GaRAGe: A Benchmark with Grounding Annotations for RAG Evaluation
机构 * Amazon AGI（亚马逊人工智能研究院）
Comments ACL 2025 (Findings)
期刊&会议
ACL
Annual Meeting of the Association for Computational Linguistics · 会议 · Natural Language Processing
LoRMA: Low-Rank Multiplicative Adaptation for LLMs
机构 * Indian Institute of Technology Kanpur (IIT Kanpur)（印度理工学院坎浦尔学院）
Comments Accepted at ACL Findings 2025; 21 pages (9 main paper + 5 pages references + 7 pages appendix)
MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts
机构 * Huazhong University of Science and Technology（华中科技大学） ； Ping An Technology (Shenzhen) Co., Ltd（平安科技（深圳）有限公司）
Comments Accepted by the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)
DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction
机构 * Graduate School of Artificial Intelligence, POSTECH, Republic of Korea（人工智能研究生院，POSTECH，韩国） ； Department of Computer Science and Engineering, POSTECH, Republic of Korea（计算机科学与工程系，POSTECH，韩国） ； Mobile eXperience Business, Samsung Electronics, Republic of Korea（三星电子移动体验业务，韩国） ； aiXplain Inc., Los Gatos, CA, USA（aiXplain公司，美国加利福尼亚州洛斯加托斯）
Comments ACL2025 Findings
Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding
机构 * State Key Laboratory of Multimedia Information Processing, School of Computer Science（多媒体信息处理国家重点实验室、计算机科学学院）
Comments Accepted by ACL 2025 Findings
Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models
机构 * Chung-Ang University（Chung-Ang 大学） ； AITRICS ； DATUMO
Comments ACL 2025 main conference
Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data
机构 * Tencent Inc.（腾讯公司） ； The Chinese University of Hong Kong（香港中文大学） ； Chinese Academy of Sciences（中国科学院）
Comments Accepted by ACL 2025 Findings
Subjectivity in the Annotation of Bridging Anaphora
机构 * Georgetown University（乔治城大学）
Comments LAW-XIX, ACL 2025 Workshop
HotelMatch-LLM: Joint Multi-Task Training of Small and Large Language Models for Efficient Multimodal Hotel Retrieval
机构 * Leiden University（莱顿大学）
Comments Accepted at ACL 2025, Main track. 13 Pages, 1 figure
AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models
Comments Accepted by ACL 2025
Com$^2$: A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models
机构 * Research Center for Social Computing and Interactive Robotics（社会计算与交互机器人研究中心） ； Harbin Institute of Technology（哈尔滨工业大学） ； Institute of Trustworthy Embodied AI（可信具身人工智能研究院） ； Fudan University（复旦大学） ； Beijing Academy of Artificial Intelligence（北京人工智能研究院） ； Nanjing University（南京大学）
Comments Accepted by ACL 2025 Main Conference
Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors
机构 * Dalian University of Technology（大连理工大学） ； RMIT University（皇家墨尔本理工大学） ； The University of Adelaide（阿德莱德大学）
Comments This paper has been accepted to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), Main Conference
Chain of Methodologies: Scaling Test Time Computation without Training
机构 * Sun Yat-sen University（中山大学） ； Temple University
Journal ref ACL 2025
ConECT Dataset: Overcoming Data Scarcity in Context-Aware E-Commerce MT
机构 * Machine Learning Research Allegro.com（Allegro公司机器学习研究部） ； NASK
Comments Accepted at ACL 2025 (The 63rd Annual Meeting of the Association for Computational Linguistics)
On Support Samples of Next Word Prediction
机构 * School of Computer Science and Technology, East China Normal University（东华大学计算机科学与技术学院） ； Utrecht University（乌特勒支大学） ； Midea Group（美的集团）
Comments Accepted to ACL2025(Main Conference)
Structured Pruning for Diverse Best-of-N Reasoning Optimization
机构 * The Chinese University of Hong Kong（香港中文大学）
Comments Accepted to ACL Findings 2025
Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race
机构 * University of Chicago（芝加哥大学） ； Rutgers University（罗格斯大学） ； Allen Institute for AI（人工智能研究所） ； University of Washington（华盛顿大学）
Comments Accepted to ACL 2025 (Main)
Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States
机构 * The Hong Kong Polytechnic University（香港理工大学） ； Shanghai Jiao Tong University（上海交通大学）
Comments Accepted by ACL 2025 Main Conference
Will AI shape the way we speak? The emerging sociolinguistic influence of synthetic voices
机构 * Department of Speech, Music and Hearing, KTH Royal Institute of Technology（语音、音乐与听觉系，皇家理工学院） ； Department of English, Aarhus University（英语系，奥胡斯大学）
Comments 5 pages, 0 figures, International Workshop on Spoken Dialogue Systems Technology (IWSDS) 2025
Journal ref Proceedings of the 2025 International Workshop on Spoken Dialogue Systems (IWSDS), pages 357-368, Bilbao, Spain, May 27-30 2025. ACL Anthology, https://aclanthology.org/2025.iwsds-1.37
sudo rm -rf agentic_security
机构 * Aim Intelligence ； Yonsei University（延世大学） ； Seoul National University（首尔国立大学）
Comments Accepted ACL 2025 Industry track
Imagine to Hear: Auditory Knowledge Generation can be an Effective Assistant for Language Models
机构 * HJ AILAB ； POSTECH
Comments 12 pages, 5 figures, ACL Findings 2025
Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering
机构 * Sapienza University of Rome（罗马萨皮恩扎大学） ； Babelscape
Comments Findings of the Association for Computational Linguistics ACL 2025
State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models
机构 * Seoul National University（首尔国立大学） ； FuriosaAI ； UW-Madison（威斯康星大学麦迪逊分校） ； Ajou University（全州大学）
Comments Accepted at ACL 2025 Main
Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative Analysis
机构 * Department of Computer Science, University of Illinois at Urbana-Champaign（计算机科学系，伊利诺伊大学厄巴纳-香槟分校）
Comments ACL 2025 Main Conference. Code available at: https://github.com/pkargupta/tree-of-debate
CORDIAL: Can Multimodal Large Language Models Effectively Understand Coherence Relationships?
机构 * The Pennsylvania State University（宾夕法尼亚州立大学） ； National Institute of Technology, Tiruchirappalli（特里奇里帕利学院）
Comments To appear at the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), Vienna, Austria, July 2025, https://2025.aclweb.org/
Gumbel Reranking: Differentiable End-to-End Reranker Optimization
机构 * LUMIA Lab, Shanghai Jiao Tong University（上海交通大学LUMIA实验室） ； Tiansuan Lab, Ant Group Co., Ltd.（蚂蚁集团天算实验室） ； SJTU Paris Elite Institute of Technology（上海交通大学巴黎精英理工学院）
Comments ACL 2025 Main
Scalable Vision Language Model Training via High Quality Data Curation
机构 * ByteDance Douyin Content Group（字节跳动抖音内容团队）
Comments ACL 2025 Main Conference
Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning
机构 * School of Computer Science and Technology, Chongqing University of Posts and Telecommunications（重庆邮电大学计算机科学与技术学院） ； Baidu AI Platform & Ecosystem（百度AI平台与生态系统）
Comments ACL 2025 Main
Unveiling and Addressing Pseudo Forgetting in Large Language Models
机构 * School of Computer Science and Technology, Beijing Institute of Technology（计算机科学与技术学院，北京理工大学）
Comments ACL 2025 Findings
Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks
机构 * University of Oxford（牛津大学） ； Microsoft Research（微软研究院） ； The Alan Turing Institute（艾伦·图灵研究所） ； Allen Institute for AI（人工智能研究所） ； University of Washington（华盛顿大学） ； Microsoft Corporation（微软公司） ； University of York（约克大学）
Comments ACL 2025 main
