论文检索

Yeliang Xiu, Yongmei Liu

Non-monotonic reasoning (NMR) refers to the fact that conclusions may be invalidated by new information. It is widely used in daily life and legal reasoning. An NMR task usually has multiple extensions, which are sets of plausible conclusions. There are two reasoning modes – skeptical and credulous reasoning, depending on whether to believe facts in all extensions or any one extension. Despite some preliminary work exploring the NMR abilities of LLMs, the multi-extension NMR capabilities of LLMs remain underexplored. In this paper, we synthesize a multi-extension NMR dataset MultiLogicNMR, and construct two variants of the dataset with more extensions or text diversity. We propose a neural-symbolic framework MultiLogicNMRer for multi-extension NMR. Experimental evaluation with the datasets shows that LLMs still face significant challenges in NMR abilities, and reveal the effectiveness of our neural-symbolic framework, with an average accuracy gain of about 15% compared to prompt-based methods, and even outperforming some fine-tuning methods. All code and data are publicly available.

Mingxuan Xia, Zhijie Jiang, Haobo Wang, Junbo Zhao, Tianlei Hu, Gang Chen

Hierarchical text classification aims to classify documents into multiple labels within a hierarchical taxonomy, making it an essential yet challenging task in natural language processing. Recently, using Large Language Models (LLM) to tackle hierarchical text classification in a zero-shot manner has attracted increasing attention due to their cost-efficiency and flexibility. Given the challenges of understanding the hierarchy, various HTC prompting strategies have been explored to elicit the best performance from LLMs.However, our empirical study reveals that LLMs are highly sensitive to these prompting strategies—(i) within a task, different strategies yield substantially different results, and (ii) across various tasks, the relative effectiveness of a given strategy varies significantly. To address this, we propose a novel ensemble method, HiEPS, which integrates the results of diverse prompting strategies to promote LLMs’ reliability. We also introduce a path-valid voting mechanism for ensembling, which selects a valid result with the highest path frequency score. Extensive experiments on three benchmark datasets show that HiEPS boosts the performance of single prompting strategies and achieves SOTA results. The source code is available at https://github.com/MingxuanXia/HiEPS.

Yunkai Dang, Mengxi Gao, Yibo Yan, Xin Zou, Yanggan Gu, Jungang Li, Jingyu Wang, Peijie Jiang, Aiwei Liu, Jia Liu 等

Multimodal large language models (MLLMs) have recently achieved state-of-the-art performance on tasks ranging from visual question answering to video understanding. However, existing studies have concentrated mainly on visual–textual misalignment, leaving largely unexplored the MLLMs’ ability to preserve an originally correct answer when confronted with misleading information. We reveal a response uncertainty phenomenon: across nine standard datasets, twelve state-of-the-art open-source MLLMs overturn a previously correct answer in 65% of cases after receiving a single deceptive cue. To systematically quantify this vulnerability, we propose a two-stage evaluation pipeline: (1) elicit each model’s original response on unperturbed inputs; (2) inject explicit (false-answer hints) and implicit (contextual contradictions) misleading instructions, and compute the misleading rate—the fraction of correct-to-incorrect flips. Leveraging the most susceptible examples, we curate the Multimodal Uncertainty Benchmark (MUB), a collection of image–question pairs stratified into low, medium, and high difficulty based on how many of twelve state-of-the-art MLLMs they mislead. Extensive evaluation on twelve open-source and five closed-source models reveals a high uncertainty: average misleading rates exceed 86%, with explicit cues over 67.19% and implicit cues over 80.67%. To reduce the misleading rate, we then fine-tune all open-source MLLMs on a compact 2,000-sample mixed-instruction dataset, reducing misleading rates to 6.97% (explicit) and 32.77% (implicit), boosting consistency by nearly 29.37% on highly deceptive inputs, and slightly improving accuracy on standard benchmarks.

Hua Cai, Shuang Zhao, Liang Zhang, Xuli Shen, Qing Xu, Weilin Shen, Zihao Wen, Tianke Ban

Reasoning-focused large language models (LLMs) are rapidly evolving across various domains, yet their capabilities in handling complex legal problems remains underexplored. In this paper, we introduce Unilaw-R1, a large language model tailored for legal reasoning. With a lightweight 7-billion parameter scale, Unilaw-R1 significantly reduces deployment cost while effectively tackling three core challenges in the legal domain: insufficient legal knowledge, unreliable reasoning logic, and weak business generalization. To address these issues, we first construct Unilaw-R1-Data, a high-quality dataset containing ~17K distilled and screened chain-of-thought (CoT) samples. Based on this, we adopt a two-stage training strategy combining Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), which significantly boosts the model’s performance on complex legal reasoning tasks and supports interpretable decision-making in legal AI applications. To assess legal reasoning ability, we also introduce Unilaw-R1-Eval, a dedicated benchmark designed to evaluate models across single- and multi-choice legal tasks. Unilaw-R1 demonstrates strong results on authoritative benchmarks, outperforming all models of similar scale and achieving performance on par with the much larger DeepSeek-R1-Distill-Qwen-32B (54.9%). Following domain-specific training, it also showed significant gains on LawBench and LexEval, exceeding Qwen-2.5-7B-Instruct (46.6%) by an average margin of 6.6%. Code is available at: https://github.com/Hanscal/Unilaw-R1.

Jingyuan Huang, Jen-tse Huang, Ziyi Liu, Xiaoyuan Liu, Wenxuan Wang, Jieyu Zhao

Visual-Language Models (VLMs) have shown remarkable performance across various tasks, particularly in recognizing geographic information from images. However, VLMs still show regional biases in this task. To systematically evaluate these issues, we introduce a benchmark consisting of 1,200 images paired with detailed geographic metadata. Evaluating four VLMs, we find that while these models demonstrate the ability to recognize geographic information from images, achieving up to 53.8% accuracy in city prediction, they exhibit significant biases. Specifically, performance is substantially higher for economically developed and densely populated regions compared to less developed (-12.5%) and sparsely populated (-17.0%) areas. Moreover, regional biases of frequently over-predicting certain locations remain. For instance, they consistently predict Sydney for images taken in Australia, shown by the low entropy scores for these countries. The strong performance of VLMs also raises privacy concerns, particularly for users who share images online without the intent of being identified. Our code and dataset are publicly available at https://github.com/uscnlp-lime/FairLocator.

Auguste Poiroux, Gail Weiss, Viktor Kunčak, Antoine Bosselut

Evaluating statement autoformalization, translating natural language mathematics into formal languages like Lean 4, remains a significant challenge, with few metrics, datasets, and standards to robustly measure progress. In this work, we present a comprehensive approach combining improved metrics, robust benchmarks, and systematic evaluation, to fill this gap. First, we introduce BEq+, an automated metric that correlates strongly with human judgment, along with ProofNetVerif, a new dataset for assessing the quality of evaluation metrics, containing 3,752 annotated examples. Second, we develop two new autoformalization benchmarks: ProofNet#, a corrected version of ProofNet, and RLM25, with 619 new pairs of research-level mathematics from six formalization projects. Through systematic experimentation across these benchmarks, we find that current techniques can achieve up to 45.1% accuracy on undergraduate mathematics but struggle with research-level content without proper context. Our work establishes a reliable foundation for evaluating and advancing autoformalization systems.

Simone Papicchio, Luca Cagliero, Paolo Papotti

Large Language Models (LLMs) have demonstrated robust performance in Semantic Parsing (SP) for well-defined queries with unambiguous intent and answerable responses. However, practical user questions frequently deviate from these ideal conditions, challenging the applicability of existing benchmarks. To address this issue, we introduce SQUAB, an automatic dataset generator of Ambiguous and Unanswerable questions. SQUAB generates complex, annotated SP tests using a blend of SQL and LLM capabilities. Results show that SQUAB reduces test generation costs by up to 99% compared to human-based solutions while aligning with real-world question patterns. Furthermore, these tests challenge LLM performance while revealing disparities between public and proprietary datasets. This highlights the need for a dynamic, automatic dataset generator as SQUAB. The code is designed for user extension to accommodate new ambiguous and unanswerable patterns and is available at https://anonymous.4open.science/r/squab-8716/.

Md Ayon Mia, Akm Moshiur Rahman Mazumder, Khadiza Sultana Sayma, Md Fahim, Md Tahmid Hasan Fuad, Muhammad Ibrahim Khan, Akmmahbubur Rahman

Detecting misogyny in multimodal content remains a notable challenge, particularly in culturally conservative and low-resource contexts like Bangladesh. While existing research has explored hate speech and general meme classification, the nuanced identification of misogyny in Bangla memes, rich in metaphor, humor, and visual-textual interplay, remains severely underexplored. To address this gap, we introduce BanMiMe, the first comprehensive Bangla misogynistic meme dataset comprising 2,000 culturally grounded samples where each meme includes misogyny labels, humor categories, metaphor localization, and detailed human-written explanations. We benchmark the various performance of open and closed-source vision-language models (VLMs) under zero-shot and prompt-based settings and evaluate their capacity for both classification and explanation generation. Furthermore, we systematically explore multiple fine-tuning strategies, including standard, data-augmented, and Chain-of-Thought (CoT) supervision. Our results demonstrate that CoT-based fine-tuning consistently enhances model performance, both in terms of accuracy and in generating meaningful explanations. We envision BanMiMe as a foundational resource for advancing explainable multimodal moderation systems in low-resource and culturally sensitive settings.

Haobo Li, Zhaowei Wang, Jiachen Wang, Yueya Wang, Alexis Kai Hon Lau, Huamin Qu

Forecasting weather and climate events is crucial for making appropriate measures to mitigate environmental hazards and minimize losses. However, existing environmental forecasting research focuses narrowly on predicting numerical meteorological variables (e.g., temperature), neglecting the translation of these variables into actionable textual narratives of events and their consequences. To bridge this gap, we proposed Weather and Climate Event Forecasting (WCEF), a new task that leverages numerical meteorological raster data and textual event data to predict weather and climate events. This task is challenging to accomplish due to difficulties in aligning multimodal data and the lack of supervised datasets. To address these challenges, we present CLLMate, the first multimodal dataset for WCEF, using 26,156 environmental news articles aligned with ERA5 reanalysis data. We systematically benchmark 32 existing models on CLLMate, including closed-source, open-source, and our fine-tuned models. Our experiments reveal the advantages and limitations of existing MLLMs and the value of CLLMate for the training and benchmarking of the WCEF task. The dataset is available at https://github.com/hobolee/CLLMate.

Alham Fikri Aji, Trevor Cohn

As one of the world’s most populous countries, with 700 languages spoken, Indonesia is behind in terms of NLP progress. We introduce LORAXBENCH, a benchmark that focuses on low-resource languages of Indonesia and covers 6 diverse tasks: reading comprehension, open-domain QA, language inference, causal reasoning, translation, and cultural QA. Our dataset cover 20 languages, with the addition of two formality registers for three languages. We evaluate a diverse set of multilingual and region-focused LLMs and found that this benchmark is challenging. We note a visible discrepancy between performance in Indonesian and other languages, especially the low-resource ones. There is no clear lead when using a region-specific model as opposed to the general multilingual model. Lastly, we show that a change in register affects model performance, especially with registers not commonly found in social media, such as high-level politeness ‘Krama’ Javanese.

Zhiyu Yang, Shuo Wang, Yukun Yan, Yang Deng

LLMs are transforming software development, yet current code generation and code repair benchmarks mainly assess syntactic and functional correctness in simple, single-error cases. LLMs’ capabilities to autonomously find and fix runtime logical errors in complex data science code remain largely unexplored. To address this gap, we introduce DSDBench: the Data Science Debugging Benchmark, the first benchmark for systematic evaluation of LLMs on multi-hop error tracing and multi-bug detection in data science code debugging. DSDBench adapts datasets from existing data science task benchmarks, such as DABench and MatPlotBench, featuring realistic data science debugging tasks with automatically synthesized multi-hop, multi-bug code snippets. DSDBench includes 1,117 annotated samples with 741 cause-effect error pairs and runtime error messages. Evaluations of state-of-the-art LLMs on DSDBench show significant performance gaps, highlighting challenges in debugging logical runtime errors in data science code. DSDBench offers a crucial resource to evaluate and improve LLMs’ debugging and reasoning capabilities, enabling more reliable AI-assisted data science in the future.

Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala, Hitomi Yanaka

Large language models (LLMs) exhibit social biases, prompting the development of various debiasing methods. However, debiasing methods may degrade the capabilities of LLMs. Previous research has evaluated the impact of bias mitigation primarily through tasks measuring general language understanding, which are often unrelated to social biases. In contrast, cultural commonsense is closely related to social biases, as both are rooted in social norms and values. The impact of bias mitigation on cultural commonsense in LLMs has not been well investigated. Considering this gap, we propose SOBACO (SOcial BiAs and Cultural cOmmonsense benchmark), a Japanese benchmark designed to evaluate social biases and cultural commonsense in LLMs in a unified format. We evaluate several LLMs on SOBACO to examine how debiasing methods affect cultural commonsense in LLMs. Our results reveal that the debiasing methods degrade the performance of the LLMs on the cultural commonsense task (up to 75% accuracy deterioration). These results highlight the importance of developing debiasing methods that consider the trade-off with cultural commonsense to improve fairness and utility of LLMs.

Yu Zhang, Zhaoman Zhong, Huihui Lv

Conversational aspect-based sentiment quadruple analysis (DiaASQ) is a newly-emergent task aiming to extract quadruples of target-aspect-opinion-sentiment from a conversation text. Existing studies struggle to capture complete dialogue semantics, largely due to inadequate inter-utterance modeling and the underutilization of dialogue structure. To address these issues, we propose an Inter-sentence Context Modeling and Structure-aware Representation Enhancement model (ICMSR) to extract dialogue aspect sentiment quadruple. We design the Dialog Inter-sentence Contextual Enhancer (DICE) module after the sentence-by-sentence encoding phase to enhance inter-sentence interactions and mitigate contextual fragmentation caused by traditional sequential encoding. Moreover, to fully exploit structural information within dialogues, we propose the Dialog Feature Amplifier (DFA), which consists of two submodules: STREAM and SMM. The STREAM module integrates diverse structural dialogue information to generate structure-aware sentence representations, effectively improving the modeling of intra-dialogue structural relations. Furthermore, the Structural Multi-scale Mechanism (SMM) employs a multi-scale modeling approach, simulating varying extents of contextual awareness, thereby enhancing the model’s ability to capture cross-sentence structural dependencies. We extensively evaluate our method on benchmark datasets, and the empirical results consistently confirm its effectiveness.

Meng-Chen Wu, Si-Chi Chin, Tess Wood, Ayush Goyal, Narayanan Sadagopan

Large Language Models (LLMs) increasingly serve diverse global audiences, making it critical for responsible AI deployment across cultures. While recent works have proposed various approaches to enhance cultural alignment in LLMs, a systematic analysis of their evaluation benchmarks remains needed. We propose a novel framework that conceptualizes alignment along three dimensions: Cultural Group (who to align with), Cultural Elements (what to align), and Awareness Scope (how to align: majority-focused vs. diversity-aware). Through this framework, we analyze 105 cultural alignment evaluation benchmarks, revealing significant imbalances: Region (37.9%) and Language (28.9%) dominate Cultural Group representation; Social and Political Relations (25.1%) and Speech and Language (20.9%) concentrate Cultural Elements coverage; and an overwhelming majority (97.1%) of datasets adopt majority-focused Awareness Scope approaches. In a case study examining AI safety evaluation across nine Asian countries (Section 5), we demonstrate how our framework reveals critical gaps between existing benchmarks and real-world cultural biases identified in the study, providing actionable guidance for developing more comprehensive evaluation resources tailored to specific deployment contexts.

Terrance Liu, Shuyi Wang, Daniel Preotiuc-Pietro, Yash Chandarana, Chirag Gupta

While large language models (LLMs) achieve strong performance on text-to-SQL parsing, they sometimes exhibit unexpected failures in which they are confidently incorrect. Building trustworthy text-to-SQL systems thus requires eliciting reliable uncertainty measures from the LLM. In this paper, we study the problem of providing a calibrated confidence score that conveys the likelihood of an output query being correct. Our work is the first to establish a benchmark for post-hoc calibration of LLM-based text-to-SQL parsing. In particular, we show that Platt scaling, a canonical method for calibration, provides substantial improvements over directly using raw model output probabilities as confidence scores. Furthermore, we propose a method for text-to-SQL calibration that leverages the structured nature of SQL queries to provide more granular signals of correctness, named “sub-clause frequency” (SCF) scores. Using multivariate Platt scaling (MPS), our extension of the canonical Platt scaling technique, we combine individual SCF scores into an overall accurate and calibrated score. Empirical evaluation on two popular text-to-SQL datasets shows that our approach of combining MPS and SCF yields further improvements in calibration and the related task of error detection over traditional Platt scaling.

Gagan Mundada, Yash Vishe, Amit Namburi, Xin Xu, Zachary Novack, Julian McAuley, Junda Wu

Recent advances in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, their reasoning abilities in the multimodal symbolic music domain remain largely unexplored.We introduce WildScore, the first in-the-wild multimodal symbolic music reasoning and analysis benchmark, designed to evaluate MLLMs’ capacity to interpret real-world music scores and answer complex musicological queries. Each instance in WildScore is sourced from genuine musical compositions and accompanied by authentic user-generated questions and discussions, capturing the intricacies of practical music analysis. To facilitate a comprehensive evaluation, we propose a systematic taxonomy,comprising both high-level and fine-grained musicological ontologies. Furthermore, we frame complex music reasoning as multiple-choice question answering,enabling controlled and scalable assessment of MLLMs’ symbolic music understanding. Empirical benchmarking of state-of-the-art MLLMs on WildScore reveals intriguing patterns in their visual-symbolic reasoning, uncovering both promising directions and persistent challenges for MLLMs in symbolic music reasoning and analysis.We release the dataset and code.

Abubakr Mohamed, Hamdy Mubarak

Arabic diacritics, similar to short vowels in English, provide phonetic and grammatical information but are typically omitted in written Arabic, leading to ambiguity. Diacritization (aka diacritic restoration or vowelization) is essential for natural language processing. This paper advances Arabic diacritization through the following contributions: first, we propose a methodology to analyze and refine a large diacritized corpus to improve training quality. Second, we introduce WikiNews-2024, a multi-reference evaluation methodology with an updated version of the standard benchmark “WikiNews-2014”. In addition, we explore various model architectures and propose a BiLSTM-based model that achieves state-of-the-art results with 3.12% and 2.70% WER on WikiNews-2014 and WikiNews-2024, respectively. Moreover, we develop a model that preserves user-specified diacritics while maintaining accuracy. Lastly, we demonstrate that augmenting training data enhances performance in low-resource settings.

Mossad Helali, Yutai Luo, Tae Jun Ham, Jim Plotts, Ashwin Chaugule, Jichuan Chang, Parthasarathy Ranganathan, Essam Mansour

Automating Exploratory Data Analysis (EDA) is critical for accelerating the workflow of data scientists. While Large Language Models (LLMs) offer a promising solution, current LLM-only approaches often exhibit limited accuracy and code reliability on less-studied or private datasets. Moreover, their effectiveness significantly diminishes with open-source LLMs compared to proprietary ones, limiting their usability in enterprises that prefer local models for privacy and cost. To address these limitations, we introduce RAGvis: a novel two-stage graph-guided Retrieval-Augmented Generation (RAG) framework. RAGvis first builds a base knowledge graph (KG) of EDA notebooks and enriches it with structured EDA operation semantics. These semantics are extracted by an LLM guided by our empirically-developed EDA operations taxonomy. Second, in the online generation stage for new datasets, RAGvis retrieves relevant operations from the KG, aligns them to the dataset’s structure, refines them with LLM reasoning, and then employs a self-correcting agent to generate executable Python code. Experiments on two benchmarks demonstrate that RAGvis significantly improves code executability (pass rate), semantic accuracy, and visual quality in generated operations. This enhanced performance is achieved with substantially lower token usage compared to LLM-only baselines. Notably, our approach enables smaller, open-source LLMs to match the performance of proprietary models, presenting a reliable and cost-effective pathway for automated EDA code generation.

Hanjun Luo, Yingbin Jin, Yiran Wang, Xinfeng Li, Tong Shang, Xuecheng Liu, Ruizhe Chen, Kun Wang, Hanan Salam, Qingsong Wen 等

The advancements of Large Language Models (LLMs) have spurred a growing interest in their application to Named Entity Recognition (NER) methods. However, existing datasets are primarily designed for traditional machine learning methods and are inadequate for LLM-based methods, in terms of corpus selection and overall dataset design logic. Moreover, the prevalent fixed and relatively coarse-grained entity categorization in existing datasets fails to adequately assess the superior generalization and contextual understanding capabilities of LLM-based methods, thereby hindering a comprehensive demonstration of their broad application prospects. To address these limitations, we propose DynamicNER, the first NER dataset designed for LLM-based methods with dynamic categorization, introducing various entity types and entity type lists for the same entity in different context, leveraging the generalization of LLM-based NER better. The dataset is also multilingual and multi-granular, covering 8 languages and 155 entity types, with corpora spanning a diverse range of domains. Furthermore, we introduce CascadeNER, a novel NER method based on a two-stage strategy and lightweight LLMs, achieving higher accuracy on fine-grained tasks while requiring fewer computational resources. Experiments show that DynamicNER serves as a robust and effective benchmark for LLM-based NER methods. Furthermore, we also conduct analysis for traditional methods and LLM-based methods on our dataset. Our code and dataset are openly available at https://github.com/Astarojth/DynamicNER.

Abdullah Hashmat, Muhammad Arham Mirza, Agha Ali Raza

With the widespread adoption of Large Language Models (LLMs) across various applications, it is imperative to ensure their fairness across all user communities. However, most LLMs are trained and evaluated on Western centric data, with little attention paid to low-resource languages and regional contexts. To address this gap, we introduce PakBBQ, a culturally and regionally adapted extension of the original Bias Benchmark for Question Answering (BBQ) dataset. PakBBQ comprises over 214 templates, 17180 QA pairs across 8 categories in both English and Urdu, covering eight bias dimensions including age, disability, appearance, gender, socio-economic status, religious, regional affiliation, and language formality that are relevant in Pakistan. We evaluate multiple multilingual LLMs under both ambiguous and explicitly disambiguated contexts, as well as negative versus non negative question framings. Our experiments reveal (i) an average accuracy gain of 12% with disambiguation, (ii) consistently stronger counter bias behaviors in Urdu than in English, and (iii) marked framing effects that reduce stereotypical responses when questions are posed negatively. These findings highlight the importance of contextualized benchmarks and simple prompt engineering strategies for bias mitigation in low resource settings.