-tuning) using both proprietary and open-source models, we demonstrate that low-resource languages consistently face disadvantages across all four dimensions. By shedding light on these disparities, we aim to raise awareness of linguistic inequalities in LLMs' new knowledge learning, fostering the development of more inclusive and equitable future LLMs.
Authors: Xiangnan Chen, Yuancheng Fang, Qian Xiao, Juncheng Li, Jun Lin, Siliang Tang, Yi Yang, Yueting Zhuang
Abstract: Multimodal Large Language Models (MLLMs) have garnered significant attention for their strong visual-semantic understanding. Most existing chart benchmarks evaluate MLLMs' ability to parse information from charts to answer questions.However, they overlook the inherent output biases of MLLMs, where models rely on their parametric memory to answer questions rather than genuinely understanding the chart content. To address this limitation, we introduce a novel Chart Hypothetical Question Answering (HQA) task, which imposes assumptions on the same question to compel models to engage in counterfactual reasoning based on the chart content. Furthermore, we introduce HAI, a human-AI interactive data synthesis approach that leverages the efficient text-editing capabilities of LLMs alongside human expert knowledge to generate diverse and high-quality HQA data at a low cost. Using HAI, we construct Chart-HQA, a challenging benchmark synthesized from publicly available data sources. Evaluation results on 18 MLLMs of varying model sizes reveal that current models face significant generalization challenges and exhibit imbalanced reasoning performance on the HQA task.
Authors: Runtao Zhou, Guangya Wan, Saadia Gabriel, Sheng Li, Alexander J Gates, Maarten Sap, Thomas Hartvigsen
Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning tasks, leading to their widespread deployment. However, recent studies have highlighted concerning biases in these models, particularly in their handling of dialectal variations like African American English (AAE). In this work, we systematically investigate dialectal disparities in LLM reasoning tasks. We develop an experimental framework comparing LLM performance given Standard American English (SAE) and AAE prompts, combining LLM-based dialect conversion with established linguistic analyses. We find that LLMs consistently produce less accurate responses and simpler reasoning chains and explanations for AAE inputs compared to equivalent SAE questions, with disparities most pronounced in social science and humanities domains. These findings highlight systematic differences in how LLMs process and reason about different language varieties, raising important questions about the development and deployment of these systems in our multilingual and multidialectal world. Our code repository is publicly available at https://github.com/Runtaozhou/dialect_bias_eval.
Authors: Zichong Li, Xinyu Feng, Yuheng Cai, Zixuan Zhang, Tianyi Liu, Chen Liang, Weizhu Chen, Haoyu Wang, Tuo Zhao
Abstract: Large Language Models (LLMs) have shown remarkable capabilities across tasks, yet they often require additional prompting techniques when facing complex problems. While approaches like self-correction and response selection have emerged as popular solutions, recent studies have shown these methods perform poorly when relying on the LLM itself to provide feedback or selection criteria. We argue this limitation stems from the fact that common LLM post-training procedures lack explicit supervision for discriminative judgment tasks. In this paper, we propose Generative Self-Aggregation (GSA), a novel prompting method that improves answer quality without requiring the model's discriminative capabilities. GSA first samples multiple diverse responses from the LLM, then aggregates them to obtain an improved solution. Unlike previous approaches, our method does not require the LLM to correct errors or compare response quality; instead, it leverages the model's generative abilities to synthesize a new response based on the context of multiple samples. While GSA shares similarities with the self-consistency (SC) approach for response aggregation, SC requires specific verifiable tokens to enable majority voting. In contrast, our approach is more general and can be applied to open-ended tasks. Empirical evaluation demonstrates that GSA effectively improves response quality across various tasks, including mathematical reasoning, knowledge-based problems, and open-ended generation tasks such as code synthesis and conversational responses.
Authors: Erik Jones, Arjun Patrawala, Jacob Steinhardt
Abstract: Humans often rely on subjective natural language to direct language models (LLMs); for example, users might instruct the LLM to write an enthusiastic blogpost, while developers might train models to be helpful and harmless using LLM-based edits. The LLM's operational semantics of such subjective phrases -- how it adjusts its behavior when each phrase is included in the prompt -- thus dictates how aligned it is with human intent. In this work, we uncover instances of misalignment between LLMs' actual operational semantics and what humans expect. Our method, TED (thesaurus error detector), first constructs a thesaurus that captures whether two phrases have similar operational semantics according to the LLM. It then elicits failures by unearthing disagreements between this thesaurus and a human-constructed reference. TED routinely produces surprising instances of misalignment; for example, Mistral 7B Instruct produces more harassing outputs when it edits text to be witty, and Llama 3 8B Instruct produces dishonest articles when instructed to make the articles enthusiastic. Our results demonstrate that humans can uncover unexpected LLM behavior by scrutinizing relationships between abstract concepts, without supervising outputs directly.
Authors: Jiyue Jiang, Zikang Wang, Yuheng Shan, Heyan Chai, Jiayi Li, Zixian Ma, Xinrui Zhang, Yu Li
Abstract: Large Language models (LLMs) have emerged as powerful tools for addressing challenges across diverse domains. Notably, recent studies have demonstrated that large language models significantly enhance the efficiency of biomolecular analysis and synthesis, attracting widespread attention from academics and medicine. In this paper, we systematically investigate the application of prompt-based methods with LLMs to biological sequences, including DNA, RNA, proteins, and drug discovery tasks. Specifically, we focus on how prompt engineering enables LLMs to tackle domain-specific problems, such as promoter sequence prediction, protein structure modeling, and drug-target binding affinity prediction, often with limited labeled data. Furthermore, our discussion highlights the transformative potential of prompting in bioinformatics while addressing key challenges such as data scarcity, multimodal fusion, and computational resource limitations. Our aim is for this paper to function both as a foundational primer for newcomers and a catalyst for continued innovation within this dynamic field of study.
Authors: Xue Han, Qian Hu, Yitong Wang, Wenchun Gao, Lianlian Zhang, Qing Wang, Lijun Mei, Chao Deng, Junlan Feng
Abstract: Large language models (LLMs) suffer from temporal misalignment issues especially across long span of time. The issue arises from knowing that LLMs are trained on large amounts of data where temporal information is rather sparse over long times, such as thousands of years, resulting in insufficient learning or catastrophic forgetting by the LLMs. This paper proposes a methodology named "Ticktack" for addressing the LLM's long-time span misalignment in a yearly setting. Specifically, we first propose to utilize the sexagenary year expression instead of the Gregorian year expression employed by LLMs, achieving a more uniform distribution in yearly granularity. Then, we employ polar coordinates to model the sexagenary cycle of 60 terms and the year order within each term, with additional temporal encoding to ensure LLMs understand them. Finally, we present a temporal representational alignment approach for post-training LLMs that effectively distinguishes time points with relevant knowledge, hence improving performance on time-related tasks, particularly over a long period. We also create a long time span benchmark for evaluation. Experimental results prove the effectiveness of our proposal.
Authors: Chi Hang, Ruiqi Deng, Lavender Yao Jiang, Zihao Yang, Anton Alyakin, Daniel Alber, Eric Karl Oermann
Abstract: Clinical measurements such as blood pressures and respiration rates are critical in diagnosing and monitoring patient outcomes. It is an important component of biomedical data, which can be used to train transformer-based language models (LMs) for improving healthcare delivery. It is, however, unclear whether LMs can effectively interpret and use clinical measurements. We investigate two questions: First, can LMs effectively leverage clinical measurements to answer related medical questions? Second, how to enhance an LM's performance on medical question-answering (QA) tasks that involve measurements? We performed a case study on blood pressure readings (BPs), a vital sign routinely monitored by medical professionals. We evaluated the performance of four LMs: BERT, BioBERT, MedAlpaca, and GPT-3.5, on our newly developed dataset, BPQA (Blood Pressure Question Answering). BPQA contains $100$ medical QA pairs that were verified by medical students and designed to rely on BPs . We found that GPT-3.5 and MedAlpaca (larger and medium sized LMs) benefit more from the inclusion of BPs than BERT and BioBERT (small sized LMs). Further, augmenting measurements with labels improves the performance of BioBERT and Medalpaca (domain specific LMs), suggesting that retrieval may be useful for improving domain-specific LMs.
Authors: R. Patrick Xian, Qiming Cui, Stefan Bauer, Reza Abbasi-Asl
Abstract: Temporal progression is an integral part of knowledge accumulation and update. Web search is frequently adopted as grounding for agent knowledge, yet its inappropriate configuration affects the quality of agent responses. Here, we construct a tool-based out-of-sample testing framework to measure the knowledge variability of large language model (LLM) agents from distinct date-controlled tools (DCTs). We demonstrate the temporal effects of an LLM agent as a writing assistant, which can use web search to help complete scientific publication abstracts. We show that temporal effects of the search engine translates into tool-dependent agent performance but can be alleviated with base model choice and explicit reasoning instructions such as chain-of-thought prompting. Our results indicate that agent evaluation should take a dynamical view and account for the temporal influence of tools and the updates of external resources.
Authors: Bin Chen, Yu Zhang, Hongfei Ye, Ziyi Huang, Hongyang Chen
Abstract: Few-shot multimodal dialogue intention recognition is a critical challenge in the e-commerce domainn. Previous methods have primarily enhanced model classification capabilities through post-training techniques. However, our analysis reveals that training for few-shot multimodal dialogue intention recognition involves two interconnected tasks, leading to a seesaw effect in multi-task learning. This phenomenon is attributed to knowledge interference stemming from the superposition of weight matrix updates during the training process. To address these challenges, we propose Knowledge-Decoupled Synergetic Learning (KDSL), which mitigates these issues by utilizing smaller models to transform knowledge into interpretable rules, while applying the post-training of larger models. By facilitating collaboration between the large and small multimodal large language models for prediction, our approach demonstrates significant improvements. Notably, we achieve outstanding results on two real Taobao datasets, with enhancements of 6.37\% and 6.28\% in online weighted F1 scores compared to the state-of-the-art method, thereby validating the efficacy of our framework.
Authors: Ziyi Yang, Fanqi Wan, Longguang Zhong, Canbin Huang, Guosheng Liang, Xiaojun Quan
Abstract: We introduce FuseChat-3.0, a suite of large language models (LLMs) developed by integrating the strengths of heterogeneous source LLMs into more compact target LLMs. Our source models include the powerful Gemma-2-27B-it, Mistral-Large-Instruct-2407, Qwen-2.5-72B-Instruct, and Llama-3.1-70B-Instruct. For target models, we focus on three widely-used smaller variants-Llama-3.1-8B-Instruct, Gemma-2-9B-it, and Qwen-2.5-7B-Instruct-along with two ultra-compact options, Llama-3.2-3B-Instruct and Llama-3.2-1B-Instruct. To leverage the diverse capabilities of these source models, we develop a specialized data construction protocol tailored to various tasks and domains. The FuseChat-3.0 training pipeline consists of two key stages: (1) supervised fine-tuning (SFT) to align the target and source model distributions, and (2) Direct Preference Optimization (DPO) to apply preferences from multiple source LLMs to fine-tune the target model. The resulting FuseChat-3.0 models exhibit significant performance gains across tasks such as instruction following, general knowledge, mathematics, and coding. As illustrated in Figure 1, using Llama-3.1-8B-Instruct as the target model, our fusion approach achieves an average improvement of 6.8 points across 14 benchmarks. Moreover, it demonstrates remarkable gains of 37.1 points and 30.1 points on the instruction-following benchmarks AlpacaEval-2 and Arena-Hard, respectively. Our code, models, and datasets are available at https://github.com/SLIT-AI/FuseChat-3.0.
Authors: Jie He, Bo Peng, Yi Liao, Qun Liu, Deyi Xiong
Abstract: In order to deeply understand the capability of pretrained language models in text generation and conduct a diagnostic evaluation, we propose TGEA, an error-annotated dataset with multiple benchmark tasks for text generation from pretrained language models (PLMs). We use carefully selected prompt words to guide GPT-2 to generate candidate sentences, from which we select 47K for error annotation. Crowdsourced workers manually check each of these sentences and detect 12k erroneous sentences. We create an error taxonomy to cover 24 types of errors occurring in these erroneous sentences according to the nature of errors with respect to linguistics and knowledge (eg, common sense). For each erroneous span in PLM-generated sentences, we also detect another span that is closely associated with it. Each error is hence manually labeled with comprehensive annotations, including the span of the error, the associated span, minimal correction to the error, the type of the error, and rationale behind the error. Apart from the fully annotated dataset, we also present a detailed description of the data collection procedure, statistics and analysis of the dataset. This is the first dataset with comprehensive annotations for PLM-generated texts, which facilitates the diagnostic evaluation of PLM-based text generation. Furthermore, we use TGEA as a benchmark dataset and propose a series of automatic diagnosis tasks, including error detection, error type classification, associated span detection, error rationale generation, to further promote future study on the automatic error detection and correction on texts generated by pretrained language models.
Authors: Ruizhe Chen, Wenhao Chai, Zhifei Yang, Xiaotian Zhang, Joey Tianyi Zhou, Tony Quek, Soujanya Poria, Zuozhu Liu
Abstract: Inference-time alignment provides an efficient alternative for aligning LLMs with humans. However, these approaches still face challenges, such as limited scalability due to policy-specific value functions and latency during the inference phase. In this paper, we propose a novel approach, Diffusion-styled Preference Optimization (\model), which provides an efficient and policy-agnostic solution for aligning LLMs with humans. By directly performing alignment at sentence level, \model~avoids the time latency associated with token-level generation. Designed as a plug-and-play module, \model~can be seamlessly integrated with various base models to enhance their alignment. Extensive experiments on AlpacaEval 2, MT-bench, and HH-RLHF demonstrate that \model~achieves superior alignment performance across various settings, achieving a favorable trade-off between alignment quality and inference-time latency. Furthermore, \model~demonstrates model-agnostic scalability, significantly improving the performance of large models such as Llama-3-70B.
Authors: Yana van de Sande, Gunes A\c{c}ar, Thabo van Woudenberg, Martha Larson
Abstract: We study LLM judgments of misinformation expressed with uncertainty. Our experiments study the response of three widely used LLMs (GPT-4o, LlaMA3, DeepSeek-v2) to misinformation propositions that have been verified false and then are transformed into uncertain statements according to an uncertainty typology. Our results show that after transformation, LLMs change their factchecking classification from false to not-false in 25% of the cases. Analysis reveals that the change cannot be explained by predictors to which humans are expected to be sensitive, i.e., modality, linguistic cues, or argumentation strategy. The exception is doxastic transformations, which use linguistic cue phrases such as "It is believed ...".To gain further insight, we prompt the LLM to make another judgment about the transformed misinformation statements that is not related to truth value. Specifically, we study LLM estimates of the frequency with which people make the uncertain statement. We find a small but significant correlation between judgment of fact and estimation of frequency.
Authors: Muhammad Amien Ibrahim, Faisal, Tora Sangputra Yopie Winarto, Zefanya Delvin Sulistiya
Abstract: Detecting gender-based hate speech in Indonesian social media remains challenging due to limited labeled datasets. While binary hate speech classification has advanced, a more granular category like gender-targeted hate speech is understudied because of class imbalance issues. This paper addresses this gap by comparing three data augmentation techniques for Indonesian gender-based hate speech detection. We evaluate backtranslation, single-class prompt generation (using only hate speech examples), and our proposed dual-class prompt generation (using both hate speech and non-hate speech examples). Experiments show all augmentation methods improve classification performance, with our dual-class approach achieving the best results (88.5% accuracy, 88.1% F1-score using Random Forest). Semantic similarity analysis reveals dual-class prompt generation produces the most novel content, while T-SNE visualizations confirm these samples occupy distinct feature space regions while maintaining class characteristics. Our findings suggest that incorporating examples from both classes helps language models generate more diverse yet representative samples, effectively addressing limited data challenges in specialized hate speech detection.
Authors: Dilek K\"u\c{c}\"uk, Fazli Can
Abstract: Recent developments in computer science and artificial intelligence have also contributed to the legal domain, as revealed by the number and range of related publications and applications. Machine and deep learning models require considerable amount of domain-specific data for training and comparison purposes, in order to attain high-performance in the legal domain. Additionally, semantic resources such as ontologies are valuable for building large-scale computational legal systems, in addition to ensuring interoperability of such systems. Considering these aspects, we present an up-to-date review of the literature on datasets, benchmarks, and ontologies proposed for computational law. We believe that this comprehensive and recent review will help researchers and practitioners when developing and testing approaches and systems for computational law.
Authors: Tadej \v{S}kvorc, Marko Robnik-\v{S}ikonja
Abstract: Many less-resourced languages struggle with a lack of large, task-specific datasets that are required for solving relevant tasks with modern transformer-based large language models (LLMs). On the other hand, many linguistic resources, such as dictionaries, are rarely used in this context despite their large information contents. We show how LLMs can be used to extend existing language resources in less-resourced languages for two important tasks: word-sense disambiguation (WSD) and word-sense induction (WSI). We approach the two tasks through the related but much more accessible word-in-context (WiC) task where, given a pair of sentences and a target word, a classification model is tasked with predicting whether the sense of a given word differs between sentences. We demonstrate that a well-trained model for this task can distinguish between different word senses and can be adapted to solve the WSD and WSI tasks. The advantage of using the WiC task, instead of directly predicting senses, is that the WiC task does not need pre-constructed sense inventories with a sufficient number of examples for each sense, which are rarely available in less-resourced languages. We show that sentence pairs for the WiC task can be successfully generated from dictionary examples using LLMs. The resulting prediction models outperform existing models on WiC, WSD, and WSI tasks. We demonstrate our methodology on the Slovene language, where a monolingual dictionary is available, but word-sense resources are tiny.
Authors: Wenhong Zhu, Weinan Zhang, Rui Wang
Abstract: Post-training alignment has increasingly become a crucial factor in enhancing the usability of language models (LMs). However, the strength of alignment varies depending on individual preferences. This paper proposes a method to incorporate alignment control into a single model, referred to as CLM. This approach adds one identity layer preceding the initial layers and performs preference learning only on this layer to map unaligned input token embeddings into the aligned space. Experimental results demonstrate that this efficient fine-tuning method performs comparable to full fine-tuning. During inference, the input embeddings are processed through the aligned and unaligned layers, which are then merged through the interpolation coefficient. By controlling this parameter, the alignment exhibits a clear interpolation and extrapolation phenomenon.
Authors: Zhenghua Wang, Yiran Ding, Changze Lv, Zhibo Xu, Tianlong Li, Tianyuan Shi, Xiaoqing Zheng, Xuanjing Huang
Abstract: Although large language models (LLMs) have achieved significant progress in handling long-context inputs, they still suffer from the ``lost-in-the-middle'' problem, where crucial information in the middle of the context is often underrepresented or lost. Our extensive experiments reveal that this issue may arise from the rapid long-term decay in Rotary Position Embedding (RoPE). To address this problem, we propose a layer-specific positional encoding scaling method that assigns distinct scaling factors to each layer, slowing down the decay rate caused by RoPE to make the model pay more attention to the middle context. A specially designed genetic algorithm is employed to efficiently select the optimal scaling factors for each layer by incorporating Bezier curves to reduce the search space. Through comprehensive experimentation, we demonstrate that our method significantly alleviates the ``lost-in-the-middle'' problem. Our approach results in an average accuracy improvement of up to 20% on the Key-Value Retrieval dataset. Furthermore, we show that layer-specific interpolation, as opposed to uniform interpolation across all layers, enhances the model's extrapolation capabilities when combined with PI and Dynamic-NTK positional encoding schemes.
Authors: Jiayi Chang, Mingqi Gao, Xinyu Hu, Xiaojun Wan
Abstract: Previous research has shown that LLMs have potential in multilingual NLG evaluation tasks. However, existing research has not fully explored the differences in the evaluation capabilities of LLMs across different languages. To this end, this study provides a comprehensive analysis of the multilingual evaluation performance of 10 recent LLMs, spanning high-resource and low-resource languages through correlation analysis, perturbation attacks, and fine-tuning. We found that 1) excluding the reference answer from the prompt and using large-parameter LLM-based evaluators leads to better performance across various languages; 2) most LLM-based evaluators show a higher correlation with human judgments in high-resource languages than in low-resource languages; 3) in the languages where they are most sensitive to such attacks, they also tend to exhibit the highest correlation with human judgments; and 4) fine-tuning with data from a particular language yields a broadly consistent enhancement in the model's evaluation performance across diverse languages. Our findings highlight the imbalance in LLMs'evaluation capabilities across different languages and suggest that low-resource language scenarios deserve more attention.
Authors: Yafu Li, Ronghao Zhang, Zhilin Wang, Huajian Zhang, Leyang Cui, Yongjing Yin, Tong Xiao, Yue Zhang
Abstract: Large language models (LLMs) have achieved remarkable success in machine translation, demonstrating impressive performance across diverse languages. However, translationese, characterized by overly literal and unnatural translations, remains a persistent challenge in LLM-based translation systems. Despite their pre-training on vast corpora of natural utterances, LLMs exhibit translationese errors and generate unexpected unnatural translations, stemming from biases introduced during supervised fine-tuning (SFT). In this work, we systematically evaluate the prevalence of translationese in LLM-generated translations and investigate its roots during supervised training. We introduce methods to mitigate these biases, including polishing golden references and filtering unnatural training instances. Empirical evaluations demonstrate that these approaches significantly reduce translationese while improving translation naturalness, validated by human evaluations and automatic metrics. Our findings highlight the need for training-aware adjustments to optimize LLM translation outputs, paving the way for more fluent and target-language-consistent translations. We release the data and code at https://github.com/yafuly/LLM_Translationese.
Authors: Orfeas Menis Mastromichalakis, Giorgos Filandrianos, Maria Symeonaki, Giorgos Stamou
Abstract: Machine Translation (MT) systems frequently encounter ambiguous scenarios where they must assign gender to certain occupations when translating without explicit guidance or contextual cues. While individual translations in such cases may not be inherently biased, systematic patterns-such as the repeated association of certain professions with specific genders-can emerge, reflecting and perpetuating societal stereotypes. This ambiguity challenges traditional instance-level single-answer evaluation approaches, as no single gold standard translation exists. To address this, we propose an approach that evaluates gender bias through aggregated model responses. Specifically, we introduce a methodology to detect gender imbalances between source texts and translations, a benchmarking dataset with ambiguous English inputs, and probability-based metrics to quantify a model's divergence from normative standards or reference distributions.
Authors: Zhilin Wang, Jiaqi Zeng, Olivier Delalleau, Daniel Egert, Ellie Evans, Hoo-Chang Shin, Felipe Soares, Yi Dong, Oleksii Kuchaiev
Abstract: Inference-Time Scaling has been critical to the success of recent models such as OpenAI o1 and DeepSeek R1. However, many techniques used to train models for inference-time scaling require tasks to have answers that can be verified, limiting their application to domains such as math, coding and logical reasoning. We take inspiration from how humans make first attempts, ask for detailed feedback from others and make improvements based on such feedback across a wide spectrum of open-ended endeavors. To this end, we collect data for and train dedicated Feedback and Edit Models that are capable of performing inference-time scaling for open-ended general-domain tasks. In our setup, one model generates an initial response, which are given feedback by a second model, that are then used by a third model to edit the response. We show that performance on Arena Hard, a benchmark strongly predictive of Chatbot Arena Elo can be boosted by scaling the number of initial response drafts, effective feedback and edited responses. When scaled optimally, our setup based on 70B models from the Llama 3 family can reach SoTA performance on Arena Hard at 92.7 as of 5 Mar 2025, surpassing OpenAI o1-preview-2024-09-12 with 90.4 and DeepSeek R1 with 92.3.
Authors: Cheng-Han Chiang, Hung-yi Lee, Michal Lukasik
Abstract: The LLM-as-a-judge paradigm uses large language models (LLMs) for automated text evaluation, where a numerical assessment is assigned by an LLM to the input text following scoring rubrics. Existing methods for LLM-as-a-judge use cross-entropy (CE) loss for fine-tuning, which neglects the numeric nature of score prediction. Recent work addresses numerical prediction limitations of LLM fine-tuning through regression-aware fine-tuning, which, however, does not consider chain-of-thought (CoT) reasoning for score prediction. In this paper, we introduce TRACT (Two-stage Regression-Aware fine-tuning with CoT), a method combining CoT reasoning with regression-aware training. TRACT consists of two stages: first, seed LLM is fine-tuned to generate CoTs, which serve as supervision for the second stage fine-tuning. The training objective of TRACT combines the CE loss for learning the CoT reasoning capabilities, and the regression-aware loss for the score prediction. Experiments across four LLM-as-a-judge datasets and two LLMs show that TRACT significantly outperforms existing methods. Extensive ablation studies validate the importance of each component in TRACT.
Authors: Shahar Levy, Nir Mazor, Lihi Shalmon, Michael Hassid, Gabriel Stanovsky
Abstract: Retrieval-augmented generation (RAG) provides LLMs with relevant documents. Although previous studies noted that retrieving many documents can degrade performance, they did not isolate how the quantity of documents affects performance while controlling for context length. We evaluate various language models on custom datasets derived from a multi-hop QA task. We keep the context length and position of relevant information constant while varying the number of documents, and find that increasing the document count in RAG settings poses significant challenges for LLMs. Additionally, our results indicate that processing multiple documents is a separate challenge from handling long contexts. We also make the datasets and code available: https://github.com/shaharl6000/MoreDocsSameLen .
Authors: Tom Kouwenhoven, Max Peeperkorn, Roy de Kleijn, Tessa Verhoef
Abstract: Languages are shaped by the inductive biases of their users. Using a classical referential game, we investigate how artificial languages evolve when optimised for inductive biases in humans and large language models (LLMs) via Human-Human, LLM-LLM and Human-LLM experiments. We show that referentially grounded vocabularies emerge that enable reliable communication in all conditions, even when humans and LLMs collaborate. Comparisons between conditions reveal that languages optimised for LLMs subtly differ from those optimised for humans. Interestingly, interactions between humans and LLMs alleviate these differences and result in vocabularies which are more human-like than LLM-like. These findings advance our understanding of how inductive biases in LLMs play a role in the dynamic nature of human language and contribute to maintaining alignment in human and machine communication. In particular, our work underscores the need to think of new methods that include human interaction in the training processes of LLMs, and shows that using communicative success as a reward signal can be a fruitful, novel direction.
Authors: Xinyi He, Yihao Liu, Mengyu Zhou, Yeye He, Haoyu Dong, Shi Han, Zejian Yuan, Dongmei Zhang
Abstract: Tabular data are crucial in many fields and their understanding by large language models (LLMs) under high parameter efficiency paradigm is important. However, directly applying parameter-efficient fine-tuning (PEFT) techniques to tabular tasks presents significant challenges, particularly in terms of better table serialization and the representation of two-dimensional structured information within a one-dimensional sequence. To address this, we propose TableLoRA, a module designed to improve LLMs' understanding of table structure during PEFT. It incorporates special tokens for serializing tables with special token encoder and uses 2D LoRA to encode low-rank information on cell positions. Experiments on four tabular-related datasets demonstrate that TableLoRA consistently outperforms vanilla LoRA and surpasses various table encoding methods tested in control experiments. These findings reveal that TableLoRA, as a table-specific LoRA, enhances the ability of LLMs to process tabular data effectively, especially in low-parameter settings, demonstrating its potential as a robust solution for handling table-related tasks.
Authors: Sanjib Narzary, Bihung Brahma, Haradip Mahilary, Mahananda Brahma, Bidisha Som, Sukumar Nandi
Abstract: Named Entity Recognition (NER) and Part-of-Speech (POS) tagging are critical tasks for Natural Language Processing (NLP), yet their availability for low-resource languages (LRLs) like Bodo remains limited. This article presents a comparative empirical study investigating the effectiveness of Google's Gemini 2.0 Flash Thinking Experiment model for zero-shot cross-lingual transfer of POS and NER tagging to Bodo. We explore two distinct methodologies: (1) direct translation of English sentences to Bodo followed by tag transfer, and (2) prompt-based tag transfer on parallel English-Bodo sentence pairs. Both methods leverage the machine translation and cross-lingual understanding capabilities of Gemini 2.0 Flash Thinking Experiment to project English POS and NER annotations onto Bodo text in CONLL-2003 format. Our findings reveal the capabilities and limitations of each approach, demonstrating that while both methods show promise for bootstrapping Bodo NLP, prompt-based transfer exhibits superior performance, particularly for NER. We provide a detailed analysis of the results, highlighting the impact of translation quality, grammatical divergences, and the inherent challenges of zero-shot cross-lingual transfer. The article concludes by discussing future research directions, emphasizing the need for hybrid approaches, few-shot fine-tuning, and the development of dedicated Bodo NLP resources to achieve high-accuracy POS and NER tagging for this low-resource language.
Authors: Hyunwoo Yoo
Abstract: This study demonstrates that generative large language models can be utilized in a more flexible manner for DNA sequence analysis and classification tasks compared to traditional transformer encoder-based models. While recent encoder-based models such as DNABERT and Nucleotide Transformer have shown significant performance in DNA sequence classification, transformer decoder-based generative models have not yet been extensively explored in this field. This study evaluates how effectively generative Large Language Models handle DNA sequences with various labels and analyzes performance changes when additional textual information is provided. Experiments were conducted on antimicrobial resistance genes, and the results show that generative Large Language Models can offer comparable or potentially better predictions, demonstrating flexibility and accuracy when incorporating both sequence and textual information. The code and data used in this work are available at the following GitHub repository: https://github.com/biocomgit/llm4dna.
Authors: Yifei Yuan, Anders S{\o}gaard
Abstract: Li et al. (2023) used the Othello board game as a test case for the ability of GPT-2 to induce world models, and were followed up by Nanda et al. (2023b). We briefly discuss the original experiments, expanding them to include more language models with more comprehensive probing. Specifically, we analyze sequences of Othello board states and train the model to predict the next move based on previous moves. We evaluate seven language models (GPT-2, T5, Bart, Flan-T5, Mistral, LLaMA-2, and Qwen2.5) on the Othello task and conclude that these models not only learn to play Othello, but also induce the Othello board layout. We find that all models achieve up to 99% accuracy in unsupervised grounding and exhibit high similarity in the board features they learned. This provides considerably stronger evidence for the Othello World Model Hypothesis than previous works.
Authors: Owen Cook, Yida Mu, Xinye Yang, Xingyi Song, Kalina Bontcheva
Abstract: Framing is an essential device in news reporting, allowing the writer to influence public perceptions of current affairs. While there are existing automatic news framing detection datasets in various languages, none of them focus on news framing in the Chinese language which has complex character meanings and unique linguistic features. This study introduces the first Chinese News Framing dataset, to be used as either a stand-alone dataset or a supplementary resource to the SemEval-2023 task 3 dataset. We detail its creation and we run baseline experiments to highlight the need for such a dataset and create benchmarks for future research, providing results obtained through fine-tuning XLM-RoBERTa-Base and using GPT-4o in the zero-shot setting. We find that GPT-4o performs significantly worse than fine-tuned XLM-RoBERTa across all languages. For the Chinese language, we obtain an F1-micro (the performance metric for SemEval task 3, subtask 2) score of 0.719 using only samples from our Chinese News Framing dataset and a score of 0.753 when we augment the SemEval dataset with Chinese news framing samples. With positive news frame detection results, this dataset is a valuable resource for detecting news frames in the Chinese language and is a valuable supplement to the SemEval-2023 task 3 dataset.
Authors: Micha{\l} Dolina, Jakub Dec, Stanis{\l}aw Dro\.zd\.z, Jaros{\l}aw Kwapie\'n, Jin Liu, Tomasz Stanisz
Abstract: Recent research shows that punctuation patterns in texts exhibit universal features across languages. Analysis of Western classical literature reveals that the distribution of spaces between punctuation marks aligns with a discrete Weibull distribution, typically used in survival analysis. By extending this analysis to Chinese literature represented here by three notable contemporary works, it is shown that Zipf's law applies to Chinese texts similarly to Western texts, where punctuation patterns also improve adherence to the law. Additionally, the distance distribution between punctuation marks in Chinese texts follows the Weibull model, though larger spacing is less frequent than in English translations. Sentence-ending punctuation, representing sentence length, diverges more from this pattern, reflecting greater flexibility in sentence length. This variability supports the formation of complex, multifractal sentence structures, particularly evident in Gao Xingjian's "Soul Mountain". These findings demonstrate that both Chinese and Western texts share universal punctuation and word distribution patterns, underscoring their broad applicability across languages.
Authors: Van Bach Nguyen, Christin Seifert, J\"org Schl\"otterer
Abstract: The need for interpretability in deep learning has driven interest in counterfactual explanations, which identify minimal changes to an instance that change a model's prediction. Current counterfactual (CF) generation methods require task-specific fine-tuning and produce low-quality text. Large Language Models (LLMs), though effective for high-quality text generation, struggle with label-flipping counterfactuals (i.e., counterfactuals that change the prediction) without fine-tuning. We introduce two simple classifier-guided approaches to support counterfactual generation by LLMs, eliminating the need for fine-tuning while preserving the strengths of LLMs. Despite their simplicity, our methods outperform state-of-the-art counterfactual generation methods and are effective across different LLMs, highlighting the benefits of guiding counterfactual generation by LLMs with classifier information. We further show that data augmentation by our generated CFs can improve a classifier's robustness. Our analysis reveals a critical issue in counterfactual generation by LLMs: LLMs rely on parametric knowledge rather than faithfully following the classifier.
Authors: Dimitri von R\"utte, Janis Fluri, Yuhui Ding, Antonio Orvieto, Bernhard Sch\"olkopf, Thomas Hofmann
Abstract: While state-of-the-art language models achieve impressive results through next-token prediction, they have inherent limitations such as the inability to revise already generated tokens. This has prompted exploration of alternative approaches such as discrete diffusion. However, masked diffusion, which has emerged as a popular choice due to its simplicity and effectiveness, reintroduces this inability to revise words. To overcome this, we generalize masked diffusion and derive the theoretical backbone of a family of general interpolating discrete diffusion (GIDD) processes offering greater flexibility in the design of the noising processes. Leveraging a novel diffusion ELBO, we achieve compute-matched state-of-the-art performance in diffusion language modeling. Exploiting GIDD's flexibility, we explore a hybrid approach combining masking and uniform noise, leading to improved sample quality and unlocking the ability for the model to correct its own mistakes, an area where autoregressive models notoriously have struggled. Our code and models are open-source: https://github.com/dvruette/gidd/
Authors: Zhenyu Wang, Zikang Wang, Jiyue Jiang, Pengan Chen, Xiangyu Shi, Yu Li
Abstract: Large Language Models (LLMs) are revolutionizing bioinformatics, enabling advanced analysis of DNA, RNA, proteins, and single-cell data. This survey provides a systematic review of recent advancements, focusing on genomic sequence modeling, RNA structure prediction, protein function inference, and single-cell transcriptomics. Meanwhile, we also discuss several key challenges, including data scarcity, computational complexity, and cross-omics integration, and explore future directions such as multimodal learning, hybrid AI models, and clinical applications. By offering a comprehensive perspective, this paper underscores the transformative potential of LLMs in driving innovations in bioinformatics and precision medicine.
Authors: Wenke Huang, Jian Liang, Xianda Guo, Yiyang Fang, Guancheng Wan, Xuankun Rong, Chi Wen, Zekun Shi, Qingyun Li, Didi Zhu, Yanbiao Ma, Ke Liang, Bin Yang, He Li, Jiawei Shao, Mang Ye, Bo Du
Abstract: Multi-modal Large Language Models (MLLMs) integrate visual and linguistic reasoning to address complex tasks such as image captioning and visual question answering. While MLLMs demonstrate remarkable versatility, MLLMs appears limited performance on special applications. But tuning MLLMs for downstream tasks encounters two key challenges: Task-Expert Specialization, where distribution shifts between pre-training and target datasets constrain target performance, and Open-World Stabilization, where catastrophic forgetting erases the model general knowledge. In this work, we systematically review recent advancements in MLLM tuning methodologies, classifying them into three paradigms: (I) Selective Tuning, (II) Additive Tuning, and (III) Reparameterization Tuning. Furthermore, we benchmark these tuning strategies across popular MLLM architectures and diverse downstream tasks to establish standardized evaluation analysis and systematic tuning principles. Finally, we highlight several open challenges in this domain and propose future research directions. To facilitate ongoing progress in this rapidly evolving field, we provide a public repository that continuously tracks developments: https://github.com/WenkeHuang/Awesome-MLLM-Tuning.
Authors: Zhipeng Chen, Yingqian Min, Beichen Zhang, Jie Chen, Jinhao Jiang, Daixuan Cheng, Wayne Xin Zhao, Zheng Liu, Xu Miao, Yang Lu, Lei Fang, Zhongyuan Wang, Ji-Rong Wen
Abstract: In this report, we present the third technical report on the development of slow-thinking models as part of the STILL project. As the technical pathway becomes clearer, scaling RL training has become a central technique for implementing such reasoning models. We systematically experiment with and document the effects of various factors influencing RL training, conducting experiments on both base models and fine-tuned models. Specifically, we demonstrate that our RL training approach consistently improves the Qwen2.5-32B base models, enhancing both response length and test accuracy. Furthermore, we show that even when a model like DeepSeek-R1-Distill-Qwen-1.5B has already achieved a high performance level, it can be further refined through RL training, reaching an accuracy of 39.33% on AIME 2024. Beyond RL training, we also explore the use of tool manipulation, finding that it significantly boosts the reasoning performance of large reasoning models. This approach achieves a remarkable accuracy of 86.67% with greedy search on AIME 2024, underscoring its effectiveness in enhancing model capabilities. We release our resources at the STILL project website: https://github.com/RUCAIBox/Slow_Thinking_with_LLMs.
Authors: Armel Zebaze, Beno\^it Sagot, Rachel Bawden
Abstract: The ability of generative large language models (LLMs) to perform in-context learning has given rise to a large body of research into how best to prompt models for various natural language processing tasks. Machine Translation (MT) has been shown to benefit from in-context examples, in particular when they are semantically similar to the sentence to translate. In this paper, we propose a new LLM-based translation paradigm, compositional translation, to replace naive few-shot MT with similarity-based demonstrations. An LLM is used to decompose a sentence into simpler phrases, and then to translate each phrase with the help of retrieved demonstrations. Finally, the LLM is prompted to translate the initial sentence with the help of the self-generated phrase-translation pairs. Our intuition is that this approach should improve translation because these shorter phrases should be intrinsically easier to translate and easier to match with relevant examples. This is especially beneficial in low-resource scenarios, and more generally whenever the selection pool is small or out of domain. We show that compositional translation boosts LLM translation performance on a wide range of popular MT benchmarks, including FLORES 200, NTREX 128 and TICO-19. Code and outputs are available at https://github.com/ArmelRandy/compositional-translation
URLs: https://github.com/ArmelRandy/compositional-translation
Authors: Jacqueline R. M. A. Maasch, Alihan H\"uy\"uk, Xinnuo Xu, Aditya V. Nori, Javier Gonzalez
Abstract: Causal reasoning and compositional reasoning are two core aspirations in generative AI. Measuring the extent of these behaviors requires principled evaluation methods. We explore a unified perspective that considers both behaviors simultaneously, termed compositional causal reasoning (CCR): the ability to infer how causal measures compose and, equivalently, how causal quantities propagate through graphs. We instantiate a framework for the systematic evaluation of CCR for the average treatment effect and the probability of necessity and sufficiency. As proof of concept, we demonstrate the design of CCR tasks for language models in the LLama, Phi, and GPT families. On a math word problem, our framework revealed a range of taxonomically distinct error patterns. Additionally, CCR errors increased with the complexity of causal paths for all models except o1.
Authors: Zhijian Zhuo, Yutao Zeng, Ya Wang, Sijun Zhang, Jian Yang, Xiaoqing Li, Xun Zhou, Jinwen Ma
Abstract: Transformers have become the de facto architecture for a wide range of machine learning tasks, particularly in large language models (LLMs). Despite their remarkable performance, challenges remain in training deep transformer networks, especially regarding the location of layer normalization. While Pre-Norm structures facilitate easier training due to their more prominent identity path, they often yield suboptimal performance compared to Post-Norm. In this paper, we propose $\textbf{HybridNorm}$, a straightforward yet effective hybrid normalization strategy that integrates the advantages of both Pre-Norm and Post-Norm approaches. Specifically, HybridNorm employs QKV normalization within the attention mechanism and Post-Norm in the feed-forward network (FFN) of each transformer block. This design not only stabilizes training but also enhances performance, particularly in the context of LLMs. Comprehensive experiments in both dense and sparse architectures show that HybridNorm consistently outperforms both Pre-Norm and Post-Norm approaches, achieving state-of-the-art results across various benchmarks. These findings highlight the potential of HybridNorm as a more stable and effective technique for improving the training and performance of deep transformer models. %Code will be made publicly available. Code is available at https://github.com/BryceZhuo/HybridNorm.
Authors: Mohammad Amin Ghanizadeh, Mohammad Javad Dousti
Abstract: In this work, we explain our approach employed in the BabyLM Challenge, which uses various methods of training language models (LMs) with significantly less data compared to traditional large language models (LLMs) and are inspired by how human children learn. While a human child is exposed to far less linguistic input than an LLM, they still achieve remarkable language understanding and generation abilities. To this end, we develop a model trained on a curated dataset consisting of 10 million words, primarily sourced from child-directed transcripts. The 2024 BabyLM Challenge initial dataset of 10M words is filtered to 8.5M. Next, it is supplemented with a randomly selected subset of TVR dataset consisting of 1.5M words of television dialogues. The latter dataset ensures that similar to children, the model is also exposed to language through media. Furthermore, we reduce the vocabulary size to 32,000 tokens, aligning it with the limited vocabulary of children in the early stages of language acquisition. We use curriculum learning and is able to match the baseline on certain benchmarks while surpassing the baseline on others. Additionally, incorporating common LLM training datasets, such as MADLAD-400, degrades performance. These findings underscore the importance of dataset selection, vocabulary scaling, and curriculum learning in creating more data-efficient language models that better mimic human learning processes.
Authors: Ashok Urlana, Gopichand Kanumolu, Charaka Vinayak Kumar, Bala Mallikarjunarao Garlapati, Rahul Mishra
Abstract: Response consistency-based, reference-free hallucination detection (RFHD) methods do not depend on internal model states, such as generation probabilities or gradients, which Grey-box models typically rely on but are inaccessible in closed-source LLMs. However, their inability to capture query-response alignment patterns often results in lower detection accuracy. Additionally, the lack of large-scale benchmark datasets spanning diverse domains remains a challenge, as most existing datasets are limited in size and scope. To this end, we propose HalluCounter, a novel reference-free hallucination detection method that utilizes both response-response and query-response consistency and alignment patterns. This enables the training of a classifier that detects hallucinations and provides a confidence score and an optimal response for user queries. Furthermore, we introduce HalluCounterEval, a benchmark dataset comprising both synthetically generated and human-curated samples across multiple domains. Our method outperforms state-of-the-art approaches by a significant margin, achieving over 90\% average confidence in hallucination detection across datasets.
Authors: Wenxiang Chen, Wei He, Zhiheng Xi, Honglin Guo, Boyang Hong, Jiazheng Zhang, Rui Zheng, Nijun Li, Tao Gui, Yun Li, Qi Zhang, Xuanjing Huang
Abstract: Process supervision, i.e., evaluating each step, is critical for complex large language model (LLM) reasoning and test-time searching with increased inference compute. Existing approaches, represented by process reward models (PRMs), primarily focus on rewarding signals up to the current step, exhibiting a one-directional nature and lacking a mechanism to model the distance to the final target. To address this problem, we draw inspiration from the A* algorithm, which states that an effective supervisory signal should simultaneously consider the incurred cost and the estimated cost for reaching the target. Building on this key insight, we introduce BiRM, a novel process supervision model that not only evaluates the correctness of previous steps but also models the probability of future success. We conduct extensive experiments on mathematical reasoning tasks and demonstrate that BiRM provides more precise evaluations of LLM reasoning steps, achieving an improvement of 3.1% on Gaokao2023 over PRM under the Best-of-N sampling method. Besides, in search-based strategies, BiRM provides more comprehensive guidance and outperforms ORM by 5.0% and PRM by 3.8% respectively on MATH-500.
Authors: Xin Zhang, Qiyu Wei, Yingjie Zhu, Linhai Zhang, Deyu Zhou, Sophia Ananiadou
Abstract: User reviews on e-commerce platforms exhibit dynamic sentiment patterns driven by temporal and contextual factors. Traditional sentiment analysis methods focus on static reviews, failing to capture the evolving temporal relationship between user sentiment rating and textual content. Sentiment analysis on streaming reviews addresses this limitation by modeling and predicting the temporal evolution of user sentiments. However, it suffers from data sparsity, manifesting in temporal, spatial, and combined forms. In this paper, we introduce SynGraph, a novel framework designed to address data sparsity in sentiment analysis on streaming reviews. SynGraph alleviates data sparsity by categorizing users into mid-tail, long-tail, and extreme scenarios and incorporating LLM-augmented enhancements within a dynamic graph-based structure. Experiments on real-world datasets demonstrate its effectiveness in addressing sparsity and improving sentiment modeling in streaming reviews.
Authors: Chengpeng Li, Mingfeng Xue, Zhenru Zhang, Jiaxi Yang, Beichen Zhang, Xiang Wang, Bowen Yu, Binyuan Hui, Junyang Lin, Dayiheng Liu
Abstract: Large reasoning models (LRMs) like OpenAI-o1 and DeepSeek-R1 have demonstrated remarkable capabilities in complex reasoning tasks through the utilization of long Chain-of-thought (CoT). However, these models often suffer from hallucinations and inefficiencies due to their reliance solely on internal reasoning processes. In this paper, we introduce START (Self-Taught Reasoner with Tools), a novel tool-integrated long CoT reasoning LLM that significantly enhances reasoning capabilities by leveraging external tools. Through code execution, START is capable of performing complex computations, self-checking, exploring diverse methods, and self-debugging, thereby addressing the limitations of LRMs. The core innovation of START lies in its self-learning framework, which comprises two key techniques: 1) Hint-infer: We demonstrate that inserting artificially designed hints (e.g., ``Wait, maybe using Python here is a good idea.'') during the inference process of a LRM effectively stimulates its ability to utilize external tools without the need for any demonstration data. Hint-infer can also serve as a simple and effective sequential test-time scaling method; 2) Hint Rejection Sampling Fine-Tuning (Hint-RFT): Hint-RFT combines Hint-infer and RFT by scoring, filtering, and modifying the reasoning trajectories with tool invocation generated by a LRM via Hint-infer, followed by fine-tuning the LRM. Through this framework, we have fine-tuned the QwQ-32B model to achieve START. On PhD-level science QA (GPQA), competition-level math benchmarks (AMC23, AIME24, AIME25), and the competition-level code benchmark (LiveCodeBench), START achieves accuracy rates of 63.6%, 95.0%, 66.7%, 47.1%, and 47.3%, respectively. It significantly outperforms the base QwQ-32B and achieves performance comparable to the state-of-the-art open-weight model R1-Distill-Qwen-32B and the proprietary model o1-Preview.
Authors: Xiangchao Yan, Shiyang Feng, Jiakang Yuan, Renqiu Xia, Bin Wang, Bo Zhang, Lei Bai
Abstract: Survey paper plays a crucial role in scientific research, especially given the rapid growth of research publications. Recently, researchers have begun using LLMs to automate survey generation for better efficiency. However, the quality gap between LLM-generated surveys and those written by human remains significant, particularly in terms of outline quality and citation accuracy. To close these gaps, we introduce SurveyForge, which first generates the outline by analyzing the logical structure of human-written outlines and referring to the retrieved domain-related articles. Subsequently, leveraging high-quality papers retrieved from memory by our scholar navigation agent, SurveyForge can automatically generate and refine the content of the generated article. Moreover, to achieve a comprehensive evaluation, we construct SurveyBench, which includes 100 human-written survey papers for win-rate comparison and assesses AI-generated survey papers across three dimensions: reference, outline, and content quality. Experiments demonstrate that SurveyForge can outperform previous works such as AutoSurvey.
Authors: Yijie Xu, Aiwei Liu, Xuming Hu, Lijie Wen, Hui Xiong
Abstract: As open-source large language models (LLMs) like Llama3 become more capable, it is crucial to develop watermarking techniques to detect their potential misuse. Existing watermarking methods either add watermarks during LLM inference, which is unsuitable for open-source LLMs, or primarily target classification LLMs rather than recent generative LLMs. Adapting these watermarks to open-source LLMs for misuse detection remains an open challenge. This work defines two misuse scenarios for open-source LLMs: intellectual property (IP) violation and LLM Usage Violation. Then, we explore the application of inference-time watermark distillation and backdoor watermarking in these contexts. We propose comprehensive evaluation methods to assess the impact of various real-world further fine-tuning scenarios on watermarks and the effect of these watermarks on LLM performance. Our experiments reveal that backdoor watermarking could effectively detect IP Violation, while inference-time watermark distillation is applicable in both scenarios but less robust to further fine-tuning and has a more significant impact on LLM performance compared to backdoor watermarking. Exploring more advanced watermarking methods for open-source LLMs to detect their misuse should be an important future direction.
Authors: Tingyu Song, Guo Gan, Mingsheng Shang, Yilun Zhao
Abstract: We introduce IFIR, the first comprehensive benchmark designed to evaluate instruction-following information retrieval (IR) in expert domains. IFIR includes 2,426 high-quality examples and covers eight subsets across four specialized domains: finance, law, healthcare, and science literature. Each subset addresses one or more domain-specific retrieval tasks, replicating real-world scenarios where customized instructions are critical. IFIR enables a detailed analysis of instruction-following retrieval capabilities by incorporating instructions at different levels of complexity. We also propose a novel LLM-based evaluation method to provide a more precise and reliable assessment of model performance in following instructions. Through extensive experiments on 15 frontier retrieval models, including those based on LLMs, our results reveal that current models face significant challenges in effectively following complex, domain-specific instructions. We further provide in-depth analyses to highlight these limitations, offering valuable insights to guide future advancements in retriever development.
Authors: Wen Yang, Junhong Wu, Chen Wang, Chengqing Zong, Jiajun Zhang
Abstract: Direct Preference Optimization (DPO) has become a prominent method for aligning Large Language Models (LLMs) with human preferences. While DPO has enabled significant progress in aligning English LLMs, multilingual preference alignment is hampered by data scarcity. To address this, we propose a novel approach that $\textit{captures}$ learned preferences from well-aligned English models by implicit rewards and $\textit{transfers}$ them to other languages through iterative training. Specifically, we derive an implicit reward model from the logits of an English DPO-aligned model and its corresponding reference model. This reward model is then leveraged to annotate preference relations in cross-lingual instruction-following pairs, using English instructions to evaluate multilingual responses. The annotated data is subsequently used for multilingual DPO fine-tuning, facilitating preference knowledge transfer from English to other languages. Fine-tuning Llama3 for two iterations resulted in a 12.72% average improvement in Win Rate and a 5.97% increase in Length Control Win Rate across all training languages on the X-AlpacaEval leaderboard. Our findings demonstrate that leveraging existing English-aligned models can enable efficient and effective multilingual preference alignment, significantly reducing the need for extensive multilingual preference data. The code is available at https://github.com/ZNLP/Implicit-Cross-Lingual-Rewarding
URLs: https://github.com/ZNLP/Implicit-Cross-Lingual-Rewarding
Authors: Dou Hu, Lingwei Wei, Wei Zhou, Songlin Hu
Abstract: This paper proposes a new principled multi-task representation learning framework (InfoMTL) to extract noise-invariant sufficient representations for all tasks. It ensures sufficiency of shared representations for all tasks and mitigates the negative effect of redundant features, which can enhance language understanding of pre-trained language models (PLMs) under the multi-task paradigm. Firstly, a shared information maximization principle is proposed to learn more sufficient shared representations for all target tasks. It can avoid the insufficiency issue arising from representation compression in the multi-task paradigm. Secondly, a task-specific information minimization principle is designed to mitigate the negative effect of potential redundant features in the input for each task. It can compress task-irrelevant redundant information and preserve necessary information relevant to the target for multi-task prediction. Experiments on six classification benchmarks show that our method outperforms 12 comparative multi-task methods under the same multi-task settings, especially in data-constrained and noisy scenarios. Extensive experiments demonstrate that the learned representations are more sufficient, data-efficient, and robust.
Authors: Sangyeop Kim, Sohhyung Park, Jaewon Jung, Jinseok Kim, Sungzoon Cho
Abstract: Understanding user satisfaction with conversational systems, known as User Satisfaction Estimation (USE), is essential for assessing dialogue quality and enhancing user experiences. However, existing methods for USE face challenges due to limited understanding of underlying reasons for user dissatisfaction and the high costs of annotating user intentions. To address these challenges, we propose PRAISE (Plan and Retrieval Alignment for Interpretable Satisfaction Estimation), an interpretable framework for effective user satisfaction prediction. PRAISE operates through three key modules. The Strategy Planner develops strategies, which are natural language criteria for classifying user satisfaction. The Feature Retriever then incorporates knowledge on user satisfaction from Large Language Models (LLMs) and retrieves relevance features from utterances. Finally, the Score Analyzer evaluates strategy predictions and classifies user satisfaction. Experimental results demonstrate that PRAISE achieves state-of-the-art performance on three benchmarks for the USE task. Beyond its superior performance, PRAISE offers additional benefits. It enhances interpretability by providing instance-level explanations through effective alignment of utterances with strategies. Moreover, PRAISE operates more efficiently than existing approaches by eliminating the need for LLMs during the inference phase.
Authors: Krish Sharma, Niyar R Barman, Nicholas Asher, Akshay Chaturvedi
Abstract: We look at reasoning on GSM8k, a dataset of short texts presenting primary school, math problems. We find, with Mirzadeh et al. (2024), that current LLM progress on the data set may not be explained by better reasoning but by exposure to a broader pretraining data distribution. We then introduce a novel information source for helping models with less data or inferior training reason better: discourse structure. We show that discourse structure improves performance for models like Llama2 13b by up to 160%. Even for models that have most likely memorized the data set, adding discourse structural information to the model still improves predictions and dramatically improves large model performance on out of distribution examples.
Authors: Pengcheng Qiu, Chaoyi Wu, Shuyu Liu, Weike Zhao, Ya Zhang, Yanfeng Wang, Weidi Xie
Abstract: The latest reasoning-enhanced large language models (reasoning LLMs), such as DeepSeek-R1 and OpenAI-o3, have demonstrated remarkable success. However, the application of such reasoning enhancements to the highly professional medical domain has not been clearly evaluated, particularly regarding with not only assessing the final generation but also examining the quality of their reasoning processes. In this study, we present MedR-Bench, a reasoning-focused medical evaluation benchmark comprising 1,453 structured patient cases with reasoning references mined from case reports. Our benchmark spans 13 body systems and 10 specialty disorders, encompassing both common and rare diseases. In our evaluation, we introduce a versatile framework consisting of three critical clinical stages: assessment recommendation, diagnostic decision-making, and treatment planning, comprehensively capturing the LLMs' performance across the entire patient journey in healthcare. For metrics, we propose a novel agentic system, Reasoning Evaluator, designed to automate and objectively quantify free-text reasoning responses in a scalable manner from the perspectives of efficiency, factuality, and completeness by dynamically searching and performing cross-referencing checks. As a result, we assess five state-of-the-art reasoning LLMs, including DeepSeek-R1, OpenAI-o3-mini, and others. Our results reveal that current LLMs can handle relatively simple diagnostic tasks with sufficient critical assessment results, achieving accuracy generally over 85%. However, they still struggle with more complex tasks, such as assessment recommendation and treatment planning. In reasoning, their reasoning processes are generally reliable, with factuality scores exceeding 90%, though they often omit critical reasoning steps. Our study clearly reveals further development directions for current clinical LLMs.
Authors: Wenyu Wang, Mengqi Zhang, Xiaotian Ye, Zhaochun Ren, Zhumin Chen, Pengjie Ren
Abstract: Large Language Models (LLMs) inevitably acquire harmful information during training on massive datasets. LLM unlearning aims to eliminate the influence of such harmful information while maintaining the model's overall performance. Existing unlearning methods, represented by gradient ascent-based approaches, primarily focus on forgetting target data while overlooking the crucial impact of logically related knowledge on the effectiveness of unlearning. In this paper, through both theoretical and experimental analyses, we first demonstrate that a key reason for the suboptimal unlearning performance is that models can reconstruct the target content through reasoning with logically related knowledge. To address this issue, we propose Unlearning Improvement via Parameter Extrapolation (UIPE), a method that removes knowledge highly correlated with the forgetting targets. Experimental results show that UIPE significantly enhances the performance of various mainstream LLM unlearning methods on the TOFU benchmark.
Authors: Pranjal Aggarwal, Sean Welleck
Abstract: Reasoning language models have shown an uncanny ability to improve performance at test-time by ``thinking longer''-that is, by generating longer chain-of-thought sequences and hence using more compute. However, the length of their chain-of-thought reasoning is not controllable, making it impossible to allocate test-time compute to achieve a desired level of performance. We introduce Length Controlled Policy Optimization (LCPO), a simple reinforcement learning method that optimizes for accuracy and adherence to user-specified length constraints. We use LCPO to train L1, a reasoning language model that produces outputs satisfying a length constraint given in its prompt. L1's length control allows for smoothly trading off computational cost and accuracy on a wide range of tasks, and outperforms the state-of-the-art S1 method for length control. Furthermore, we uncover an unexpected short chain-of-thought capability in models trained with LCPO. For instance, our 1.5B L1 model surpasses GPT-4o at equal reasoning lengths. Overall, LCPO enables precise control over reasoning length, allowing for fine-grained allocation of test-time compute and accuracy. We release code and models at https://www.cmu-l3.github.io/l1
Authors: Guan-Ting Lin, Jiachen Lian, Tingle Li, Qirui Wang, Gopala Anumanchipalli, Alexander H. Liu, Hung-yi Lee
Abstract: Spoken dialogue modeling introduces unique challenges beyond text-based language modeling, demanding robust turn-taking, backchanneling, and real-time interaction. Although most Spoken Dialogue Models (SDMs) rely on half-duplex processing (handling speech one turn at a time), emerging full-duplex SDMs can listen and speak simultaneously, enabling more natural and engaging conversations. However, current evaluations of such models remain limited, often focusing on turn-based metrics or high-level corpus analyses (e.g., turn gaps, pauses). To address this gap, we present Full-Duplex-Bench, a new benchmark that systematically evaluates key conversational behaviors: pause handling, backchanneling, turn-taking, and interruption management. Our framework uses automatic metrics for consistent and reproducible assessments of SDMs' interactive performance. By offering an open and standardized evaluation benchmark, we aim to advance spoken dialogue modeling and encourage the development of more interactive and natural dialogue systems.
Authors: Ritwik Gupta, Rodolfo Corona, Jiaxin Ge, Eric Wang, Dan Klein, Trevor Darrell, David M. Chan
Abstract: Large language models (LLMs) exhibit the ability to generalize given few-shot examples in their input prompt, an emergent capability known as in-context learning (ICL). We investigate whether LLMs utilize ICL to perform structured reasoning in ways that are consistent with a Bayesian framework or rely on pattern matching. Using a controlled setting of biased coin flips, we find that: (1) LLMs often possess biased priors, causing initial divergence in zero-shot settings, (2) in-context evidence outweighs explicit bias instructions, (3) LLMs broadly follow Bayesian posterior updates, with deviations primarily due to miscalibrated priors rather than flawed updates, and (4) attention magnitude has negligible effect on Bayesian inference. With sufficient demonstrations of biased coin flips via ICL, LLMs update their priors in a Bayesian manner.
Authors: Yuhao Wu, Yushi Bai, Zhiqing Hu, Shangqing Tu, Ming Shan Hee, Juanzi Li, Roy Ka-Wei Lee
Abstract: Recent advancements in long-context Large Language Models (LLMs) have primarily concentrated on processing extended input contexts, resulting in significant strides in long-context comprehension. However, the equally critical aspect of generating long-form outputs has received comparatively less attention. This paper advocates for a paradigm shift in NLP research toward addressing the challenges of long-output generation. Tasks such as novel writing, long-term planning, and complex reasoning require models to understand extensive contexts and produce coherent, contextually rich, and logically consistent extended text. These demands highlight a critical gap in current LLM capabilities. We underscore the importance of this under-explored domain and call for focused efforts to develop foundational LLMs tailored for generating high-quality, long-form outputs, which hold immense potential for real-world applications.
Authors: Sambal Shikhar, Mohammed Irfan Kurpath, Sahal Shaji Mullappilly, Jean Lahoud, Fahad Khan, Rao Muhammad Anwer, Salman Khan, Hisham Cholakkal
Abstract: Recent advancements in speech-to-speech dialogue systems leverage LLMs for multimodal interactions, yet they remain hindered by fine-tuning requirements, high computational overhead, and text-speech misalignment. Existing speech-enabled LLMs often degrade conversational quality by modifying the LLM, thereby compromising its linguistic capabilities. In contrast, we propose LLMVoX, a lightweight 30M-parameter, LLM-agnostic, autoregressive streaming TTS system that generates high-quality speech with low latency, while fully preserving the capabilities of the base LLM. Our approach achieves a significantly lower Word Error Rate compared to speech-enabled LLMs, while operating at comparable latency and UTMOS score. By decoupling speech synthesis from LLM processing via a multi-queue token streaming system, LLMVoX supports seamless, infinite-length dialogues. Its plug-and-play design also facilitates extension to various tasks with different backbones. Furthermore, LLMVoX generalizes to new languages with only dataset adaptation, attaining a low Character Error Rate on an Arabic speech task. Additionally, we have integrated LLMVoX with a Vision-Language Model to create an omni-model with speech, text, and vision capabilities, without requiring additional multimodal training. Our code base and project page is available at https://mbzuai-oryx.github.io/LLMVoX .
Authors: Zhuo Chen, Oriol Mayn\'e i Comas, Zhuotao Jin, Di Luo, Marin Solja\v{c}i\'c
Abstract: We rigorously establish a bipartite mutual information scaling law in natural language that governs long-range dependencies. This scaling law, which we show is distinct from and scales independently of the conventional two-point mutual information, is the key to understanding long-context language modeling. Using this scaling law, we formulate the Long-context Language Modeling (L$^2$M) condition, which relates a model's capacity for effective long context length modeling to the scaling of its latent state size for storing past information. Our results are validated through experiments on both transformers and state space models. This work establishes a theoretical foundation that guides the development of large language models toward longer context lengths.
Authors: Cristian Jimenez-Romero, Alper Yegenoglu, Christian Blum
Abstract: This work examines the integration of large language models (LLMs) into multi-agent simulations by replacing the hard-coded programs of agents with LLM-driven prompts. The proposed approach is showcased in the context of two examples of complex systems from the field of swarm intelligence: ant colony foraging and bird flocking. Central to this study is a toolchain that integrates LLMs with the NetLogo simulation platform, leveraging its Python extension to enable communication with GPT-4o via the OpenAI API. This toolchain facilitates prompt-driven behavior generation, allowing agents to respond adaptively to environmental data. For both example applications mentioned above, we employ both structured, rule-based prompts and autonomous, knowledge-driven prompts. Our work demonstrates how this toolchain enables LLMs to study self-organizing processes and induce emergent behaviors within multi-agent environments, paving the way for new approaches to exploring intelligent systems and modeling swarm intelligence inspired by natural phenomena. We provide the code, including simulation files and data at https://github.com/crjimene/swarm_gpt.
Authors: Matteo Grella
Abstract: We propose leveraging chromostereopsis, a perceptual phenomenon inducing depth perception through color contrast, as a novel approach to visually differentiating conversational roles in text-based AI interfaces. This method aims to implicitly communicate role hierarchy and add a subtle sense of physical space.
Authors: Sreyan Ghosh, Zhifeng Kong, Sonal Kumar, S Sakshi, Jaehyeon Kim, Wei Ping, Rafael Valle, Dinesh Manocha, Bryan Catanzaro
Abstract: Understanding and reasoning over non-speech sounds and music are crucial for both humans and AI agents to interact effectively with their environments. In this paper, we introduce Audio Flamingo 2 (AF2), an Audio-Language Model (ALM) with advanced audio understanding and reasoning capabilities. AF2 leverages (i) a custom CLAP model, (ii) synthetic Audio QA data for fine-grained audio reasoning, and (iii) a multi-stage curriculum learning strategy. AF2 achieves state-of-the-art performance with only a 3B parameter small language model, surpassing large open-source and proprietary models across over 20 benchmarks. Next, for the first time, we extend audio understanding to long audio segments (30 secs to 5 mins) and propose LongAudio, a large and novel dataset for training ALMs on long audio captioning and question-answering tasks. Fine-tuning AF2 on LongAudio leads to exceptional performance on our proposed LongAudioBench, an expert annotated benchmark for evaluating ALMs on long audio understanding capabilities. We conduct extensive ablation studies to confirm the efficacy of our approach. Project Website: https://research.nvidia.com/labs/adlr/AF2/.
Authors: Wenhui Zhu, Xin Li, Xiwen Chen, Peijie Qiu, Vamsi Krishna Vasa, Xuanzhao Dong, Yanxi Chen, Natasha Lepore, Oana Dumitrascu, Yi Su, Yalin Wang
Abstract: Recently, Multimodal Large Language Models (MLLMs) have gained significant attention for their remarkable ability to process and analyze non-textual data, such as images, videos, and audio. Notably, several adaptations of general-domain MLLMs to the medical field have been explored, including LLaVA-Med. However, these medical adaptations remain insufficiently advanced in understanding and interpreting retinal images. In contrast, medical experts emphasize the importance of quantitative analyses for disease detection and interpretation. This underscores a gap between general-domain and medical-domain MLLMs: while general-domain MLLMs excel in broad applications, they lack the specialized knowledge necessary for precise diagnostic and interpretative tasks in the medical field. To address these challenges, we introduce \textit{RetinalGPT}, a multimodal conversational assistant for clinically preferred quantitative analysis of retinal images. Specifically, we achieve this by compiling a large retinal image dataset, developing a novel data pipeline, and employing customized visual instruction tuning to enhance both retinal analysis and enrich medical knowledge. In particular, RetinalGPT outperforms MLLM in the generic domain by a large margin in the diagnosis of retinal diseases in 8 benchmark retinal datasets. Beyond disease diagnosis, RetinalGPT features quantitative analyses and lesion localization, representing a pioneering step in leveraging LLMs for an interpretable and end-to-end clinical research framework. The code is available at https://github.com/Retinal-Research/RetinalGPT
Authors: Xinyue Cui, Johnny Tian-Zheng Wei, Swabha Swayamdipta, Robin Jia
Abstract: Data watermarking in language models injects traceable signals, such as specific token sequences or stylistic patterns, into copyrighted text, allowing copyright holders to track and verify training data ownership. Previous data watermarking techniques primarily focus on effective memorization after pretraining, while overlooking challenges that arise in other stages of the LLM pipeline, such as the risk of watermark filtering during data preprocessing, or potential forgetting through post-training, or verification difficulties due to API-only access. We propose a novel data watermarking approach that injects coherent and plausible yet fictitious knowledge into training data using generated passages describing a fictitious entity and its associated attributes. Our watermarks are designed to be memorized by the LLM through seamlessly integrating in its training data, making them harder to detect lexically during preprocessing.We demonstrate that our watermarks can be effectively memorized by LLMs, and that increasing our watermarks' density, length, and diversity of attributes strengthens their memorization. We further show that our watermarks remain robust throughout LLM development, maintaining their effectiveness after continual pretraining and supervised finetuning. Finally, we show that our data watermarks can be evaluated even under API-only access via question answering.
Authors: Feng Ni, Kui Huang, Yao Lu, Wenyu Lv, Guanzhong Wang, Zeyu Chen, Yi Liu
Abstract: With the rapid advancement of digitalization, various document images are being applied more extensively in production and daily life, and there is an increasingly urgent need for fast and accurate parsing of the content in document images. Therefore, this report presents PP-DocBee, a novel multimodal large language model designed for end-to-end document image understanding. First, we develop a data synthesis strategy tailored to document scenarios in which we build a diverse dataset to improve the model generalization. Then, we apply a few training techniques, including dynamic proportional sampling, data preprocessing, and OCR postprocessing strategies. Extensive evaluations demonstrate the superior performance of PP-DocBee, achieving state-of-the-art results on English document understanding benchmarks and even outperforming existing open source and commercial models in Chinese document understanding. The source code and pre-trained models are publicly available at \href{https://github.com/PaddlePaddle/PaddleMIX}{https://github.com/PaddlePaddle/PaddleMIX}.
URLs: https://github.com/PaddlePaddle/PaddleMIX, https://github.com/PaddlePaddle/PaddleMIX
Authors: Sangyeop Kim, Hangyeul Lee, Yohan Lee
Abstract: The growth of conversational AI services has increased demand for effective information retrieval from dialogue data. However, existing methods often face challenges in capturing semantic intent or require extensive labeling and fine-tuning. This paper introduces HEISIR (Hierarchical Expansion of Inverted Semantic Indexing for Retrieval), a novel framework that enhances semantic understanding in conversational data retrieval through optimized data ingestion, eliminating the need for resource-intensive labeling or model adaptation. HEISIR implements a two-step process: (1) Hierarchical Triplets Formulation and (2) Adjunct Augmentation, creating semantic indices consisting of Subject-Verb-Object-Adjunct (SVOA) quadruplets. This structured representation effectively captures the underlying semantic information from dialogue content. HEISIR achieves high retrieval performance while maintaining low latency during the actual retrieval process. Our experimental results demonstrate that HEISIR outperforms fine-tuned models across various embedding types and language models. Beyond improving retrieval capabilities, HEISIR also offers opportunities for intent and topic analysis in conversational data, providing a versatile solution for dialogue systems.
Authors: Simin Chen, Pranav Pusarla, Baishakhi Ray
Abstract: The rapid evolution of code largelanguage models underscores the need for effective and transparent benchmarking of their reasoning capabilities. However, the current benchmarking approach heavily depends on publicly available, human-created datasets. The widespread use of these fixed benchmark datasets makes the benchmarking process to be static and thus particularly susceptible to data contamination, an unavoidable consequence of the extensive data collection processes used to train Code LLMs. Existing approaches that address data contamination often suffer from human effort limitations and imbalanced problem complexity. To tackle these challenges, we propose \tool, a novel benchmarking suite for evaluating Code LLMs under potential data contamination. Given a seed programming problem, \tool employs multiple agents to extract and modify the context without altering the core logic, generating semantically equivalent variations. We introduce a dynamic data generation methods and conduct empirical studies on two seed datasets across 21 Code LLMs. Results show that \tool effectively benchmarks reasoning capabilities under contamination risks while generating diverse problem sets to ensure consistent and reliable evaluations.
Authors: Hejie Cui, Alyssa Unell, Bowen Chen, Jason Alan Fries, Emily Alsentzer, Sanmi Koyejo, Nigam Shah
Abstract: Large language models (LLMs) have emerged as promising tools for assisting in medical tasks, yet processing Electronic Health Records (EHRs) presents unique challenges due to their longitudinal nature. While LLMs' capabilities to perform medical tasks continue to improve, their ability to reason over temporal dependencies across multiple patient visits and time frames remains unexplored. We introduce TIMER (Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records), a framework that incorporate instruction-response pairs grounding to different parts of a patient's record as a critical dimension in both instruction evaluation and tuning for longitudinal clinical records. We develop TIMER-Bench, the first time-aware benchmark that evaluates temporal reasoning capabilities over longitudinal EHRs, as well as TIMER-Instruct, an instruction-tuning methodology for LLMs to learn reasoning over time. We demonstrate that models fine-tuned with TIMER-Instruct improve performance by 7.3% on human-generated benchmarks and 9.2% on TIMER-Bench, indicating that temporal instruction-tuning improves model performance for reasoning over EHR.
Authors: Adnan Shahid, Adrian Kliks, Ahmed Al-Tahmeesschi, Ahmed Elbakary, Alexandros Nikou, Ali Maatouk, Ali Mokh, Amirreza Kazemi, Antonio De Domenico, Athanasios Karapantelakis, Bo Cheng, Bo Yang, Bohao Wang, Carlo Fischione, Chao Zhang, Chaouki Ben Issaid, Chau Yuen, Chenghui Peng, Chongwen Huang, Christina Chaccour, Christo Kurisummoottil Thomas, Dheeraj Sharma, Dimitris Kalogiros, Dusit Niyato, Eli De Poorter, Elissa Mhanna, Emilio Calvanese Strinati, Faouzi Bader, Fathi Abdeldayem, Fei Wang, Fenghao Zhu, Gianluca Fontanesi, Giovanni Geraci, Haibo Zhou, Hakimeh Purmehdi, Hamed Ahmadi, Hang Zou, Hongyang Du, Hoon Lee, Howard H. Yang, Iacopo Poli, Igor Carron, Ilias Chatzistefanidis, Inkyu Lee, Ioannis Pitsiorlas, Jaron Fontaine, Jiajun Wu, Jie Zeng, Jinan Li, Jinane Karam, Johny Gemayel, Juan Deng, Julien Frison, Kaibin Huang, Kehai Qiu, Keith Ball, Kezhi Wang, Kun Guo, Leandros Tassiulas, Lecorve Gwenole, Liexiang Yue, Lina Bariah, Louis Powell, Marcin Dryjanski, Maria Amparo Canaveras Galdon, Marios Kountouris, Maryam Hafeez, Maxime Elkael, Mehdi Bennis, Mehdi Boudjelli, Meiling Dai, Merouane Debbah, Michele Polese, Mohamad Assaad, Mohamed Benzaghta, Mohammad Al Refai, Moussab Djerrab, Mubeen Syed, Muhammad Amir, Na Yan, Najla Alkaabi, Nan Li, Nassim Sehad, Navid Nikaein, Omar Hashash, Pawel Sroka, Qianqian Yang, Qiyang Zhao, Rasoul Nikbakht Silab, Rex Ying, Roberto Morabito, Rongpeng Li, Ryad Madi, Salah Eddine El Ayoubi, Salvatore D'Oro, Samson Lasaulce, Serveh Shalmashi, Sige Liu, Sihem Cherrared, Swarna Bindu Chetty, Swastika Dutta, Syed A. R. Zaidi, Tianjiao Chen, Timothy Murphy, Tommaso Melodia, Tony Q. S. Quek, Vishnu Ram, Walid Saad, Wassim Hamidouche, Weilong Chen, Xiaoou Liu, Xiaoxue Yu, Xijun Wang, Xingyu Shang, Xinquan Wang, Xuelin Cao, Yang Su, Yanping Liang, Yansha Deng, Yifan Yang, Yingping Cui, Yu Sun, Yuxuan Chen, Yvan Pointurier, Zeinab Nehme, Zeinab Nezami, Zhaohui Yang, Zhaoyang Zhang, Zhe Liu, Zhenyu Yang, Zhu Han, Zhuang Zhou, Zihan Chen, Zirui Chen, Zitao Shuai
Abstract: This white paper discusses the role of large-scale AI in the telecommunications industry, with a specific focus on the potential of generative AI to revolutionize network functions and user experiences, especially in the context of 6G systems. It highlights the development and deployment of Large Telecom Models (LTMs), which are tailored AI models designed to address the complex challenges faced by modern telecom networks. The paper covers a wide range of topics, from the architecture and deployment strategies of LTMs to their applications in network management, resource allocation, and optimization. It also explores the regulatory, ethical, and standardization considerations for LTMs, offering insights into their future integration into telecom infrastructure. The goal is to provide a comprehensive roadmap for the adoption of LTMs to enhance scalability, performance, and user-centric innovation in telecom networks.
Authors: Yingli Zhou, Yaodong Su, Youran Sun, Shu Wang, Taotao Wang, Runyuan He, Yongwei Zhang, Sicong Liang, Xilin Liu, Yuchi Ma, Yixiang Fang
Abstract: Graph-based Retrieval-Augmented Generation (RAG) has proven effective in integrating external knowledge into large language models (LLMs), improving their factual accuracy, adaptability, interpretability, and trustworthiness. A number of graph-based RAG methods have been proposed in the literature. However, these methods have not been systematically and comprehensively compared under the same experimental settings. In this paper, we first summarize a unified framework to incorporate all graph-based RAG methods from a high-level perspective. We then extensively compare representative graph-based RAG methods over a range of questing-answering (QA) datasets -- from specific questions to abstract questions -- and examine the effectiveness of all methods, providing a thorough analysis of graph-based RAG approaches. As a byproduct of our experimental analysis, we are also able to identify new variants of the graph-based RAG methods over specific QA and abstract QA tasks respectively, by combining existing techniques, which outperform the state-of-the-art methods. Finally, based on these findings, we offer promising research opportunities. We believe that a deeper understanding of the behavior of existing methods can provide new valuable insights for future research.
Authors: Aoxiong Yin, Kai Shen, Yichong Leng, Xu Tan, Xinyu Zhou, Juncheng Li, Siliang Tang
Abstract: Recent advancements in text-to-video (T2V) generation have been driven by two competing paradigms: autoregressive language models and diffusion models. However, each paradigm has intrinsic limitations: language models struggle with visual quality and error accumulation, while diffusion models lack semantic understanding and causal modeling. In this work, we propose LanDiff, a hybrid framework that synergizes the strengths of both paradigms through coarse-to-fine generation. Our architecture introduces three key innovations: (1) a semantic tokenizer that compresses 3D visual features into compact 1D discrete representations through efficient semantic compression, achieving a $\sim$14,000$\times$ compression ratio; (2) a language model that generates semantic tokens with high-level semantic relationships; (3) a streaming diffusion model that refines coarse semantics into high-fidelity videos. Experiments show that LanDiff, a 5B model, achieves a score of 85.43 on the VBench T2V benchmark, surpassing the state-of-the-art open-source models Hunyuan Video (13B) and other commercial models such as Sora, Keling, and Hailuo. Furthermore, our model also achieves state-of-the-art performance in long video generation, surpassing other open-source models in this field. Our demo can be viewed at https://landiff.github.io/.
Authors: Anuj Diwan, Zhisheng Zheng, David Harwath, Eunsol Choi
Abstract: We introduce Paralinguistic Speech Captions (ParaSpeechCaps), a large-scale dataset that annotates speech utterances with rich style captions. While rich abstract tags (e.g. guttural, nasal, pained) have been explored in small-scale human-annotated datasets, existing large-scale datasets only cover basic tags (e.g. low-pitched, slow, loud). We combine off-the-shelf text and speech embedders, classifiers and an audio language model to automatically scale rich tag annotations for the first time. ParaSpeechCaps covers a total of 59 style tags, including both speaker-level intrinsic tags and utterance-level situational tags. It consists of 342 hours of human-labelled data (PSC-Base) and 2427 hours of automatically annotated data (PSC-Scaled). We finetune Parler-TTS, an open-source style-prompted TTS model, on ParaSpeechCaps, and achieve improved style consistency (+7.9% Consistency MOS) and speech quality (+15.5% Naturalness MOS) over the best performing baseline that combines existing rich style tag datasets. We ablate several of our dataset design choices to lay the foundation for future work in this space. Our dataset, models and code are released at https://github.com/ajd12342/paraspeechcaps .
Authors: Jessica Ojo, Odunayo Ogundepo, Akintunde Oladipo, Kelechi Ogueji, Jimmy Lin, Pontus Stenetorp, David Ifeoluwa Adelani
Abstract: Large-scale multilingual evaluations, such as MEGA, often include only a handful of African languages due to the scarcity of high-quality evaluation data and the limited discoverability of existing African datasets. This lack of representation hinders comprehensive LLM evaluation across a diverse range of languages and tasks. To address these challenges, we introduce AfroBench -- a multi-task benchmark for evaluating the performance of LLMs across 64 African languages, 15 tasks and 22 datasets. AfroBench consists of nine natural language understanding datasets, six text generation datasets, six knowledge and question answering tasks, and one mathematical reasoning task. We present results comparing the performance of prompting LLMs to fine-tuned baselines based on BERT and T5-style models. Our results suggest large gaps in performance between high-resource languages, such as English, and African languages across most tasks; but performance also varies based on the availability of monolingual data resources. Our findings confirm that performance on African languages continues to remain a hurdle for current LLMs, underscoring the need for additional efforts to close this gap. https://mcgill-nlp.github.io/AfroBench/
Authors: Lele Cao, Valentin Buchner, Zineb Senane, Fangkai Yang
Abstract: Multimodal Large Language Models (MLLMs) are typically assessed using expensive annotated multimodal benchmarks, which often lag behind the rapidly evolving demands of MLLM evaluation. This paper outlines and validates GenCeption, a novel, annotation-free evaluation method that requires only unimodal data to measure inter-modality semantic coherence and inversely assesses MLLMs' tendency to hallucinate. This approach eliminates the need for costly data annotation, minimizes the risk of training data contamination, is expected to result in slower benchmark saturation, and avoids the illusion of emerging abilities. Inspired by the DrawCeption game, GenCeption begins with a non-textual sample and proceeds through iterative description and generation steps. The semantic drift across iterations is quantified using the GC@T metric. While GenCeption is principally applicable to MLLMs across various modalities, this paper focuses on its implementation and validation for Vision LLMs (VLLMs). Based on the GenCeption method, we establish the MMECeption benchmark for evaluating VLLMs, and compare the performance of several popular VLLMs and human annotators. Our empirical results validate GenCeption's effectiveness, demonstrating strong correlations with established VLLM benchmarks. VLLMs still significantly lag behind human performance and struggle especially with text-intensive tasks.
Authors: Andi Zhang, Tim Z. Xiao, Weiyang Liu, Robert Bamler, Damon Wischik
Abstract: We revisit the likelihood ratio between a pretrained large language model (LLM) and its finetuned variant as a criterion for out-of-distribution (OOD) detection. The intuition behind such a criterion is that, the pretrained LLM has the prior knowledge about OOD data due to its large amount of training data, and once finetuned with the in-distribution data, the LLM has sufficient knowledge to distinguish their difference. Leveraging the power of LLMs, we show that, the likelihood ratio can serve as an effective OOD detection criterion. Moreover, we apply the proposed LLM-based likelihood ratio to detect OOD questions in question-answering (QA) systems, which can be used to improve the performance of specialized LLMs for general questions. Given that likelihood can be easily obtained by the loss functions within contemporary neural network frameworks, it is straightforward to implement this approach in practice. Since both the pretrained LLMs and its various finetuned models are widely available from online platforms such as Hugging Face, our proposed criterion can be effortlessly incorporated for OOD detection without the need for further training. We conduct comprehensive evaluation across on multiple settings, including far OOD, near OOD, spam detection, and QA scenarios, to demonstrate the effectiveness of the method. Code can be found at https://github.com/andiac/LLMOODratio
Authors: Jiawei Zhou, Li Dong, Furu Wei, Lei Chen
Abstract: Information retrieval has transitioned from standalone systems into essential components across broader applications, with indexing efficiency, cost-effectiveness, and freshness becoming increasingly critical yet often overlooked. In this paper, we introduce SemI-parametric Disentangled Retrieval (SiDR), a bi-encoder retrieval framework that decouples retrieval index from neural parameters to enable efficient, low-cost, and parameter-agnostic indexing for emerging use cases. Specifically, in addition to using embeddings as indexes like existing neural retrieval methods, SiDR supports a non-parametric tokenization index for search, achieving BM25-like indexing complexity with significantly better effectiveness. Our comprehensive evaluation across 16 retrieval benchmarks demonstrates that SiDR outperforms both neural and term-based retrieval baselines under the same indexing workload: (i) When using an embedding-based index, SiDR exceeds the performance of conventional neural retrievers while maintaining similar training complexity; (ii) When using a tokenization-based index, SiDR drastically reduces indexing cost and time, matching the complexity of traditional term-based retrieval, while consistently outperforming BM25 on all in-domain datasets; (iii) Additionally, we introduce a late parametric mechanism that matches BM25 index preparation time while outperforming other neural retrieval baselines in effectiveness.
Authors: Abhinav Lalwani, Tasha Kim, Lovish Chopra, Christopher Hahn, Zhijing Jin, Mrinmaya Sachan
Abstract: Translating natural language into formal language such as First-Order Logic (FOL) is a foundational challenge in NLP with wide-ranging applications in automated reasoning, misinformation tracking, and knowledge validation. In this paper, we introduce Natural Language to First-Order Logic (NL2FOL), a framework to autoformalize natural language to FOL step by step using Large Language Models (LLMs). Our approach addresses key challenges in this translation process, including the integration of implicit background knowledge. By leveraging structured representations generated by NL2FOL, we use Satisfiability Modulo Theory (SMT) solvers to reason about the logical validity of natural language statements. We present logical fallacy detection as a case study to evaluate the efficacy of NL2FOL. Being neurosymbolic, our approach also provides interpretable insights into the reasoning process and demonstrates robustness without requiring model fine-tuning or labeled training data. Our framework achieves strong performance on multiple datasets. On the LOGIC dataset, NL2FOL achieves an F1-score of 78%, while generalizing effectively to the LOGICCLIMATE dataset with an F1-score of 80%.
Authors: Guangyi Liu, Yongqi Zhang, Yong Li, Quanming Yao
Abstract: Large Language Models (LLMs) excel at intuitive, implicit reasoning. Guiding LLMs to construct thought chains can enhance their deliberate reasoning abilities, but also faces challenges such as hallucination. Knowledge Graphs (KGs) can provide explicit structured knowledge for LLMs to alleviate these issues. However, existing KG-enhanced methods often overlook explicit graph learning, making it challenging to efficiently provide precise reasoning chains for LLMs. Following dual-process theory, we propose Dual-Reasoning (DualR), a novel framework that integrates an external system based on Graph Neural Network (GNN) for explicit reasoning on KGs, complementing the implicit reasoning of LLMs through externalized reasoning chains. DualR designs an LLM-empowered GNN module for explicit learning on KGs, efficiently extracting high-quality reasoning chains. These reasoning chains are then refined to a knowledge-enhanced multiple-choice prompt, guiding a frozen LLM to reason thoughtfully for final answer determination. Extensive experiments on three benchmark KGQA datasets demonstrate that DualR achieves state-of-the-art performance while maintaining high efficiency and interpretability.
Authors: Zhen Huang, Zengzhi Wang, Shijie Xia, Xuefeng Li, Haoyang Zou, Ruijie Xu, Run-Ze Fan, Lyumanshan Ye, Ethan Chern, Yixin Ye, Yikai Zhang, Yuqing Yang, Ting Wu, Binjie Wang, Shichao Sun, Yang Xiao, Yiyuan Li, Fan Zhou, Steffi Chern, Yiwei Qin, Yan Ma, Jiadi Su, Yixiu Liu, Yuxiang Zheng, Shaoting Zhang, Dahua Lin, Yu Qiao, Pengfei Liu
Abstract: The evolution of Artificial Intelligence (AI) has been significantly accelerated by advancements in Large Language Models (LLMs) and Large Multimodal Models (LMMs), gradually showcasing potential cognitive reasoning abilities in problem-solving and scientific discovery (i.e., AI4Science) once exclusive to human intellect. To comprehensively evaluate current models' performance in cognitive reasoning abilities, we introduce OlympicArena, which includes 11,163 bilingual problems across both text-only and interleaved text-image modalities. These challenges encompass a wide range of disciplines spanning seven fields and 62 international Olympic competitions, rigorously examined for data leakage. We argue that the challenges in Olympic competition problems are ideal for evaluating AI's cognitive reasoning due to their complexity and interdisciplinary nature, which are essential for tackling complex scientific challenges and facilitating discoveries. Beyond evaluating performance across various disciplines using answer-only criteria, we conduct detailed experiments and analyses from multiple perspectives. We delve into the models' cognitive reasoning abilities, their performance across different modalities, and their outcomes in process-level evaluations, which are vital for tasks requiring complex reasoning with lengthy solutions. Our extensive evaluations reveal that even advanced models like GPT-4o only achieve a 39.97% overall accuracy, illustrating current AI limitations in complex reasoning and multimodal integration. Through the OlympicArena, we aim to advance AI towards superintelligence, equipping it to address more complex challenges in science and beyond. We also provide a comprehensive set of resources to support AI research, including a benchmark dataset, an open-source annotation platform, a detailed evaluation tool, and a leaderboard with automatic submission features.
Authors: Junkai Liu, Yujie Tong, Hui Huang, Bowen Zheng, Yiran Hu, Peicheng Wu, Chuan Xiao, Makoto Onizuka, Muyun Yang, Shuyuan Zheng
Abstract: Legal judgment prediction (LJP), which enables litigants and their lawyers to forecast judgment outcomes and refine litigation strategies, has emerged as a crucial legal NLP task. Existing studies typically utilize legal facts, i.e., facts that have been established by evidence and determined by the judge, to predict the judgment. However, legal facts are often difficult to obtain in the early stages of litigation, significantly limiting the practical applicability of fact-based LJP. To address this limitation, we propose a novel legal NLP task: \textit{legal fact prediction} (LFP), which takes the evidence submitted by litigants for trial as input to predict legal facts, thereby empowering fact-based LJP technologies to perform prediction in the absence of ground-truth legal facts. We also propose the first benchmark dataset, LFPBench, for evaluating the LFP task. Our extensive experiments on LFPBench demonstrate the effectiveness of LFP-empowered LJP and highlight promising research directions for LFP. Our code and data are available at https://github.com/HPRCEST/LFPBench.
Authors: Haoran Ye, Yuhang Xie, Yuanyi Ren, Hanjun Fang, Xin Zhang, Guojie Song
Abstract: Human values and their measurement are long-standing interdisciplinary inquiry. Recent advances in AI have sparked renewed interest in this area, with large language models (LLMs) emerging as both tools and subjects of value measurement. This work introduces Generative Psychometrics for Values (GPV), an LLM-based, data-driven value measurement paradigm, theoretically grounded in text-revealed selective perceptions. The core idea is to dynamically parse unstructured texts into perceptions akin to static stimuli in traditional psychometrics, measure the value orientations they reveal, and aggregate the results. Applying GPV to human-authored blogs, we demonstrate its stability, validity, and superiority over prior psychological tools. Then, extending GPV to LLM value measurement, we advance the current art with 1) a psychometric methodology that measures LLM values based on their scalable and free-form outputs, enabling context-specific measurement; 2) a comparative analysis of measurement paradigms, indicating response biases of prior methods; and 3) an attempt to bridge LLM values and their safety, revealing the predictive power of different value systems and the impacts of various values on LLM safety. Through interdisciplinary efforts, we aim to leverage AI for next-generation psychometrics and psychometrics for value-aligned AI.
Authors: Haiyan Zhao, Heng Zhao, Bo Shen, Ali Payani, Fan Yang, Mengnan Du
Abstract: Probing learned concepts in large language models (LLMs) is crucial for understanding how semantic knowledge is encoded internally. Training linear classifiers on probing tasks is a principle approach to denote the vector of a certain concept in the representation space. However, the single vector identified for a concept varies with both data and training, making it less robust and weakening its effectiveness in real-world applications. To address this challenge, we propose an approach to approximate the subspace representing a specific concept. Built on linear probing classifiers, we extend the concept vectors into Gaussian Concept Subspace (GCS). We demonstrate GCS's effectiveness through measuring its faithfulness and plausibility across multiple LLMs with different sizes and architectures. Additionally, we use representation intervention tasks to showcase its efficacy in real-world applications such as emotion steering. Experimental results indicate that GCS concept vectors have the potential to balance steering performance and maintaining the fluency in natural language generation tasks.
Authors: Zhijian Li, Stefan Larson, Kevin Leach
Abstract: Rapid document classification is critical in several time-sensitive applications like digital forensics and large-scale media classification. Traditional approaches that rely on heavy-duty deep learning models fall short due to high inference times over vast input datasets and computational resources associated with analyzing whole documents. In this paper, we present a method using lightweight supervised learning models, combined with a TF-IDF feature extraction-based tokenization method, to accurately and efficiently classify documents based solely on file names, that substantially reduces inference time. Our results indicate that file name classifiers can process more than 90% of in-scope documents with 99.63% and 96.57% accuracy when tested on two datasets, while being 442x faster than more complex models such as DiT. Our method offers a crucial solution to efficiently process vast document datasets in critical scenarios, enabling fast and more reliable document classification.
Authors: Collin Zhang, Tingwei Zhang, Vitaly Shmatikov
Abstract: We design, implement, and evaluate adversarial decoding, a new, generic text generation technique that produces readable documents for different adversarial objectives. Prior methods either produce easily detectable gibberish, or cannot handle objectives that include embedding similarity. In particular, they only work for direct attacks (such as jailbreaking) and cannot produce adversarial text for realistic indirect injection, e.g., documents that (1) are retrieved in RAG systems in response to broad classes of queries, and also (2) adversarially influence subsequent generation. We also show that fluency (low perplexity) is not sufficient to evade filtering. We measure the effectiveness of adversarial decoding for different objectives, including RAG poisoning, jailbreaking, and evasion of defensive filters, and demonstrate that it outperforms existing methods while producing readable adversarial documents.
Authors: Howard Yen, Tianyu Gao, Minmin Hou, Ke Ding, Daniel Fleischer, Peter Izsak, Moshe Wasserblat, Danqi Chen
Abstract: Many benchmarks exist for evaluating long-context language models (LCLMs), yet developers often rely on synthetic tasks such as needle-in-a-haystack (NIAH) or an arbitrary subset of tasks. However, it remains unclear whether these benchmarks reflect the diverse downstream applications of LCLMs, and such inconsistencies further complicate model comparison. We investigate the underlying reasons behind these practices and find that existing benchmarks often provide noisy signals due to limited coverage of applications, insufficient context lengths, unreliable metrics, and incompatibility with base models. In this work, we introduce HELMET (How to Evaluate Long-context Models Effectively and Thoroughly), a comprehensive benchmark encompassing seven diverse, application-centric categories. We also address several issues in previous benchmarks by adding controllable lengths up to 128K tokens, model-based evaluation for reliable metrics, and few-shot prompting for robustly evaluating base models. Consequently, we demonstrate that HELMET offers more reliable and consistent rankings of frontier LCLMs. Through a comprehensive study of 59 LCLMs, we find that (1) synthetic tasks like NIAH do not reliably predict downstream performance; (2) the diverse categories in HELMET exhibit distinct trends and low correlations with each other; and (3) while most LCLMs achieve perfect NIAH scores, open-source models significantly lag behind closed ones when tasks require full-context reasoning or following complex instructions -- the gap widens as length increases. Finally, we recommend using our RAG tasks for fast model development, as they are easy to run and better predict other downstream performance; ultimately, we advocate for a holistic evaluation across diverse tasks.
Authors: Heming Xia, Yongqi Li, Jun Zhang, Cunxiao Du, Wenjie Li
Abstract: Speculative decoding (SD) has emerged as a widely used paradigm to accelerate LLM inference without compromising quality. It works by first employing a compact model to draft multiple tokens efficiently and then using the target LLM to verify them in parallel. While this technique has achieved notable speedups, most existing approaches necessitate either additional parameters or extensive training to construct effective draft models, thereby restricting their applicability across different LLMs and tasks. To address this limitation, we explore a novel plug-and-play SD solution with layer-skipping, which skips intermediate layers of the target LLM as the compact draft model. Our analysis reveals that LLMs exhibit great potential for self-acceleration through layer sparsity and the task-specific nature of this sparsity. Building on these insights, we introduce SWIFT, an on-the-fly self-speculative decoding algorithm that adaptively selects intermediate layers of LLMs to skip during inference. SWIFT does not require auxiliary models or additional training, making it a plug-and-play solution for accelerating LLM inference across diverse input data streams. Our extensive experiments across a wide range of models and downstream tasks demonstrate that SWIFT can achieve over a 1.3x-1.6x speedup while preserving the original distribution of the generated text. We release our code in https://github.com/hemingkx/SWIFT.
Authors: Valentin Knappich, Simon Razniewski, Anna H\"atty, Annemarie Friedrich
Abstract: Dealing with long and highly complex technical text is a challenge for Large Language Models (LLMs), which still have to unfold their potential in supporting expensive and timeintensive processes like patent drafting. Within patents, the description constitutes more than 90% of the document on average. Yet, its automatic generation remains understudied. When drafting patent applications, patent attorneys typically receive invention reports (IRs), which are usually confidential, hindering research on LLM-supported patent drafting. Often, prepublication research papers serve as IRs. We leverage this duality to build PAP2PAT, an open and realistic benchmark for patent drafting consisting of 1.8k patent-paper pairs describing the same inventions. To address the complex longdocument patent generation task, we propose chunk-based outline-guided generation using the research paper as invention specification. Our extensive evaluation using PAP2PAT and a human case study show that LLMs can effectively leverage information from the paper, but still struggle to provide the necessary level of detail. Fine-tuning leads to more patent-style language, but also to more hallucination. We release our data and code https://github.com/boschresearch/Pap2Pat.
Authors: Jinlong Pang, Jiaheng Wei, Ankit Parag Shah, Zhaowei Zhu, Yaxuan Wang, Chen Qian, Yang Liu, Yujia Bao, Wei Wei
Abstract: Instruction tuning is critical for adapting large language models (LLMs) to downstream tasks, and recent studies have demonstrated that small amounts of human-curated data can outperform larger datasets, challenging traditional data scaling laws. While LLM-based data quality rating systems offer a cost-effective alternative to human annotation, they often suffer from inaccuracies and biases, even in powerful models like GPT-4. In this work, we introduce DS2, a Diversity-aware Score curation method for Data Selection. By systematically modeling error patterns through a score transition matrix, DS2 corrects LLM-based scores and promotes diversity in the selected data samples. Our approach shows that a curated subset (just 3.3% of the original dataset) outperforms full-scale datasets (300k samples) across various machine-alignment benchmarks, and matches or surpasses human-aligned datasets such as LIMA with the same sample size (1k samples). These findings challenge conventional data scaling assumptions, highlighting that redundant, low-quality samples can degrade performance and reaffirming that "more can be less."
Authors: Wenhong Zhu, Zhiwei He, Xiaofeng Wang, Pengfei Liu, Rui Wang
Abstract: Aligning language models (LMs) with human preferences has become a key area of research, enabling these models to meet diverse user needs better. Inspired by weak-to-strong generalization, where a strong LM fine-tuned on labels generated by a weaker model can consistently outperform its weak supervisor, we extend this idea to model alignment. In this work, we observe that the alignment behavior in weaker models can be effectively transferred to stronger models and even exhibit an amplification effect. Based on this insight, we propose a method called Weak-to-Strong Preference Optimization (WSPO), which achieves strong model alignment by learning the distribution differences before and after the alignment of the weak model. Experiments demonstrate that WSPO delivers outstanding performance, improving the win rate of Qwen2-7B-Instruct on Arena-Hard from 39.70 to 49.60, achieving a remarkable 47.04 length-controlled win rate on AlpacaEval 2, and scoring 7.33 on MT-bench. Our results suggest that using the weak model to elicit a strong model with a high alignment ability is feasible.
Authors: Esteban Garces Arias, Hannah Blocher, Julian Rodemann, Meimingwei Li, Christian Heumann, Matthias A{\ss}enmacher
Abstract: Open-ended text generation has become a prominent task in natural language processing due to the rise of powerful (large) language models. However, evaluating the quality of these models and the employed decoding strategies remains challenging because of trade-offs among widely used metrics such as coherence, diversity, and perplexity. Decoding methods often excel in some metrics while underperforming in others, complicating the establishment of a clear ranking. In this paper, we present novel ranking strategies within this multicriteria framework. Specifically, we employ benchmarking approaches based on partial orderings and present a new summary metric designed to balance existing automatic indicators, providing a more holistic evaluation of text generation quality. Our experiments demonstrate that the proposed methods offer a robust way to compare decoding strategies, and serve as valuable tools in guiding model selection for open-ended text generation tasks. Finally, we suggest future directions for improving evaluation methodologies in text generation. Our codebase, datasets, and models are publicly available.
Authors: Honglin Mu, Han He, Yuxin Zhou, Yunlong Feng, Yang Xu, Libo Qin, Xiaoming Shi, Zeming Liu, Xudong Han, Qi Shi, Qingfu Zhu, Wanxiang Che
Abstract: Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential vulnerabilities by crafting malicious prompts that induce model outputs contrary to safety alignments. Existing black-box jailbreak methods often rely on model feedback, repeatedly submitting queries with detectable malicious instructions during the attack search process. Although these approaches are effective, the attacks may be intercepted by content moderators during the search process. We propose an improved transfer attack method that guides malicious prompt construction by locally training a mirror model of the target black-box model through benign data distillation. This method offers enhanced stealth, as it does not involve submitting identifiable malicious instructions to the target model during the search phase. Our approach achieved a maximum attack success rate of 92%, or a balanced value of 80% with an average of 1.5 detectable jailbreak queries per sample against GPT-3.5 Turbo on a subset of AdvBench. These results underscore the need for more robust defense mechanisms.
Authors: Andrew Estornell, Jean-Francois Ton, Yuanshun Yao, Yang Liu
Abstract: Large language models (LLMs) have demonstrated a remarkable ability to serve as general-purpose tools for various language-based tasks. Recent works have demonstrated that the efficacy of such models can be improved through iterative dialog between multiple models. While these paradigms show promise in improving model efficacy, most works in this area treat collaboration as an emergent behavior, rather than a learned behavior. In doing so, current multi-agent frameworks rely on collaborative behaviors to have been sufficiently trained into off-the-shelf models. To address this limitation, we propose ACC-Collab, an Actor-Critic based learning framework to produce a two-agent team (an actor-agent and a critic-agent) specialized in collaboration. We demonstrate that ACC-Collab outperforms SotA multi-agent techniques on a wide array of benchmarks.
Authors: Hoang H Nguyen, Khyati Mahajan, Vikas Yadav, Julian Salazar, Philip S. Yu, Masoud Hashemi, Rishabh Maheshwary
Abstract: Although multilingual LLMs have achieved remarkable performance across benchmarks, we find they continue to underperform on non-Latin script languages across contemporary LLM families. This discrepancy arises from the fact that LLMs are pretrained with orthographic scripts, which are dominated by Latin characters that obscure their shared phonology with non-Latin scripts. We propose leveraging phonemic transcriptions as complementary signals to induce script-invariant representations. Our study demonstrates that integrating phonemic signals improves performance across both non-Latin and Latin script languages, with a particularly significant impact on closing the performance gap between the two. Through detailed experiments, we show that phonemic and orthographic scripts retrieve distinct examples for in-context learning (ICL). This motivates our proposed Mixed-ICL retrieval strategy, where further aggregation from both leads to our significant performance improvements for both Latin script languages (up to 12.6%) and non-Latin script languages (up to 15.1%) compared to randomized ICL retrieval.
Authors: Shauli Ravfogel, Anej Svete, V\'esteinn Sn{\ae}bjarnarson, Ryan Cotterell
Abstract: Understanding and manipulating the causal generation mechanisms in language models is essential for controlling their behavior. Previous work has primarily relied on techniques such as representation surgery -- e.g., model ablations or manipulation of linear subspaces tied to specific concepts -- to \emph{intervene} on these models. To understand the impact of interventions precisely, it is useful to examine \emph{counterfactuals} -- e.g., how a given sentence would have appeared had it been generated by the model following a specific intervention. We highlight that counterfactual reasoning is conceptually distinct from interventions, as articulated in Pearl's causal hierarchy. Based on this observation, we propose a framework for generating true string counterfactuals by reformulating language models as a structural equation model using the Gumbel-max trick, which we called Gumbel counterfactual generation. This reformulation allows us to model the joint distribution over original strings and their counterfactuals resulting from the same instantiation of the sampling noise. We develop an algorithm based on hindsight Gumbel sampling that allows us to infer the latent noise variables and generate counterfactuals of observed strings. Our experiments demonstrate that the approach produces meaningful counterfactuals while at the same time showing that commonly used intervention techniques have considerable undesired side effects.
Authors: Laura Ruis, Maximilian Mozes, Juhan Bae, Siddhartha Rao Kamalakara, Dwarak Talupuru, Acyr Locatelli, Robert Kirk, Tim Rockt\"aschel, Edward Grefenstette, Max Bartolo
Abstract: The capabilities and limitations of Large Language Models have been sketched out in great detail in recent years, providing an intriguing yet conflicting picture. On the one hand, LLMs demonstrate a general ability to solve problems. On the other hand, they show surprising reasoning gaps when compared to humans, casting doubt on the robustness of their generalisation strategies. The sheer volume of data used in the design of LLMs has precluded us from applying the method traditionally used to measure generalisation: train-test set separation. To overcome this, we study what kind of generalisation strategies LLMs employ when performing reasoning tasks by investigating the pretraining data they rely on. For two models of different sizes (7B and 35B) and 2.5B of their pretraining tokens, we identify what documents influence the model outputs for three simple mathematical reasoning tasks and contrast this to the data that are influential for answering factual questions. We find that, while the models rely on mostly distinct sets of data for each factual question, a document often has a similar influence across different reasoning questions within the same task, indicating the presence of procedural knowledge. We further find that the answers to factual questions often show up in the most influential data. However, for reasoning questions the answers usually do not show up as highly influential, nor do the answers to the intermediate reasoning steps. When we characterise the top ranked documents for the reasoning questions qualitatively, we confirm that the influential documents often contain procedural knowledge, like demonstrating how to obtain a solution using formulae or code. Our findings indicate that the approach to reasoning the models use is unlike retrieval, and more like a generalisable strategy that synthesises procedural knowledge from documents doing a similar form of reasoning.
Authors: Yifan Zhang
Abstract: The rapid advancement of large language models (LLMs) such as GPT-3, PaLM, and Llama has significantly transformed natural language processing, showcasing remarkable capabilities in understanding and generating language. However, these models often struggle with tasks requiring complex reasoning, particularly in mathematical problem-solving, due in part to the scarcity of large-scale, high-quality, domain-specific datasets necessary for training sophisticated reasoning abilities. To address this limitation, we introduce Template-based Data Generation (TDG), a novel approach that leverages LLMs (GPT-4) to automatically generate parameterized meta-templates, which are then used to synthesize a vast array of high-quality problems and solutions. Leveraging TDG, we create TemplateMath Part I: TemplateGSM, a dataset comprising over 7 million synthetically generated grade school math problems--each accompanied by code-based and natural language solutions--with the potential to generate an effectively unlimited number more. This dataset alleviates the scarcity of large-scale mathematical datasets and serves as a valuable resource for pre-training, fine-tuning, and evaluating LLMs in mathematical reasoning. Our method not only enables the generation of virtually infinite data but also elevates data augmentation to a new level by using GPT-4 for meta-template generation, ensuring diverse and high-quality problem structures. The TemplateMath Part I: TemplateGSM dataset is publicly available at https://huggingface.co/datasets/math-ai/TemplateGSM. The code is available at https://github.com/iiis-ai/TemplateMath.
URLs: https://huggingface.co/datasets/math-ai/TemplateGSM., https://github.com/iiis-ai/TemplateMath.
Authors: Songlin Yang, Jan Kautz, Ali Hatamizadeh
Abstract: Linear Transformers have gained attention as efficient alternatives to standard Transformers, but their performance in retrieval and long-context tasks has been limited. To address these limitations, recent work has explored two distinct mechanisms: gating for adaptive memory control and the delta update rule for precise memory modifications. We observe that these mechanisms are complementary: gating enables rapid memory erasure while the delta rule facilitates targeted updates. Building on this insight, we introduce the gated delta rule and develop a parallel training algorithm optimized for modern hardware. Our proposed architecture, Gated DeltaNet, consistently surpasses existing models like Mamba2 and DeltaNet across multiple benchmarks, including language modeling, common-sense reasoning, in-context retrieval, length extrapolation, and long-context understanding. We further enhance performance by developing hybrid architectures that combine Gated DeltaNet layers with sliding window attention or Mamba2 layers, achieving both improved training efficiency and superior task performance.
Authors: Sourabrata Mukherjee, Soumya Teotia, Sougata Saha, Monojit Choudhury
Abstract: Honorifics serve as powerful linguistic markers that reflect social hierarchies and cultural values. This paper presents a large-scale, cross-linguistic exploration of usage of honorific pronouns in Bengali and Hindi Wikipedia articles, shedding light on how socio-cultural factors shape language. Using LLM (GPT-4o), we annotated 10, 000 articles of real and fictional beings in each language for several sociodemographic features such as gender, age, fame, and exoticness, and the use of honorifics. We find that across all feature combinations, use of honorifics is consistently more common in Bengali than Hindi. For both languages, the use non-honorific pronouns is more commonly observed for infamous, juvenile, and exotic beings. Notably, we observe a gender bias in use of honorifics in Hindi, with men being more commonly referred to with honorifics than women.
Authors: Yicheng Tao, Haotian Liu, Shanwen Wang, Hongteng Xu
Abstract: Premise selection is a crucial yet challenging step in mathematical formalization, especially for users with limited experience. Due to the lack of available formalization projects, existing approaches that leverage language models often suffer from data scarcity. In this work, we introduce an innovative method for training a premise retriever to support the formalization of mathematics. Our approach employs a BERT model to embed proof states and premises into a shared latent space. The retrieval model is trained within a contrastive learning framework and incorporates a domain-specific tokenizer along with a fine-grained similarity computation method. Experimental results show that our model is highly competitive compared to existing baselines, achieving strong performance while requiring fewer computational resources. Performance is further enhanced through the integration of a re-ranking module. To streamline the formalization process, we will release a search engine that enables users to query Mathlib theorems directly using proof states, significantly improving accessibility and efficiency. Codes are available at https://github.com/ruc-ai4math/Premise-Retrieval.
Authors: Ved Sirdeshmukh, Kaustubh Deshpande, Johannes Mols, Lifeng Jin, Ed-Yeremai Cardona, Dean Lee, Jeremy Kritz, Willow Primack, Summer Yue, Chen Xing
Abstract: We present MultiChallenge, a pioneering benchmark evaluating large language models (LLMs) on conducting multi-turn conversations with human users, a crucial yet underexamined capability for their applications. MultiChallenge identifies four categories of challenges in multi-turn conversations that are not only common and realistic among current human-LLM interactions, but are also challenging to all current frontier LLMs. All 4 challenges require accurate instruction-following, context allocation, and in-context reasoning at the same time. We also develop LLM as judge with instance-level rubrics to facilitate an automatic evaluation method with fair agreement with experienced human raters. Despite achieving near-perfect scores on existing multi-turn evaluation benchmarks, all frontier models have less than 50% accuracy on MultiChallenge, with the top-performing Claude 3.5 Sonnet (June 2024) achieving just a 41.4% average accuracy.
Authors: Wei Wu, Qiuyi Li, Mingyang Li, Kun Fu, Fuli Feng, Jieping Ye, Hui Xiong, Zheng Wang
Abstract: Advancements in DNA sequencing technologies have significantly improved our ability to decode genomic sequences. However, the prediction and interpretation of these sequences remain challenging due to the intricate nature of genetic material. Large language models (LLMs) have introduced new opportunities for biological sequence analysis. Recent developments in genomic language models have underscored the potential of LLMs in deciphering DNA sequences. Nonetheless, existing models often face limitations in robustness and application scope, primarily due to constraints in model structure and training data scale. To address these limitations, we present GENERator, a generative genomic foundation model featuring a context length of 98k base pairs (bp) and 1.2B parameters. Trained on an expansive dataset comprising 386B bp of eukaryotic DNA, the GENERator demonstrates state-of-the-art performance across both established and newly proposed benchmarks. The model adheres to the central dogma of molecular biology, accurately generating protein-coding sequences that translate into proteins structurally analogous to known families. It also shows significant promise in sequence optimization, particularly through the prompt-responsive generation of enhancer sequences with specific activity profiles. These capabilities position the GENERator as a pivotal tool for genomic research and biotechnological advancement, enhancing our ability to interpret and predict complex biological systems and enabling precise genomic interventions. Implementation details and supplementary resources are available at https://github.com/GenerTeam/GENERator.
Authors: Sumin Jo, Junseong Choi, Jiho Kim, Edward Choi
Abstract: Recent studies have combined Large Language Models (LLMs) with Knowledge Graphs (KGs) to enhance reasoning, improving inference accuracy without additional training while mitigating hallucination. However, existing frameworks are often rigid, struggling to adapt to KG or task changes. They also rely heavily on powerful LLMs for reliable (i.e., trustworthy) reasoning. To address this, We introduce R2-KG, a plug-and-play, dual-agent framework that separates reasoning into two roles: an Operator (a low-capacity LLM) that gathers evidence and a Supervisor (a high-capacity LLM) that makes final judgments. This design is cost-efficient for LLM inference while still maintaining strong reasoning accuracy. Additionally, R2-KG employs an Abstention mechanism, generating answers only when sufficient evidence is collected from KG, which significantly enhances reliability. Experiments across multiple KG-based reasoning tasks show that R2-KG consistently outperforms baselines in both accuracy and reliability, regardless of the inherent capability of LLMs used as the Operator. Further experiments reveal that the single-agent version of R2-KG, equipped with a strict self-consistency strategy, achieves significantly higher-than-baseline reliability while reducing inference cost. However, it also leads to a higher abstention rate in complex KGs. Our findings establish R2-KG as a flexible and cost-effective solution for KG-based reasoning. It reduces reliance on high-capacity LLMs while ensuring trustworthy inference.
Authors: Leena Mathur, Marian Qian, Paul Pu Liang, Louis-Philippe Morency
Abstract: Social reasoning abilities are crucial for AI systems to effectively interpret and respond to multimodal human communication and interaction within social contexts. We introduce Social Genome, the first benchmark for fine-grained, grounded social reasoning abilities of multimodal models. Social Genome contains 272 videos of interactions and 1,486 human-annotated reasoning traces related to inferences about these interactions. These traces contain 5,777 reasoning steps that reference evidence from visual cues, verbal cues, vocal cues, and external knowledge (contextual knowledge external to videos). Social Genome is also the first modeling challenge to study external knowledge in social reasoning. Social Genome computes metrics to holistically evaluate semantic and structural qualities of model-generated social reasoning traces. We demonstrate the utility of Social Genome through experiments with state-of-the-art models, identifying performance gaps and opportunities for future research to improve the grounded social reasoning abilities of multimodal models.
Authors: Sophie Xhonneux, David Dobre, Mehrnaz Mofakhami, Leo Schwinn, Gauthier Gidel
Abstract: Most safety training methods for large language models (LLMs) based on fine-tuning rely on dramatically changing the output distribution of the model when faced with a harmful request, shifting it from an unsafe answer to a refusal to respond. These methods inherently compromise model capabilities and might make auto-regressive models vulnerable to attacks that make likely an initial token of affirmative response. To avoid that, we propose to expand the model's vocabulary with a special token we call red flag token (
Authors: Heegyu Kim, Taeyang Jeon, Seungtaek Choi, Ji Hoon Hong, Dong Won Jeon, Sung Beom Cho, Ga-Yeon Baek, Kyung-Won Kwak, Dong-Hee Lee, Sun-Jin Choi, Jisu Bae, Chihoon Lee, Yunseo Kim, Jinsung Park, Hyunsouk Cho
Abstract: Materials synthesis is vital for innovations such as energy storage, catalysis, electronics, and biomedical devices. Yet, the process relies heavily on empirical, trial-and-error methods guided by expert intuition. Our work aims to support the materials science community by providing a practical, data-driven resource. We have curated a comprehensive dataset of 17K expert-verified synthesis recipes from open-access literature, which forms the basis of our newly developed benchmark, AlchemyBench. AlchemyBench offers an end-to-end framework that supports research in large language models applied to synthesis prediction. It encompasses key tasks, including raw materials and equipment prediction, synthesis procedure generation, and characterization outcome forecasting. We propose an LLM-as-a-Judge framework that leverages large language models for automated evaluation, demonstrating strong statistical agreement with expert assessments. Overall, our contributions offer a supportive foundation for exploring the capabilities of LLMs in predicting and guiding materials synthesis, ultimately paving the way for more efficient experimental design and accelerated innovation in materials science.
Authors: Guangliang Liu, Lei Jiang, Xitong Zhang, Kristen Marie Johnson
Abstract: Ensuring that Large Language Models (LLMs) return just responses which adhere to societal values is crucial for their broader application. Prior research has shown that LLMs often fail to perform satisfactorily on tasks requiring moral cognizance, such as ethics-based judgments. While current approaches have focused on fine-tuning LLMs with curated datasets to improve their capabilities on such tasks, choosing the optimal learning paradigm to enhance the ethical responses of LLMs remains an open research debate. In this work, we aim to address this fundamental question: can current learning paradigms enable LLMs to acquire sufficient moral reasoning capabilities? Drawing from distributional semantics theory and the pragmatic nature of moral discourse, our analysis indicates that performance improvements follow a mechanism similar to that of semantic-level tasks, and therefore remain affected by the pragmatic nature of morals latent in discourse, a phenomenon we name the pragmatic dilemma. We conclude that this pragmatic dilemma imposes significant limitations on the generalization ability of current learning paradigms, making it the primary bottleneck for moral reasoning acquisition in LLMs.
Authors: Yaxi Lu, Haolun Li, Xin Cong, Zhong Zhang, Yesai Wu, Yankai Lin, Zhiyuan Liu, Fangming Liu, Maosong Sun
Abstract: This study investigates the structured generation capabilities of large language models (LLMs), focusing on producing valid JSON outputs against a given schema. Despite the widespread use of JSON in integrating language models with programs, there is a lack of comprehensive analysis and benchmarking of these capabilities. We explore various aspects of JSON generation, such as structure understanding, escaping, and natural language description, to determine how to assess and enable LLMs to generate valid responses. Building upon this, we propose SchemaBench features around 40K different JSON schemas to obtain and assess models' abilities in generating valid JSON. We find that the latest LLMs are still struggling to generate a valid JSON string. Moreover, we demonstrate that incorporating reinforcement learning with a Fine-grained Schema Validator can further enhance models' understanding of JSON schema, leading to improved performance. Our models demonstrate significant improvement in both generating JSON outputs and downstream tasks.
Authors: Thanet Markchom, Tong Wu, Liting Huang, Huizhi Liang
Abstract: SemEval-2025 Task 1 focuses on ranking images based on their alignment with a given nominal compound that may carry idiomatic meaning in both English and Brazilian Portuguese. To address this challenge, this work uses generative large language models (LLMs) and multilingual CLIP models to enhance idiomatic compound representations. LLMs generate idiomatic meanings for potentially idiomatic compounds, enriching their semantic interpretation. These meanings are then encoded using multilingual CLIP models, serving as representations for image ranking. Contrastive learning and data augmentation techniques are applied to fine-tune these embeddings for improved performance. Experimental results show that multimodal representations extracted through this method outperformed those based solely on the original nominal compounds. The fine-tuning approach shows promising outcomes but is less effective than using embeddings without fine-tuning. The source code used in this paper is available at https://github.com/tongwu17/SemEval-2025-Task1-UoR-NCL.
URLs: https://github.com/tongwu17/SemEval-2025-Task1-UoR-NCL.
Authors: David James Woo, Hengky Susanto, Chi Ho Yeung, Kai Guo
Abstract: Generative artificial intelligence (AI) chatbots, such as ChatGPT, are reshaping how English as a foreign language (EFL) students write since students can compose texts by integrating their own words with AI-generated text. This study investigated how 59 Hong Kong secondary school students with varying levels of academic achievement interacted with AI-generated text to compose a feature article, exploring whether any interaction patterns benefited the overall quality of the article. Through content analysis, multiple linear regression and cluster analysis, we found the overall number of words -- whether AI- or human-generated -- is the main predictor of writing quality. However, the impact varies by students' competence to write independently, for instance, by using their own words accurately and coherently to compose a text, and to follow specific interaction patterns with AI-generated text. Therefore, although composing texts with human words and AI-generated text may become prevalent in EFL writing classrooms, without educators' careful attention to EFL writing pedagogy and AI literacy, high-achieving students stand to benefit more from using AI-generated text than low-achieving students.
Authors: Teng Lin, Yizhang Zhu, Yuyu Luo, Nan Tang
Abstract: Multi-entity question answering (MEQA) poses significant challenges for large language models (LLMs), which often struggle to consolidate scattered information across multiple documents. An example question might be "What is the distribution of IEEE Fellows among various fields of study?", which requires retrieving information from diverse sources e.g., Wikipedia pages. The effectiveness of current retrieval-augmented generation (RAG) methods is limited by the LLMs' capacity to aggregate insights from numerous pages. To address this gap, this paper introduces a structured RAG (SRAG) framework that systematically organizes extracted entities into relational tables (e.g., tabulating entities with schema columns like "name" and "field of study") and then apply table-based reasoning techniques. Our approach decouples retrieval and reasoning, enabling LLMs to focus on structured data analysis rather than raw text aggregation. Extensive experiments on Wikipedia-based multi-entity QA tasks demonstrate that SRAG significantly outperforms state-of-the-art long-context LLMs and RAG solutions, achieving a 29.6% improvement in accuracy. The results underscore the efficacy of structuring unstructured data to enhance LLMs' reasoning capabilities.
Authors: Mohammad Albinhassan, Pranava Madhyastha, Alessandra Russo
Abstract: Ensuring both syntactic and semantic correctness in Large Language Model (LLM) outputs remains a significant challenge, despite being critical for real-world deployment. In this paper, we introduce $\texttt{SEM-CTRL}$, a unified approach that enforces rich context-sensitive constraints and task- and instance-specific semantics directly on an LLM decoder. Our approach integrates token-level MCTS, which is guided by specific syntactic and semantic constraints. The constraints over the desired outputs are expressed using Answer Set Grammars -- a logic-based formalism that generalizes context-sensitive grammars while incorporating background knowledge to represent task-specific semantics. We show that our approach guarantees correct completions for any off-the-shelf LLM without the need for fine-tuning. We evaluate $\texttt{SEM-CTRL}$ on a range of tasks, including synthetic grammar synthesis, combinatorial reasoning, and planning. Our results demonstrate that $\texttt{SEM-CTRL}$ allows small pre-trained LLMs to efficiently outperform larger variants and state-of-the-art reasoning models (e.g., o1-preview) while simultaneously guaranteeing solution correctness.
Authors: Jude Khouja, Karolina Korgul, Simi Hellsten, Lingyi Yang, Vlad Neacs, Harry Mayne, Ryan Kearns, Andrew Bean, Adam Mahdi
Abstract: Assessing the reasoning capabilities of large language models (LLMs) is susceptible to overestimation due to data exposure of evaluation benchmarks. We introduce a framework for producing linguistic reasoning problems that reduces the effect of memorisation in model performance estimates and apply this framework to develop LINGOLY-TOO, a challenging benchmark for linguistic reasoning. By developing orthographic templates, we dynamically obfuscate the writing systems of real languages to generate numerousquestion variations. These variations preserve the reasoning steps required for each solution while reducing the likelihood of specific problem instances appearing in model training data. Our experiments demonstrate that frontier models, including Claud 3.7 Sonnet, o1-preview and DeepSeek R1, struggle with advanced reasoning. Our analysis also shows that LLMs exhibit noticeable variance in accuracy across permutations of the same problem, and on average perform better on questions appearing in their original orthography. Our findings highlight the opaque nature of response generation in LLMs and provide evidence that prior data exposure contributes to over estimating the reasoning capabilities of frontier models.
Authors: Jabez Magomere, Emanuele La Malfa, Manuel Tonneau, Ashkan Kazemi, Scott Hale
Abstract: Online misinformation remains a critical challenge, and fact-checkers increasingly rely on embedding-based methods to retrieve relevant fact-checks. Yet, when debunked claims reappear in edited forms, the performance of these methods is unclear. In this work, we introduce a taxonomy of six common real-world misinformation edits and propose a perturbation framework that generates valid, natural claim variations. Our multi-stage retrieval evaluation reveals that standard embedding models struggle with user-introduced edits, while LLM-distilled embeddings offer improved robustness at a higher computational cost. Although a strong reranker helps mitigate some issues, it cannot fully compensate for first-stage retrieval gaps. Addressing these retrieval gaps, our train- and inference-time mitigation approaches enhance in-domain robustness by up to 17 percentage points and boost out-of-domain generalization by 10 percentage points over baseline models. Overall, our findings provide practical improvements to claim-matching systems, enabling more reliable fact-checking of evolving misinformation.
Authors: Rickard Br\"uel-Gabrielsson, Tongzhou Wang, Manel Baradad, Justin Solomon
Abstract: Despite dropout's ubiquity in machine learning, its effectiveness as a form of data augmentation remains under-explored. We address two key questions: (i) When is dropout effective as an augmentation strategy? (ii) Is dropout uniquely effective under these conditions? To explore these questions, we propose Deep Augmentation, a network- and modality-agnostic method that applies dropout or PCA transformations to targeted layers in neural networks. Through extensive experiments on contrastive learning tasks in NLP, computer vision, and graph learning, we find that uniformly applying dropout across layers does not consistently improve performance. Instead, dropout proves most beneficial in deeper layers and can be matched by alternative augmentations (e.g., PCA). We also show that a stop-gradient operation is critical for ensuring dropout functions effectively as an augmentation, and that performance trends invert when moving from contrastive tasks to supervised tasks. Our analysis suggests that Deep Augmentation helps mitigate inter-layer co-adaptation -- a notable issue in self-supervised learning due to the absence of labeled data. Drawing on these insights, we outline a procedure for selecting the optimal augmentation layer and demonstrate that Deep Augmentation can outperform traditional input-level augmentations. This simple yet powerful approach can be seamlessly integrated into a wide range of architectures and modalities, yielding notable gains in both performance and generalization.
Authors: Zongxin Yang, Guikun Chen, Xiaodi Li, Wenguan Wang, Yi Yang
Abstract: Recent LLM-driven visual agents mainly focus on solving image-based tasks, which limits their ability to understand dynamic scenes, making it far from real-life applications like guiding students in laboratory experiments and identifying their mistakes. Hence, this paper explores DoraemonGPT, a comprehensive and conceptually elegant system driven by LLMs to understand dynamic scenes. Considering the video modality better reflects the ever-changing nature of real-world scenarios, we exemplify DoraemonGPT as a video agent. Given a video with a question/task, DoraemonGPT begins by converting the input video into a symbolic memory that stores task-related attributes. This structured representation allows for spatial-temporal querying and reasoning by well-designed sub-task tools, resulting in concise intermediate results. Recognizing that LLMs have limited internal knowledge when it comes to specialized domains (e.g., analyzing the scientific principles underlying experiments), we incorporate plug-and-play tools to assess external knowledge and address tasks across different domains. Moreover, a novel LLM-driven planner based on Monte Carlo Tree Search is introduced to explore the large planning space for scheduling various tools. The planner iteratively finds feasible solutions by backpropagating the result's reward, and multiple solutions can be summarized into an improved final answer. We extensively evaluate DoraemonGPT's effectiveness on three benchmarks and several in-the-wild scenarios. The code will be released at https://github.com/z-x-yang/DoraemonGPT.
Authors: Shen Gao, Hao Li, Chengrui Huang, Quan Tu, Zhiliang Tian, Minlie Huang, Shuo Shang
Abstract: Large language model agents have demonstrated remarkable advancements across various complex tasks. Recent works focus on optimizing the agent team or employing self-reflection to iteratively solve complex tasks. Since these agents are all based on the same LLM, only conducting self-evaluation or removing underperforming agents does not substantively enhance the capability of the agents. We argue that a comprehensive evaluation and accumulating experience from evaluation feedback is an effective approach to improving system performance. In this paper, we propose Reusable Experience Accumulation with 360$^\circ$ Assessment (360$^\circ$REA), a hierarchical multi-agent framework inspired by corporate organizational practices. The framework employs a novel 360$^\circ$ performance assessment method for multi-perspective performance evaluation with fine-grained assessment. To enhance the capability of agents in addressing complex tasks, we introduce dual-level experience pool for agents to accumulate experience through fine-grained assessment. Extensive experiments on complex task datasets demonstrate the effectiveness of 360$^\circ$REA.
Authors: William Merrill, Jackson Petty, Ashish Sabharwal
Abstract: State-space models (SSMs) have emerged as a potential alternative architecture for building large language models (LLMs) compared to the previously ubiquitous transformer architecture. One theoretical weakness of transformers is that they cannot express certain kinds of sequential computation and state tracking (Merrill & Sabharwal, 2023), which SSMs are explicitly designed to address via their close architectural similarity to recurrent neural networks (RNNs). But do SSMs truly have an advantage (over transformers) in expressive power for state tracking? Surprisingly, the answer is no. Our analysis reveals that the expressive power of SSMs is limited very similarly to transformers: SSMs cannot express computation outside the complexity class $\mathsf{TC}^0$. In particular, this means they cannot solve simple state-tracking problems like permutation composition. It follows that SSMs are provably unable to accurately track chess moves with certain notation, evaluate code, or track entities in a long narrative. To supplement our formal analysis, we report experiments showing that Mamba-style SSMs indeed struggle with state tracking. Thus, despite its recurrent formulation, the "state" in an SSM is an illusion: SSMs have similar expressiveness limitations to non-recurrent models like transformers, which may fundamentally limit their ability to solve real-world state-tracking problems.
Authors: Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Utkarsh Tyagi, Oriol Nieto, Zeyu Jin, Dinesh Manocha
Abstract: Large Vision-Language Models (LVLMs) often produce responses that misalign with factual information, a phenomenon known as hallucinations. While hallucinations are well-studied, the exact causes behind them remain underexplored. In this paper, we first investigate the root causes of hallucinations in LVLMs. Our findings reveal that existing mitigation techniques primarily reduce hallucinations for visual recognition prompts-those that require simple descriptions of visual elements-but fail for cognitive prompts that demand deliberate reasoning. We identify the core issue as a lack of true visual perception in LVLMs: although they can accurately recognize visual elements, they struggle to fully interpret these elements in the context of the input prompt and effectively link this recognition to their internal knowledge, which is critical for reasoning. To address this gap, we introduce Visual Description Grounded Decoding (VDGD), a simple, robust, and training-free method designed to enhance visual perception and improve reasoning capabilities in LVLMs. VDGD works by first generating a detailed description of the image and appending it as a prefix to the instruction. During response generation, tokens are sampled based on their KL divergence to the description, favoring candidates with lower divergence. Experimental results on multiple visual reasoning benchmarks and LVLMs demonstrate that VDGD consistently outperforms existing baselines 2% - 33%. Finally, we introduce VaLLu, a benchmark designed for comprehensive evaluation of the cognitive capabilities of LVLMs.
Authors: Mingda Li, Xinyu Li, Yifan Chen, Wenfeng Xuan, Weinan Zhang
Abstract: Although Retrieval-Augmented Large Language Models (RALMs) demonstrate their superiority in terms of factuality, they do not consistently outperform the original retrieval-free Language Models (LMs). Our experiments reveal that this example-level performance inconsistency exists not only between retrieval-augmented and retrieval-free LM but also among different retrievers. To understand this phenomenon, we investigate the degeneration behavior of RALMs and theoretically decompose it into four categories. Further analysis based on our decomposition reveals that the innate difference in knowledge sources and the unpredictable degeneration of the reader model contribute most to the inconsistency. Drawing from our analysis, we introduce Ensemble of Retrievers (EoR), a trainable framework that can adaptively retrieve from different knowledge sources and effectively decrease unpredictable reader errors. Our experiments on Open Domain Question Answering show that EoR substantially improves performance over the RALM with a single retriever by considerably reducing inconsistent behaviors.
Authors: Yixuan Mei, Yonghao Zhuang, Xupeng Miao, Juncheng Yang, Zhihao Jia, Rashmi Vinayak
Abstract: This paper introduces Helix, a distributed system for high-throughput, low-latency large language model (LLM) serving in heterogeneous GPU clusters. The key idea behind Helix is to formulate inference computation of LLMs over heterogeneous GPUs and network connections as a max-flow problem on directed, weighted graphs, whose nodes represent GPU instances and edges capture both GPU and network heterogeneity through their capacities. Helix then uses a mixed integer linear programming (MILP) algorithm to discover highly optimized strategies to serve LLMs on heterogeneous GPUs. This approach allows Helix to jointly optimize model placement and request scheduling, two highly entangled tasks in heterogeneous LLM serving. Our evaluation on several heterogeneous clusters ranging from 24 to 42 GPU nodes shows that Helix improves serving throughput by up to 3.3x and reduces prompting and decoding latency by up to 66% and 24%, respectively, compared to existing approaches. Helix is available at https://github.com/Thesys-lab/Helix-ASPLOS25.
Authors: Utsav Singh, Pramit Bhattacharyya, Vinay P. Namboodiri
Abstract: Developing interactive systems that utilize natural language instructions to solve complex robotic control tasks has long been a goal of the robotics community. While Large Language Models (LLMs) excel at logical reasoning, in-context learning, and code generation, translating high-level instructions into low-level robotic actions still remains challenging. Furthermore, solving such tasks often requires acquiring policies to execute diverse subtasks and integrating them to achieve the final objective. Hierarchical Reinforcement Learning (HRL) offers a promising solution for solving such tasks by enabling temporal abstraction and improved exploration. However, HRL suffers from non-stationarity caused by the changing lower-level behaviour, which hinders effective policy learning. We propose LGR2, a novel HRL framework that mitigates non-stationarity in HRL by using language-guided higher-level rewards that remain unaffected by the changing lower-level policy behaviour. To analyze the efficacy of our approach, we perform empirical analysis to demonstrate that LGR2 effectively mitigates non-stationarity in HRL and attains success rates exceeding 70% in challenging, sparsely-rewarded robotic navigation and manipulation environments, where other baselines typically fail to show significant progress. Finally, we perform real-world robotic experiments on complex tasks and demonstrate that LGR2 consistently outperforms the baselines.
Authors: Chufan Gao, Jathurshan Pradeepkumar, Trisha Das, Shivashankar Thati, Jimeng Sun
Abstract: Background The cost of drug discovery and development is substantial, with clinical trial outcomes playing a critical role in regulatory approval and patient care. However, access to large-scale, high-quality clinical trial outcome data remains limited, hindering advancements in predictive modeling and evidence-based decision-making. Methods We present the Clinical Trial Outcome (CTO) benchmark, a fully reproducible, large-scale repository encompassing approximately 125,000 drug and biologics trials. CTO integrates large language model (LLM) interpretations of publications, trial phase progression tracking, sentiment analysis from news sources, stock price movements of trial sponsors, and additional trial-related metrics. Furthermore, we manually annotated a dataset of clinical trials conducted between 2020 and 2024 to enhance the quality and reliability of outcome labels. Results The trial outcome labels in the CTO benchmark agree strongly with expert annotations, achieving an F1 score of 94 for Phase 3 trials and 91 across all phases. Additionally, benchmarking standard machine learning models on our manually annotated dataset revealed distribution shifts in recent trials, underscoring the necessity of continuously updated labeling approaches. Conclusions By analyzing CTO's performance on recent clinical trials, we demonstrate the ongoing need for high-quality, up-to-date trial outcome labels. We publicly release the CTO knowledge base and annotated labels at https://chufangao.github.io/CTOD, with regular updates to support research on clinical trial outcomes and inform data-driven improvements in drug development.
Authors: Lucas M\"oller, Pascal Tilli, Ngoc Thang Vu, Sebastian Pad\'o
Abstract: Dual encoder architectures like CLIP models map two types of inputs into a shared embedding space and predict similarities between them. Despite their success, it is, however, not understood how these models compare their two inputs. Common first-order feature-attribution methods can only provide limited insights into dual-encoders since their predictions depend on feature-interactions rather than on individual features. In this paper, we first derive a second-order method enabling the attribution of predictions by any differentiable dual encoder onto feature-interactions between its inputs. Second, we apply our method to CLIP models and show that they learn fine-grained correspondences between parts of captions and regions in images. They match objects across input modes also account for mismatches. This visual-linguistic grounding ability, however, varies heavily between object classes and exhibits pronounced out-of-domain effects. We can identify individual errors as well as systematic failure categories including object coverage, unusual scenes and correlated contexts.
Authors: Longshen Ou, Jingwei Zhao, Ziyu Wang, Gus Xia, Ye Wang
Abstract: Automatic music arrangement streamlines the creation of musical variants for composers and arrangers, reducing reliance on extensive music expertise. However, existing methods suffer from inefficient tokenization, underutilization of pre-trained music language models (LMs), and suboptimal fidelity and coherence in generated arrangements. This paper introduces an efficient multitrack music tokenizer for unconditional and conditional symbolic music generation, along with a unified sequence-to-sequence reconstruction fine-tuning objective for pre-trained music LMs that balances task-specific needs with coherence constraints. Our approach achieves state-of-the-art results on band arrangement, piano reduction, and drum arrangement, surpassing task-specific models in both objective metrics and perceptual quality. Additionally, we demonstrate that generative pretraining significantly contributes to the performance across these arrangement tasks, especially when handling long segments with complex alignment.
Authors: Liam Hebert, Marialena Kyriakidi, Hubert Pham, Krishna Sayana, James Pine, Sukhdeep Sodhi, Ambarish Jash
Abstract: Recent proposals in recommender systems represent items with their textual description, using a large language model. They show better results on standard benchmarks compared to an item ID-only model, such as Bert4Rec. In this work, we revisit the often-used Bert4Rec baseline and show that with further tuning, Bert4Rec significantly outperforms previously reported numbers, and in some datasets, is competitive with state-of-the-art models. With revised baselines for item ID-only models, this paper also establishes new competitive results for architectures that combine IDs and textual descriptions. We demonstrate this with Flare (Fusing Language models and collaborative Architectures for Recommender Enhancement). Flare is a novel hybrid sequence recommender that integrates a language model with a collaborative filtering model using a Perceiver network. Prior studies focus evaluation on datasets with limited-corpus size, but many commercially-applicable recommender systems common on the web must handle larger corpora. We evaluate Flare on a more realistic dataset with a significantly larger item vocabulary, introducing new baselines for this setting. This paper also showcases Flare's inherent ability to support critiquing, enabling users to provide feedback and refine recommendations. We leverage critiquing as an evaluation method to assess the model's language understanding and its transferability to the recommendation task.
Authors: Zhilin Wang, Alexander Bukharin, Olivier Delalleau, Daniel Egert, Gerald Shen, Jiaqi Zeng, Oleksii Kuchaiev, Yi Dong
Abstract: Reward models are critical for aligning models to follow instructions, and are typically trained following one of two popular paradigms: Bradley-Terry style or Regression style. However, there is a lack of evidence that either approach is better than the other, when adequately matched for data. This is primarily because these approaches require data collected in different (but incompatible) formats, meaning that adequately matched data is not available in existing public datasets. To tackle this problem, we release preference annotations (designed for Bradley-Terry training) to complement existing ratings (designed for Regression style training) in the HelpSteer2 dataset. To improve data interpretability, preference annotations are accompanied with human-written justifications. Using this data, we conduct the first head-to-head comparison of Bradley-Terry and Regression models when adequately matched for data. Based on insights derived from such a comparison, we propose a novel approach to combine Bradley-Terry and Regression reward modeling. A Llama-3.1-70B-Instruct model tuned with this approach scores 94.1 on RewardBench, emerging top of more than 140 reward models as of 1 Oct 2024. This reward model can then be used with REINFORCE algorithm (RLHF) to align an Instruct model to reach 85.0 on Arena Hard, which is No. 1 as of 1 Oct 2024. We open-source this dataset (CC-BY-4.0 license) at https://huggingface.co/datasets/nvidia/HelpSteer2#preferences-new -- 1-oct-2024 and openly release the trained Reward and Instruct models at https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Reward and https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct
URLs: https://huggingface.co/datasets/nvidia/HelpSteer2, https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Reward, https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct
Authors: Michael Zhang, Simran Arora, Rahul Chalamala, Alan Wu, Benjamin Spector, Aaryan Singhal, Krithik Ramesh, Christopher R\'e
Abstract: Recent works show we can linearize large language models (LLMs) -- swapping the quadratic attentions of popular Transformer-based LLMs with subquadratic analogs, such as linear attention -- avoiding the expensive pretraining costs. However, linearizing LLMs often significantly degrades model quality, still requires training over billions of tokens, and remains limited to smaller 1.3B to 7B LLMs. We thus propose Low-rank Linear Conversion via Attention Transfer (LoLCATs), a simple two-step method that improves LLM linearizing quality with orders of magnitudes less memory and compute. We base these steps on two findings. First, we can replace an LLM's softmax attentions with closely-approximating linear attentions, simply by training the linear attentions to match their softmax counterparts with an output MSE loss ("attention transfer"). Then, this enables adjusting for approximation errors and recovering LLM quality simply with low-rank adaptation (LoRA). LoLCATs significantly improves linearizing quality, training efficiency, and scalability. We significantly reduce the linearizing quality gap and produce state-of-the-art subquadratic LLMs from Llama 3 8B and Mistral 7B v0.1, leading to 20+ points of improvement on 5-shot MMLU. Furthermore, LoLCATs does so with only 0.2% of past methods' model parameters and 0.4% of their training tokens. Finally, we apply LoLCATs to create the first linearized 70B and 405B LLMs (50x larger than prior work). When compared with prior approaches under the same compute budgets, LoLCATs significantly improves linearizing quality, closing the gap between linearized and original Llama 3.1 70B and 405B LLMs by 77.8% and 78.1% on 5-shot MMLU.
Authors: Wen Yang, Minpeng Liao, Kai Fan
Abstract: Chain of Thought (CoT) of multi-step benefits from the logical structure of the reasoning steps and task-specific actions, significantly enhancing the mathematical reasoning capabilities of large language models. As the prevalence of long CoT, the number of reasoning steps exceeds manageable token limits and leads to higher computational demands. Inspired by the fundamental logic of human cognition, "derive, then reduce", we conceptualize the standard multi-step CoT as a novel Markov Chain of Thought (MCoT). In this study, we consider the mathematical reasoning task, defining each reasoning step as text accompanied by a Python code snippet. To facilitate a longer reasoning path, self-correction is enabled through interactions with the code interpreter. Our MCoT aims to compress previous reasoning steps into a simplified question, enabling efficient next-step inference without relying on a lengthy KV cache. In our experiments, we curate the $\texttt{MCoTInstruct}$ dataset, and the empirical results indicate that MCoT not only significantly enhances efficiency but also maintains comparable accuracy. While much remains to be explored, this work paves the way for exploring the long CoT reasoning abilities of LLMs. The code is available at https://github.com/james-yw/Markov-Chain-of-Thought
Authors: Shivam Singh, Karthik Swaminathan, Nabanita Dash, Ramandeep Singh, Snehasis Banerjee, Mohan Sridharan, Madhava Krishna
Abstract: An embodied agent assisting humans is often asked to complete new tasks, and there may not be sufficient time or labeled examples to train the agent to perform these new tasks. Large Language Models (LLMs) trained on considerable knowledge across many domains can be used to predict a sequence of abstract actions for completing such tasks, although the agent may not be able to execute this sequence due to task-, agent-, or domain-specific constraints. Our framework addresses these challenges by leveraging the generic predictions provided by LLM and the prior domain knowledge encoded in a Knowledge Graph (KG), enabling an agent to quickly adapt to new tasks. The robot also solicits and uses human input as needed to refine its existing knowledge. Based on experimental evaluation in the context of cooking and cleaning tasks in simulation domains, we demonstrate that the interplay between LLM, KG, and human input leads to substantial performance gains compared with just using the LLM. Project website{\S}: https://sssshivvvv.github.io/adaptbot/
Authors: Xiaoya Lu, Dongrui Liu, Yi Yu, Luxin Xu, Jing Shao
Abstract: Despite the rapid development of safety alignment techniques for LLMs, defending against multi-turn jailbreaks is still a challenging task. In this paper, we conduct a comprehensive comparison, revealing that some existing defense methods can improve the robustness of LLMs against multi-turn jailbreaks but compromise usability, i.e., reducing general capabilities or causing the over-refusal problem. From the perspective of mechanism interpretability of LLMs, we discover that these methods fail to establish a boundary that exactly distinguishes safe and harmful feature representations. Therefore, boundary-safe representations close to harmful representations are inevitably disrupted, leading to a decline in usability. To address this issue, we propose X-Boundary to push harmful representations away from boundary-safe representations and obtain an exact distinction boundary. In this way, harmful representations can be precisely erased without disrupting safe ones. Experimental results show that X-Boundary achieves state-of-the-art defense performance against multi-turn jailbreaks, while reducing the over-refusal rate by about 20% and maintaining nearly complete general capability. Furthermore, we theoretically prove and empirically verify that X-Boundary can accelerate the convergence process during training. Please see our code at: https://github.com/AI45Lab/X-Boundary.
Authors: Ruida Hu, Chao Peng, Xinchen Wang, Cuiyun Gao
Abstract: Environment configuration is a critical yet time-consuming step in software development, especially when dealing with unfamiliar code repositories. While Large Language Models (LLMs) demonstrate the potential to accomplish software engineering tasks, existing methods for environment configuration often rely on manual efforts or fragile scripts, leading to inefficiencies and unreliable outcomes. We introduce Repo2Run, the first LLM-based agent designed to fully automate environment configuration and generate executable Dockerfiles for arbitrary Python repositories. We address two major challenges: (1) enabling the LLM agent to configure environments within isolated Docker containers, and (2) ensuring the successful configuration process is recorded and accurately transferred to a Dockerfile without error. To achieve this, we propose atomic configuration synthesis, featuring a dual-environment architecture (internal and external environment) with a rollback mechanism to prevent environment "pollution" from failed commands, guaranteeing atomic execution (execute fully or not at all) and a Dockerfile generator to transfer successful configuration steps into runnable Dockerfiles. We evaluate Repo2Run~on our proposed benchmark of 420 recent Python repositories with unit tests, where it achieves an 86.0% success rate, outperforming the best baseline by 63.9%. Repo2Run is available at https://github.com/bytedance/Repo2Run.
Authors: Yi Xu, Laura Ruis, Tim Rockt\"aschel, Robert Kirk
Abstract: Automatic evaluation methods based on large language models (LLMs) are emerging as the standard tool for assessing the instruction-following abilities of LLM-based agents. The most common method in this paradigm, pairwise comparisons with a baseline model, critically depends on the assumption of transitive preferences. However, the validity of this assumption remains largely unexplored. In this study, we investigate the presence of non-transitivity within the AlpacaEval framework and analyze its effects on model rankings. We find that LLM judges exhibit non-transitive preferences, leading to rankings that are sensitive to the choice of the baseline model. To mitigate this issue, we show that round-robin tournaments combined with Bradley-Terry models of preference can produce more reliable rankings. Notably, our method increases both the Spearman correlation and the Kendall correlation with Chatbot Arena (95.0% -> 96.4% and 82.1% -> 86.3% respectively). To address the computational cost of round-robin tournaments, we propose Swiss-Wise Iterative Matchmaking (Swim) tournaments, using a dynamic matching strategy to capture the benefits of round-robin tournaments while maintaining computational efficiency.
Authors: Yijia Xiao, Wanjia Zhao, Junkai Zhang, Yiqiao Jin, Han Zhang, Zhicheng Ren, Renliang Sun, Haixin Wang, Guancheng Wan, Pan Lu, Xiao Luo, Yu Zhang, James Zou, Yizhou Sun, Wei Wang
Abstract: Protein-specific large language models (Protein LLMs) are revolutionizing protein science by enabling more efficient protein structure prediction, function annotation, and design. While existing surveys focus on specific aspects or applications, this work provides the first comprehensive overview of Protein LLMs, covering their architectures, training datasets, evaluation metrics, and diverse applications. Through a systematic analysis of over 100 articles, we propose a structured taxonomy of state-of-the-art Protein LLMs, analyze how they leverage large-scale protein sequence data for improved accuracy, and explore their potential in advancing protein engineering and biomedical research. Additionally, we discuss key challenges and future directions, positioning Protein LLMs as essential tools for scientific discovery in protein science. Resources are maintained at https://github.com/Yijia-Xiao/Protein-LLM-Survey.
Authors: Bingxuan Li, Yiwei Wang, Jiuxiang Gu, Kai-Wei Chang, Nanyun Peng
Abstract: Chart generation aims to generate code to produce charts satisfying the desired visual properties, e.g., texts, layout, color, and type. It has great potential to empower the automatic professional report generation in financial analysis, research presentation, education, and healthcare. In this work, we build a vision-language model (VLM) based multi-agent framework for effective automatic chart generation. Generating high-quality charts requires both strong visual design skills and precise coding capabilities that embed the desired visual properties into code. Such a complex multi-modal reasoning process is difficult for direct prompting of VLMs. To resolve these challenges, we propose METAL, a multi-agent framework that decomposes the task of chart generation into the iterative collaboration among specialized agents. METAL achieves 5.2% improvement over the current best result in the chart generation task. The METAL framework exhibits the phenomenon of test-time scaling: its performance increases monotonically as the logarithmic computational budget grows from 512 to 8192 tokens. In addition, we find that separating different modalities during the critique process of METAL boosts the self-correction capability of VLMs in the multimodal context.
Authors: MohammadHossein Rezaei, Yicheng Fu, Phil Cuvin, Caleb Ziems, Yanzhe Zhang, Hao Zhu, Diyi Yang
Abstract: Human activity is moderated by norms. However, machines are often trained without explicit supervision on norm understanding and reasoning, especially when the norms are grounded in a physical and social context. To improve and evaluate the normative reasoning capability of vision-language models (VLMs), we present EgoNormia $\|\epsilon\|$, consisting of 1,853 ego-centric videos of human interactions, each of which has two related questions evaluating both the prediction and justification of normative actions. The normative actions encompass seven categories: safety, privacy, proxemics, politeness, cooperation, coordination/proactivity, and communication/legibility. To compile this dataset at scale, we propose a novel pipeline leveraging video sampling, automatic answer generation, filtering, and human validation. Our work demonstrates that current state-of-the-art vision-language models lack robust norm understanding, scoring a maximum of 45% on EgoNormia (versus a human bench of 92%). Our analysis of performance in each dimension highlights the significant risks of safety, privacy, and the lack of collaboration and communication capability when applied to real-world agents. We additionally show that through a retrieval-based generation method, it is possible to use EgoNormia to enhance normative reasoning in VLMs.
Authors: Xiwen Liang, Min Lin, Weiqi Ruan, Rongtao Xu, Yuecheng Liu, Jiaqi Chen, Bingqian Lin, Yuzheng Zhuang, Xiaodan Liang
Abstract: Existing methods for vision-language task planning excel in short-horizon tasks but often fall short in complex, long-horizon planning within dynamic environments. These challenges primarily arise from the difficulty of effectively training models to produce high-quality reasoning processes for long-horizon tasks. To address this, we propose Structured Preference Optimization (SPO), which aims to enhance reasoning and action selection in long-horizon task planning through structured preference evaluation and optimized training strategies. Specifically, SPO introduces: 1) Preference-Based Scoring and Optimization, which systematically evaluates reasoning chains based on task relevance, visual grounding, and historical consistency; and 2) Curriculum-Guided Training, where the model progressively adapts from simple to complex tasks, improving its generalization ability in long-horizon scenarios and enhancing reasoning robustness. To advance research in vision-language long-horizon task planning, we introduce ExtendaBench, a comprehensive benchmark covering 1,509 tasks across VirtualHome and Habitat 2.0, categorized into ultra-short, short, medium, and long tasks. Experimental results demonstrate that SPO significantly improves reasoning quality and final decision accuracy, outperforming prior methods on long-horizon tasks and underscoring the effectiveness of preference-driven optimization in vision-language task planning. Specifically, SPO achieves a +5.98% GCR and +4.68% SR improvement in VirtualHome and a +3.30% GCR and +2.11% SR improvement in Habitat over the best-performing baselines.
Authors: Lama Moukheiber, Mira Moukheiber, Dana Moukheiiber, Jae-Woo Ju, Hyung-Chul Lee
Abstract: We introduce a novel question-answering (QA) dataset using echocardiogram reports sourced from the Medical Information Mart for Intensive Care database. This dataset is specifically designed to enhance QA systems in cardiology, consisting of 771,244 QA pairs addressing a wide array of cardiac abnormalities and their severity. We compare large language models (LLMs), including open-source and biomedical-specific models for zero-shot evaluation, and closed-source models for zero-shot and three-shot evaluation. Our results show that fine-tuning LLMs improves performance across various QA metrics, validating the value of our dataset. Clinicians also qualitatively evaluate the best-performing model to assess the LLM responses for correctness. Further, we conduct fine-grained fairness audits to assess the bias-performance trade-off of LLMs across various social determinants of health. Our objective is to propel the field forward by establishing a benchmark for LLM AI agents aimed at supporting clinicians with cardiac differential diagnoses, thereby reducing the documentation burden that contributes to clinician burnout and enabling healthcare professionals to focus more on patient care.
Authors: Yujiao Yang, Jing Lian, Linhui Li
Abstract: We propose Union-of-Experts (UoE), which decomposes transformer into an equitant group of experts, and then implement selective routing on input data and experts. Our approach advances MoE design with four key innovations: (1) We conducted equitant expert decomposition on both MLP blocks and attention blocks based on matrix partition in tensor parallelism. (2) We developed two routing paradigms: patch-wise data selection and expert selection, to apply routing across different levels. (3) We design the architecture of UoE model, including Selective Multi-Head Attention (SMHA) and Union-of-MLP-Experts (UoME). (4) We develop parallel implementation of UoE's routing and computation operation, and optimize efficiency based on the hardware processing analysis. The experiments demonstrate that the UoE model surpass Full Attention, state-of-art MoEs and efficient transformers (including the model architecture of recently proposed DeepSeek-V3) in several tasks across image and natural language domains. In language modeling tasks, we achieve an average reduction of 2.38 in perplexity compared to the best-performed MoE method with an average of 76% FLOPs. In Long Range Arena benchmark, we recorded an average score that is at least 0.68% higher than all comparison models including Full Attention, MoEs, and transformer variants, with only 50% FLOPs of the best MoE method. In image classification, our model yielded an average accuracy improvement of 1.75% than the best model while maintaining comparable FLOPs. The source codes are available at https://github.com/YujiaoYang-work/UoE.
Authors: Pengbo Hu, Xiang Ying
Abstract: Large language models (LLMs) have recently demonstrated remarkable capabilities across domains, tasks, and languages (e.g., ChatGPT and GPT-4), reviving the research of general autonomous agents with human-like cognitive abilities. Such human-level agents require semantic comprehension and instruction-following capabilities, which exactly fall into the strengths of LLMs. Although there have been several initial attempts to build human-level agents based on LLMs, the theoretical foundation remains a challenging open problem. In this paper, we propose a novel theoretical cognitive architecture, the Unified Mind Model (UMM), which offers guidance to facilitate the rapid creation of autonomous agents with human-level cognitive abilities. Specifically, our UMM starts with the global workspace theory and further leverage LLMs to enable the agent with various cognitive abilities, such as multi-modal perception, planning, reasoning, tool use, learning, memory, reflection and motivation. Building upon UMM, we then develop an agent-building engine, MindOS, which allows users to quickly create domain-/task-specific autonomous agents without any programming effort.