{"ok":true,"capturedAt":"2026-06-01T23:58:04.272Z","venues":["ACL 2025","EMNLP 2025","NAACL 2025"],"paper_count":90,"papers":[{"title":"EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association","authors":["Sreyashi Nag","Wenju Xu","Sheikh Muhammad Sarwar","Yang Li","Hansu Gu"],"venue_group":"ACL 2025","abstract_snippet":"Goal-oriented script planning, or the ability to devise coherent sequences of actions toward specific goals, is commonly employed by humans to plan for typical activities. In e-commerce, customers increasingly seek LLM-based assistants t...","url":"https://aclanthology.org/2025.acl-long.1","doi":"10.18653/v1/2025.acl-long.1"},{"title":"GraphNarrator: Generating Textual Explanations for Graph Neural Networks","authors":["Zhen Xiong","Guanchen Wu","Zheng Zhang"],"venue_group":"ACL 2025","abstract_snippet":"Graph representation learning has garnered significant attention due to its broad applications in various domains, such as recommendation systems and social network analysis. Despite advancements in graph learning methods, challenges sti...","url":"https://aclanthology.org/2025.acl-long.2","doi":"10.18653/v1/2025.acl-long.2"},{"title":"M-RewardBench: Evaluating Reward Models in Multilingual Settings","authors":["Srishti Gureja","Shayekh Bin Islam","Rishabh Maheshwary","Drishti Sharma","Gusti Triandi Winata"],"venue_group":"ACL 2025","abstract_snippet":"Reward models (RMs) have driven the state-of-the-art performance of LLMs today by enabling the integration of human feedback into the language modeling process. However, RMs are primarily trained and evaluated in English, and their capab...","url":"https://aclanthology.org/2025.acl-long.3","doi":"10.18653/v1/2025.acl-long.3"},{"title":"ELABORATION: A Comprehensive Benchmark on Human-LLM Competitive Programming","authors":["Zhaofeng Liu","Chen Huang","Tong Zhang","Wenqiang Lei"],"venue_group":"ACL 2025","abstract_snippet":"While recent research increasingly emphasizes the value of human-LLM collaboration in competitive programming and proposes numerous empirical methods, a comprehensive understanding remains elusive due to the fragmented nature of existing...","url":"https://aclanthology.org/2025.acl-long.4","doi":"10.18653/v1/2025.acl-long.4"},{"title":"The Impossibility of Fair LLMs","authors":["Kristian Lum","Avi Feller","Chenhao Tan"],"venue_group":"ACL 2025","abstract_snippet":"The rise of general-purpose artificial intelligence (AI) systems, particularly large language models (LLMs), has raised pressing moral questions about how to reduce bias and ensure fairness at scale. Researchers have documented a sort of...","url":"https://aclanthology.org/2025.acl-long.5","doi":"10.18653/v1/2025.acl-long.5"},{"title":"Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process","authors":["Ermo Hua","Kai Tian","Xingtai Lv","Ning Ding"],"venue_group":"ACL 2025","abstract_snippet":"Supervised Fine-Tuning (SFT) and Preference Optimization (PO) are key processes for aligning Language Models (LMs) with human preferences post pre-training. While SFT excels in efficiency and PO in effectiveness, they are often combined...","url":"https://aclanthology.org/2025.acl-long.6","doi":"10.18653/v1/2025.acl-long.6"},{"title":"Bias in Language Models: Beyond Trick Tests and Towards RUTEd Evaluation","authors":["Kristian Lum","Kevin Robinson","Chirag Nagpal","Alexander Nicholas D’Amour"],"venue_group":"ACL 2025","abstract_snippet":"Standard bias benchmarks used for large language models (LLMs) measure the association between social attributes in model inputs and single-word model outputs. We test whether these benchmarks are robust to lengthening the model outputs...","url":"https://aclanthology.org/2025.acl-long.7","doi":"10.18653/v1/2025.acl-long.7"},{"title":"Sliding Windows Are Not the End: Exploring Full Ranking with Long-Context Large Language Models","authors":[],"venue_group":"ACL 2025","abstract_snippet":"Large Language Models (LLMs) have shown exciting performance in listwise passage ranking. Due to the limited input length, existing methods often adopt the sliding window strategy. Such a strategy, though effective, is inefficient as it...","url":"https://aclanthology.org/2025.acl-long.8","doi":"10.18653/v1/2025.acl-long.8"},{"title":"The Impact of Auxiliary Patient Data on Automated Chest X-Ray Report Generation and How to Incorporate It","authors":["Bevan Koopman"],"venue_group":"ACL 2025","abstract_snippet":"This study investigates the integration of diverse patient data sources into multimodal language models for automated chest X-ray (CXR) report generation. Traditionally, CXR report generation relies solely on data from a patient’s CXR ex...","url":"https://aclanthology.org/2025.acl-long.9","doi":"10.18653/v1/2025.acl-long.9"},{"title":"CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction","authors":["Zishan Xu","Yinghui Li","Linlin Song","Wenhao Jiang","Ruitong Liu"],"venue_group":"ACL 2025","abstract_snippet":"The paper focuses on the interpretability of Grammatical Error Correction (GEC) evaluation metrics, which received little attention in previous studies. To bridge the gap, we introduce **CLEME2.0**, a reference-based metric describing fo...","url":"https://aclanthology.org/2025.acl-long.10","doi":"10.18653/v1/2025.acl-long.10"},{"title":"StrucText-Eval: Evaluating Large Language Model’s Reasoning Ability in Structure-Rich Text","authors":["Zhouhong Gu","Haoning Ye","Xingzhou Chen","Zeyang Zhou","Hongwei Feng"],"venue_group":"ACL 2025","abstract_snippet":"The effective utilization of structured data, integral to corporate data strategies, has been challenged by the rise of large language models (LLMs) capable of processing unstructured information. This shift prompts the question: can LLM...","url":"https://aclanthology.org/2025.acl-long.11","doi":"10.18653/v1/2025.acl-long.11"},{"title":"Literature Meets Data: A Synergistic Approach to Hypothesis Generation","authors":["Haokun Liu","Yangqiaoyu Zhou","Mingxuan Li","Chenhao Tan"],"venue_group":"ACL 2025","abstract_snippet":"AI holds promise for transforming scientific processes, including hypothesis generation. Prior work on hypothesis generation can be broadly categorized into theory-driven and data-driven approaches. While both have proven effective in ge...","url":"https://aclanthology.org/2025.acl-long.12","doi":"10.18653/v1/2025.acl-long.12"},{"title":"GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization","authors":["Zhouhong Gu","Xingzhou Chen","Xiaoran Shi","Tao Wang","Suhang Zheng"],"venue_group":"ACL 2025","abstract_snippet":"Recent advances in large language models have highlighted the critical need for precise control over model outputs through predefined constraints. While existing methods attempt to achieve this through either direct instruction-response...","url":"https://aclanthology.org/2025.acl-long.13","doi":"10.18653/v1/2025.acl-long.13"},{"title":"Tree-of-Evolution: Tree-Structured Instruction Evolution for Code Generation in Large Language Models","authors":["Ziyang Luo","Kaixin Li","Yuchen Tian","Jing Ma"],"venue_group":"ACL 2025","abstract_snippet":"Data synthesis has become a crucial research area in large language models (LLMs), especially for generating high-quality instruction fine-tuning data to enhance downstream performance. In code generation, a key application of LLMs, manu...","url":"https://aclanthology.org/2025.acl-long.14","doi":"10.18653/v1/2025.acl-long.14"},{"title":"Delving into Multilingual Ethical Bias: The MSQAD with Statistical Hypothesis Tests for Large Language Models","authors":["Seunguk Yu","Juhwan Choi","YoungBin Kim"],"venue_group":"ACL 2025","abstract_snippet":"Despite the recent strides in large language models, studies have underscored the existence of social biases within these systems. In this paper, we delve into the validation and comparison of the ethical biases of LLMs concerning global...","url":"https://aclanthology.org/2025.acl-long.15","doi":"10.18653/v1/2025.acl-long.15"},{"title":"ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervision","authors":["Dosung Lee","Wonjun Oh","Boyoung Kim","Minyoung Kim"],"venue_group":"ACL 2025","abstract_snippet":"Multi-hop question answering (MHQA) involves reasoning across multiple documents to answer complex questions. Dense retrievers typically outperform sparse methods like BM25 by leveraging semantic embeddings in many tasks; however, they r...","url":"https://aclanthology.org/2025.acl-long.16","doi":"10.18653/v1/2025.acl-long.16"},{"title":"FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models","authors":["Yang Deng","Wenxuan Zhang","Jing Ma"],"venue_group":"ACL 2025","abstract_snippet":"Large Language Models (LLMs) have significantly advanced the fact-checking studies. However, existing automated fact-checking evaluation methods rely on static datasets and classification metrics, which fail to automatically evaluate the...","url":"https://aclanthology.org/2025.acl-long.17","doi":"10.18653/v1/2025.acl-long.17"},{"title":"Statistical Deficiency for Task Inclusion Estimation","authors":["Loïc Fosse","Gwénolé Lecorvé","Maxime Darrin","Philippe Formont","Pablo Piantanida"],"venue_group":"ACL 2025","abstract_snippet":"Tasks are central in machine learning, as they are the most natural objects to assess the capabilities of current models. The trend is to build general models able to address any task. Even though transfer learning and multitask learning...","url":"https://aclanthology.org/2025.acl-long.18","doi":"10.18653/v1/2025.acl-long.18"},{"title":"Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients","authors":["Jabin Koo","Minwoo Jang"],"venue_group":"ACL 2025","abstract_snippet":"Federated fine-tuning for Large Language Models (LLMs) has recently gained attention due to the heavy communication overhead of transmitting large model updates. Low Rank Adaptation (LoRA) has been proposed as a solution, yet its applica...","url":"https://aclanthology.org/2025.acl-long.19","doi":"10.18653/v1/2025.acl-long.19"},{"title":"LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs","authors":["Jie M. Zhang","Yun Ma","Yihong Dong","Ge Li","Gang Huang"],"venue_group":"ACL 2025","abstract_snippet":"Detecting tricky bugs in plausible programs, those that pass existing test suites yet still contain bugs, remains a significant challenge in software testing. To address this problem, we propose TrickCatcher, an LLM-powered approach to g...","url":"https://aclanthology.org/2025.acl-long.20","doi":"10.18653/v1/2025.acl-long.20"},{"title":"Capture the Key in Reasoning to Enhance CoT Distillation Generalization","authors":["Chengwei Dai","Kun Li","Wei Zhou","Songlin Hu"],"venue_group":"ACL 2025","abstract_snippet":"As Large Language Models (LLMs) scale up and gain powerful Chain-of-Thoughts (CoTs) reasoning abilities, practical resource constraints drive efforts to distill these capabilities into more compact Smaller Language Models (SLMs). We find...","url":"https://aclanthology.org/2025.acl-long.21","doi":"10.18653/v1/2025.acl-long.21"},{"title":"How to Enable Effective Cooperation Between Humans and NLP Models: A Survey of Principles, Formalizations, and Beyond","authors":["Chen Huang","Yang Deng","Wenqiang Lei","Jiancheng Lv"],"venue_group":"ACL 2025","abstract_snippet":"With the advancement of large language models (LLMs), intelligent models have evolved from mere tools to autonomous agents with their own goals and strategies for cooperating with humans. This evolution has birthed a novel paradigm in NL...","url":"https://aclanthology.org/2025.acl-long.22","doi":"10.18653/v1/2025.acl-long.22"},{"title":"Enhancing Hyperbole and Metaphor Detection with Their Bidirectional Dynamic Interaction and Emotion Knowledge","authors":["Li Zheng","Sihang Wang","Zuquan Peng","Fei Li","Jianming Fu"],"venue_group":"ACL 2025","abstract_snippet":"Text-based hyperbole and metaphor detection are of great significance for natural language processing (NLP) tasks. However, due to their semantic obscurity and expressive diversity, it is rather challenging to identify them. Existing met...","url":"https://aclanthology.org/2025.acl-long.23","doi":"10.18653/v1/2025.acl-long.23"},{"title":"UniICL: An Efficient ICL Framework Unifying Compression, Selection, and Generation","authors":["Jun Gao","Zili Wang","Tianxiang Wu"],"venue_group":"ACL 2025","abstract_snippet":"In-context learning (ICL) enhances the reasoning abilities of Large Language Models (LLMs) by prepending a few demonstrations. It motivates researchers to introduce more examples to provide additional contextual information for the gener...","url":"https://aclanthology.org/2025.acl-long.24","doi":"10.18653/v1/2025.acl-long.24"},{"title":"BelarusianGLUE: Towards a Natural Language Understanding Benchmark for Belarusian","authors":["Maksim Aparovich","Volha Harytskaya","Vladislav Poritski","Oksana Volchek"],"venue_group":"ACL 2025","abstract_snippet":"In the epoch of multilingual large language models (LLMs), it is still challenging to evaluate the models’ understanding of lower-resourced languages, which motivates further development of expert-crafted natural language understanding b...","url":"https://aclanthology.org/2025.acl-long.25","doi":"10.18653/v1/2025.acl-long.25"},{"title":"A Survey on Foundation Language Models for Single-cell Biology","authors":["Zhihong Zhu","Ziheng Zhang","Zhenxi Lin","Ziyue Qiao"],"venue_group":"ACL 2025","abstract_snippet":"The recent advancements in language models have significantly catalyzed progress in computational biology. A growing body of research strives to construct unified foundation models for single-cell biology, with language models serving as...","url":"https://aclanthology.org/2025.acl-long.26","doi":"10.18653/v1/2025.acl-long.26"},{"title":"RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios","authors":["Liangming Pan","Sitao Cheng","Xiaobao Wu","En Yu","William Yang Wang"],"venue_group":"ACL 2025","abstract_snippet":"This paper introduces RuleArena, a novel and challenging benchmark designed to evaluate the ability of large language models (LLMs) to follow complex, real-world rules in reasoning. Covering three practical domains – airline baggage fees...","url":"https://aclanthology.org/2025.acl-long.27","doi":"10.18653/v1/2025.acl-long.27"},{"title":"Extending LLM Context Window with Adaptive Grouped Positional Encoding: A Training-Free Method","authors":["Xinhao Xu","Jiaxin Li"],"venue_group":"ACL 2025","abstract_snippet":"Processing long input remains a significant challenge for large language models (LLMs) due to the scarcity of large-scale long-context training data and the high computational cost of training models for extended context windows. In this...","url":"https://aclanthology.org/2025.acl-long.28","doi":"10.18653/v1/2025.acl-long.28"},{"title":"Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Models","authors":["Hyejin Park"],"venue_group":"ACL 2025","abstract_snippet":"Recent advancements in large language models (LLMs) have shown remarkable potential in various complex tasks requiring multi-step reasoning methods like tree search to explore diverse reasoning paths. However, existing methods often suff...","url":"https://aclanthology.org/2025.acl-long.29","doi":"10.18653/v1/2025.acl-long.29"},{"title":"HotelMatch-LLM: Joint Multi-Task Training of Small and Large Language Models for Efficient Multimodal Hotel Retrieval","authors":["Arian Askari","Emmanouil Stergiadis","Moran Beladev"],"venue_group":"ACL 2025","abstract_snippet":"We present HotelMatch-LLM, a multimodal dense retrieval model for the travel domain that enables natural language property search, addressing the limitations of traditional travel search engines which require users to start with a destin...","url":"https://aclanthology.org/2025.acl-long.30","doi":"10.18653/v1/2025.acl-long.30"},{"title":"Towards Automated Error Discovery: A Study in Conversational AI","authors":["Dominic Petrak","Iryna Gurevych"],"venue_group":"EMNLP 2025","abstract_snippet":"Although LLM-based conversational agents demonstrate strong fluency and coherence, they still produce undesirable behaviors (errors) that are challenging to prevent from reaching users during deployment. Recent research leverages large l...","url":"https://aclanthology.org/2025.emnlp-main.1","doi":"10.18653/v1/2025.emnlp-main.1"},{"title":"Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs","authors":["Ajwad Abrar"],"venue_group":"EMNLP 2025","abstract_snippet":"A large number of studies rely on closed-style multiple-choice surveys to evaluate cultural alignment in Large Language Models (LLMs). In this work, we challenge this constrained evaluation paradigm and explore more realistic, unconstrai...","url":"https://aclanthology.org/2025.emnlp-main.2","doi":"10.18653/v1/2025.emnlp-main.2"},{"title":"Biased Tales: Cultural and Topic Bias in Generating Children’s Stories","authors":["Vilém Zouhar"],"venue_group":"EMNLP 2025","abstract_snippet":"Stories play a pivotal role in human communication, shaping beliefs and morals, particularly in children. As parents increasingly rely on large language models (LLMs) to craft bedtime stories, the presence of cultural and gender stereoty...","url":"https://aclanthology.org/2025.emnlp-main.3","doi":"10.18653/v1/2025.emnlp-main.3"},{"title":"Large Language Models as Realistic Microservice Trace Generators","authors":["Donghyun Kim","Sriram Ravula","Taemin Ha","Alex Dimakis","Daehyeok Kim"],"venue_group":"EMNLP 2025","abstract_snippet":"Workload traces are essential to understand complex computer systems’ behavior and manage processing and memory resources. Since real-world traces are hard to obtain, synthetic trace generation is a promising alternative. This paper prop...","url":"https://aclanthology.org/2025.emnlp-main.4","doi":"10.18653/v1/2025.emnlp-main.4"},{"title":"JUDGEBERT: Assessing Legal Meaning Preservation Between Sentences","authors":["Michelle Albert-Rochette","Pierre-Luc Déziel"],"venue_group":"EMNLP 2025","abstract_snippet":"Simplifying text while preserving its meaning is a complex yet essential task, especially in sensitive domain applications like legal texts. When applied to a specialized field, like the legal domain, preservation differs significantly f...","url":"https://aclanthology.org/2025.emnlp-main.5","doi":"10.18653/v1/2025.emnlp-main.5"},{"title":"QFrCoLA: a Quebec-French Corpus of Linguistic Acceptability Judgments","authors":[],"venue_group":"EMNLP 2025","abstract_snippet":"Large and Transformer-based language models perform outstandingly in various downstream tasks. However, there is limited understanding regarding how these models internalize linguistic knowledge, so various linguistic benchmarks have rec...","url":"https://aclanthology.org/2025.emnlp-main.6","doi":"10.18653/v1/2025.emnlp-main.6"},{"title":"Revisiting LLM Value Probing Strategies: Are They Robust and Expressive?","authors":["Siqi Shen","Mehar Singh","Lajanugen Logeswaran","Honglak Lee"],"venue_group":"EMNLP 2025","abstract_snippet":"The value orientation of Large Language Models (LLMs) has been extensively studied, as it can shape user experiences across demographic groups.However, two key challenges remain: (1) the lack of systematic comparison across value probing...","url":"https://aclanthology.org/2025.emnlp-main.7","doi":"10.18653/v1/2025.emnlp-main.7"},{"title":"A Systematic Analysis of Base Model Choice for Reward Modeling","authors":["Kian Ahrabian","Pegah Jandaghi","Negar Mokhberian","Sai Praneeth Karimireddy"],"venue_group":"EMNLP 2025","abstract_snippet":"Reinforcement learning from human feedback (RLHF) and, at its core, reward modeling have become a crucial part of training powerful large language models (LLMs). One commonly overlooked factor in training high-quality reward models (RMs)...","url":"https://aclanthology.org/2025.emnlp-main.8","doi":"10.18653/v1/2025.emnlp-main.8"},{"title":"Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even Performance","authors":[],"venue_group":"EMNLP 2025","abstract_snippet":"When solving NLP tasks with limited labelled data, researchers typically either use a general large language model without further update, or use a small number of labelled samples to tune a specialised smaller model. In this work, we an...","url":"https://aclanthology.org/2025.emnlp-main.9","doi":"10.18653/v1/2025.emnlp-main.9"},{"title":"Is the Top Still Spinning? Evaluating Subjectivity in Narrative Understanding","authors":["Melanie Subbiah","Akankshya Mishra","Grace Kim","Liyan Tang","Greg Durrett"],"venue_group":"EMNLP 2025","abstract_snippet":"Determining faithfulness of a claim to a source document is an important problem across many domains. This task is generally treated as a binary judgment of whether the claim is supported or unsupported in relation to the source. In many...","url":"https://aclanthology.org/2025.emnlp-main.10","doi":"10.18653/v1/2025.emnlp-main.10"},{"title":"MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors","authors":["Nico Daheim","Ido Hakimi","Manu Kapur","Iryna Gurevych","Mrinmaya Sachan"],"venue_group":"EMNLP 2025","abstract_snippet":"Evaluating the pedagogical capabilities of AI-based tutoring models is critical for making guided progress in the field. Yet, we lack a reliable, easy-to-use, and simple-to-run evaluation that reflects the pedagogical abilities of models...","url":"https://aclanthology.org/2025.emnlp-main.11","doi":"10.18653/v1/2025.emnlp-main.11"},{"title":"Preemptive Detection and Correction of Misaligned Actions in LLM Agents","authors":["Haishuo Fang","Iryna Gurevych"],"venue_group":"EMNLP 2025","abstract_snippet":"Deploying LLM-based agents in real-life applications often faces a critical challenge: the misalignment between agents’ behavior and user intent. Such misalignment may lead agents to unintentionally execute some critical actions that car...","url":"https://aclanthology.org/2025.emnlp-main.12","doi":"10.18653/v1/2025.emnlp-main.12"},{"title":"Fingerprinting LLMs through Survey Item Factor Correlation: A Case Study on Humor Style Questionnaire","authors":[],"venue_group":"EMNLP 2025","abstract_snippet":"LLMs increasingly engage with psychological instruments, yet how they represent constructs internally remains poorly understood. We introduce a novel approach to “fingerprinting” LLMs through their factor correlation patterns on standard...","url":"https://aclanthology.org/2025.emnlp-main.13","doi":"10.18653/v1/2025.emnlp-main.13"},{"title":"Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval","authors":["Tianlu Zheng","Yifan Zhang","Kaicheng Yang","Qichuan Ding"],"venue_group":"EMNLP 2025","abstract_snippet":"Although Contrastive Language-Image Pre-training (CLIP) exhibits strong performance across diverse vision tasks, its application to person representation learning faces two critical challenges: (i) the scarcity of large-scale annotated v...","url":"https://aclanthology.org/2025.emnlp-main.14","doi":"10.18653/v1/2025.emnlp-main.14"},{"title":"From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning","authors":["David Dinucu-Jianu","Nico Daheim","Ido Hakimi","Iryna Gurevych","Mrinmaya Sachan"],"venue_group":"EMNLP 2025","abstract_snippet":"Large language models (LLMs) can transform education, but their optimization for direct question-answering often undermines effective pedagogy which requires strategically withholding answers. To mitigate this, we propose an online reinf...","url":"https://aclanthology.org/2025.emnlp-main.15","doi":"10.18653/v1/2025.emnlp-main.15"},{"title":"CompKBQA: Component-wise Task Decomposition for Knowledge Base Question Answering","authors":["Pan Yang","Jun Yang","Huipeng Ma","Chenhao Li","Luan Zhang"],"venue_group":"EMNLP 2025","abstract_snippet":"Knowledge Base Question Answering (KBQA) aims to extract accurate answers from the Knowledge Base (KB). Traditional Semantic Parsing (SP)-based methods are widely used but struggle with complex queries. Recently, large language models (L...","url":"https://aclanthology.org/2025.emnlp-main.16","doi":"10.18653/v1/2025.emnlp-main.16"},{"title":"Permutative Preference Alignment from Listwise Ranking of Human Judgments","authors":["Yang Zhao"],"venue_group":"EMNLP 2025","abstract_snippet":"Aligning Large Language Models (LLMs) with human preferences is crucial in ensuring desirable and controllable model behaviors. Current methods, such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization...","url":"https://aclanthology.org/2025.emnlp-main.17","doi":"10.18653/v1/2025.emnlp-main.17"},{"title":"ToneCraft: Cantonese Lyrics Generation with Harmony of Tones and Pitches","authors":["Junyu Cheng","Chang Pan"],"venue_group":"EMNLP 2025","abstract_snippet":"Lyrics generation has garnered increasing attention within the artificial intelligence community. Our task focuses on generating harmonious Cantonese lyrics. Unlike other languages, Cantonese has a unique system of nine contours and six...","url":"https://aclanthology.org/2025.emnlp-main.18","doi":"10.18653/v1/2025.emnlp-main.18"},{"title":"SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition","authors":["Zechen Li","Shohreh Deldari","Linyao Chen","Hao Xue"],"venue_group":"EMNLP 2025","abstract_snippet":"We introduce SensorLLM, a two-stage framework that enables Large Language Models (LLMs) to perform human activity recognition (HAR) from sensor time-series data. Despite their strong reasoning and generalization capabilities, LLMs remain...","url":"https://aclanthology.org/2025.emnlp-main.19","doi":"10.18653/v1/2025.emnlp-main.19"},{"title":"MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora","authors":["Trung Le","Yuan-Fang Li","Thanh-Toan Do"],"venue_group":"EMNLP 2025","abstract_snippet":"Continually updating model-based indexes in generative retrieval with new documents remains challenging, as full retraining is computationally expensive and impractical under resource constraints. We propose MixLoRA-DSI, a novel framewor...","url":"https://aclanthology.org/2025.emnlp-main.20","doi":"10.18653/v1/2025.emnlp-main.20"},{"title":"ViClaim: A Multilingual Multilabel Dataset for Automatic Claim Detection in Videos","authors":["Mark Cieliebak"],"venue_group":"EMNLP 2025","abstract_snippet":"The growing influence of video content as a medium for communication and misinformation underscores the urgent need for effective tools to analyze claims in multilingual and multi-topic settings. Existing efforts in misinformation detect...","url":"https://aclanthology.org/2025.emnlp-main.21","doi":"10.18653/v1/2025.emnlp-main.21"},{"title":"DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments","authors":["Yuxiang Zheng","Xiangkun Hu","Xiaojie Cai","Lyumanshan Ye","Pengrui Lu"],"venue_group":"EMNLP 2025","abstract_snippet":"Large Language Models (LLMs) with web search capabilities show significant potential for deep research, yet current methods—brittle prompt engineering or RAG-based reinforcement learning in controlled environments—fail to capture real-wo...","url":"https://aclanthology.org/2025.emnlp-main.22","doi":"10.18653/v1/2025.emnlp-main.22"},{"title":"Mixture of Length and Pruning Experts for Knowledge Graphs Reasoning","authors":[],"venue_group":"EMNLP 2025","abstract_snippet":"Knowledge Graph (KG) reasoning, which aims to infer new facts from structured knowledge repositories, plays a vital role in Natural Language Processing (NLP) systems. Its effectiveness critically depends on constructing informative and c...","url":"https://aclanthology.org/2025.emnlp-main.23","doi":"10.18653/v1/2025.emnlp-main.23"},{"title":"MPRF: Interpretable Stance Detection through Multi-Path Reasoning Framework","authors":["Jin Zhang","Hui Xu","Jiafeng Guo"],"venue_group":"EMNLP 2025","abstract_snippet":"Stance detection, a critical task in Natural Language Processing (NLP), aims to identify the attitude expressed in text toward specific targets. Despite advancements in Large Language Models (LLMs), challenges such as limited interpretab...","url":"https://aclanthology.org/2025.emnlp-main.24","doi":"10.18653/v1/2025.emnlp-main.24"},{"title":"Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels","authors":["Yang Nan","Shuo Li","Qi Zhang","Tao Gui","Peng Wang"],"venue_group":"EMNLP 2025","abstract_snippet":"Large language models (LLMs) acquire substantial world knowledge during pre-training, which is further shaped by post-training techniques such as supervised fine-tuning (SFT). However, the impact of SFT on a model’s knowledge remains und...","url":"https://aclanthology.org/2025.emnlp-main.25","doi":"10.18653/v1/2025.emnlp-main.25"},{"title":"JI^2S: Joint Influence‐Aware Instruction Data Selection for Efficient Fine‐Tuning","authors":["Jingyu Wei","Baoyun Peng"],"venue_group":"EMNLP 2025","abstract_snippet":"Instruction tuning (IT) improves large language models (LLMs) by aligning their outputs with human instructions, but its success depends critically on training data quality, and datasets such as Alpaca often contain noisy or suboptimal e...","url":"https://aclanthology.org/2025.emnlp-main.26","doi":"10.18653/v1/2025.emnlp-main.26"},{"title":"SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models","authors":["Chunhui Zhang","Chiyu Ma","Zhongyu Ouyang","Peijun Qing"],"venue_group":"EMNLP 2025","abstract_snippet":"While large language models have demonstrated impressive reasoning abilities, their extension to the audio modality, particularly within large audio-language models (LALMs), remains underexplored. Addressing this gap requires a systemati...","url":"https://aclanthology.org/2025.emnlp-main.27","doi":"10.18653/v1/2025.emnlp-main.27"},{"title":"Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors","authors":["Xiangchen Wang","Teng Wang","Haigang Zhang"],"venue_group":"EMNLP 2025","abstract_snippet":"Recent advancements in large video-language models have revolutionized video understanding tasks. However, their efficiency is significantly constrained by processing high volumes of visual tokens. Existing token compression strategies a...","url":"https://aclanthology.org/2025.emnlp-main.28","doi":"10.18653/v1/2025.emnlp-main.28"},{"title":"RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals","authors":["Xuanliang Zhang","Dingzirui Wang","Keyan Xu","Qingfu Zhu","Wanxiang Che"],"venue_group":"EMNLP 2025","abstract_snippet":"The table reasoning task, crucial for efficient data acquisition, aims to answer questions based on the given table. Recently, reasoning large language models (RLLMs) with Long Chain-of-Thought (Long CoT) significantly enhance reasoning...","url":"https://aclanthology.org/2025.emnlp-main.29","doi":"10.18653/v1/2025.emnlp-main.29"},{"title":"T-MAD: Target-driven Multimodal Alignment for Stance Detection","authors":["Jin Zhang","Hui Xu"],"venue_group":"EMNLP 2025","abstract_snippet":"Multimodal Stance Detection (MSD) aims to determine a user’s stance - support, oppose, or neutral - toward a target by analyzing multimodal content such as texts and images from social media. Existing MSD methods struggle with generalizi...","url":"https://aclanthology.org/2025.emnlp-main.30","doi":"10.18653/v1/2025.emnlp-main.30"}],"notes":["Recent papers from the current ACL, EMNLP, and NAACL proceedings via the ACL Anthology. A bounded per-venue sample (the first papers in program order); follow url for the full paper. Abstracts (CC-BY) are clipped. The venue list is curated and refreshed each cycle."],"source":{"name":"ACL Anthology","url":"https://aclanthology.org","license":"ACL Anthology metadata; abstracts CC-BY. TensorFeed links and summarizes with a clipped abstract; full papers are linked, not republished."}}