ACL

DeFine: Decision-Making with Analogical Reasoning over Factor Profiles

Yebowen Hu, Xiaoyang Wang, Wenlin Yao, Yiming Lu, Daoan Zhang, Hassan Foroosh, Dong Yu, Fei Liu

机构 * University of Central Florida（中央佛罗里达大学） ； Tencent AI Lab, Seattle（腾讯AI实验室（西雅图）） ； University of Rochester（罗切斯特大学） ； Emory University（埃默里大学） 纠错

Comments Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), Vienna, Austria

BOOKCOREF: Coreference Resolution at Book Scale

Giuliano Martinelli, Tommaso Bonomo, Pere-Lluís Huguet Cabot, Roberto Navigli

机构 * Sapienza NLP Group, Sapienza University of Rome（Sapienza 大学自然语言处理小组，Sapienza 罗马大学） 纠错

Comments Accepted to ACL 2025 Main Conference. 19 pages

IAM: Efficient Inference through Attention Mapping between Different-scale LLMs

Yi Zhao, Zuchao Li, Hai Zhao

机构 * School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院） ； Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University（上海交通大学智能交互与认知工程重点实验室） ； Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3（上海Web3可信数据流通与治理关键实验室） ； School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院） 纠错

Comments ACL 2025

DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt Compression

Yi Zhao, Zuchao Li, Hai Zhao, Baoyuan Qi, Guoming Liu

机构 * School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院） ； Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University（上海教育委员会智能交互与认知工程重点实验室） ； Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3（上海Web3可信数据流通与治理重点实验室） ； School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院） ； Xiaomi, Beijing, China（小米（北京）） 纠错

Comments ACL 2025

Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language Models

Bo Zeng, Chenyang Lyu, Sinuo Liu, Mingyan Zeng, Minghao Wu, Xuanfan Ni, Tianqi Shi, Yu Zhao, Yefeng Liu, Chenyu Zhu, Ruizhe Li, Jiahui Geng, Qing Li, Yu Tong, Longyue Wang, Weihua Luo, Kaifu Zhang

机构 * Alibaba International Digital Commerce（阿里巴巴国际数字商务） ； University of Aberdeen（阿伯丁大学） ； MBZUAI 纠错

Comments ACL 2025 Main Conference paper

Towards Geo-Culturally Grounded LLM Generations

Piyawat Lertvittayakumjorn, David Kinney, Vinodkumar Prabhakaran, Donald Martin, Sunipa Dev

机构 * Google（谷歌） ； Washington University in St. Louis（华盛顿大学圣路易斯分校） 纠错

Comments ACL 2025 (main conference)

Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp Context

Maggie Mi, Aline Villavicencio, Nafise Sadat Moosavi

机构 * University of Sheffield（谢菲尔德大学） ； University of Exeter（埃克塞特大学） ； Alan Turing Institute（艾伦·图灵研究所） 纠错

Comments ACL 2025

Internal Value Alignment in Large Language Models through Controlled Value Vector Activation

Haoran Jin, Meng Li, Xiting Wang, Zhihao Xu, Minlie Huang, Yantao Jia, Defu Lian

机构 * University of Science and Technology of China（中国科学技术大学） ； State Key Laboratory of Cognitive Intelligence（认知智能国家重点实验室） ； Gaoling School of Artificial Intelligence（光明人工智能学院） ； Renmin University of China（中国人民大学） ； Beijing Key Laboratory of Research on Large Models and Intelligent Governance（北京大型模型与智能治理重点实验室） ； Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE（下一代智能搜索与推荐工程技术研究中心） ； Tsinghua University（清华大学） ； Huawei Technologies Co. Ltd（华为技术有限公司） 纠错

Comments 25 pages, 14 figures. Accepted by ACL 2025 (main conference)

KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding

Luohe Shi, Zuchao Li, Lefei Zhang, Guoming Liu, Baoyuan Qi, Hai Zhao

机构 * School of Computer Science, Wuhan University（武汉大学计算机学院） ； School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院） ； Xiaomi（小米） ； School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机学院） 纠错

Comments To be published in The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

On the Effect of Instruction Tuning Loss on Generalization

Anwoy Chatterjee, H S V N S Kowndinya Renduchintala, Sumit Bhatia, Tanmoy Chakraborty

机构 * Dept. of Electrical Engineering（电气工程系） ； Indian Institute of Technology Delhi（印度理工学院德里） ； Media and Data Science Research（媒体与数据科学研究） ； Adobe Inc., India（Adobe公司，印度） 纠错

Comments To appear in Transactions of the Association for Computational Linguistics (TACL)

Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification

Yejun Yoon, Jaeyoon Jung, Seunghyun Yoon, Kunwoo Park

机构 * Department of Intelligent Semiconductors, Soongsil University（智能半导体系，顺慈大学） ； School of AI Convergence, Soongsil University（人工智能融合学院，顺慈大学） ； MAUM AI Inc.（MAUM人工智能公司） ； Adobe Research, USA（Adobe研究，美国） 纠错

Comments ACL 2025 Workshop (FEVER)

Enhancing Safe and Controllable Protein Generation via Knowledge Preference Optimization

Yuhao Wang, Keyan Ding, Kehua Feng, Zeyuan Wang, Ming Qin, Xiaotong Li, Qiang Zhang, Huajun Chen

机构 * Zhejiang University（浙江大学） ； ZJU-Hangzhou Global Scientific and Technological Innovation Center（浙大杭州国际科创中心） 纠错

Comments Accepted at ACL 2025 (Main Conference)

Can Multimodal Foundation Models Understand Schematic Diagrams? An Empirical Study on Information-Seeking QA over Scientific Papers

Yilun Zhao, Chengye Wang, Chuhan Li, Arman Cohan

Comments ACL 2025 Findings

Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning

Andrei Mircea, Supriyo Chakraborty, Nima Chitsazan, Milind Naphade, Sambit Sahu, Irina Rish, Ekaterina Lobacheva

机构 * Mila – Quebec AI Institute（魁北克人工智能研究所） ； Université de Montréal（蒙特利尔大学） ； Capital One 纠错

Comments Published as a conference paper at ACL 2025

Representation Bending for Large Language Model Safety

Ashkan Yousefpour, Taeheon Kim, Ryan S. Kwon, Seungbeen Lee, Wonje Jeung, Seungju Han, Alvin Wan, Harrison Ngan, Youngjae Yu, Jonghyun Choi

机构 * Seoul National University（首尔国立大学） ； Yonsei University（延世大学） ； AIM Intelligence（AIM智能） ； University of Michigan（密歇根大学） ； Stanford University（斯坦福大学） ； Amazon AWS（亚马逊AWS） 纠错

Comments Accepted to ACL 2025 (main)

Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools

Junde Wu, Jiayuan Zhu, Yuyuan Liu, Min Xu, Yueming Jin

机构 * University of Oxford（牛津大学） ； National University of Singapore（新加坡国立大学） ； Carnegie Mellon University（卡内基梅隆大学） ； MBZUAI 纠错

Comments ACL 2025

AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning

Jiayu Li, Xuan Zhu, Fang Liu, Yanjun Qi

机构 * Syracuse University（苏塞克斯大学） ； AWS Bedrock Science（AWS Bedrock科学） 纠错

Comments Accepted for publication in ACL 2025. The official version will be available in the ACL Anthology

Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities

Shivam Chandhok, Wan-Cyuan Fan, Vered Shwartz, Vineeth N Balasubramanian, Leonid Sigal

机构 * University of British Columbia（不列颠哥伦比亚大学） ； Vector Institute for AI（人工智能矢量研究所） ； IIT Hyderabad（海得拉巴印度理工学院） ； CIFAR AI Chair（卡尔加里人工智能主席） ； Microsoft Research India（微软印度研究院） 纠错

Comments Accepted at ACL 2025 (Main Conference)

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning

Chenxi Huang, Shaotian Yan, Liang Xie, Binbin Lin, Sinan Fan, Yue Xin, Deng Cai, Chen Shen, Jieping Ye

Comments Accepted by ACL 2025

OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agents

Pengzhou Cheng, Zheng Wu, Zongru Wu, Aston Zhang, Zhuosheng Zhang, Gongshen Liu

机构 * School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院） 纠错

Comments 25 pages, 24 figures, 11 tables (ACL 2025, Findings)

Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process

Ermo Hua, Biqing Qi, Kaiyan Zhang, Kai Tian, Xingtai Lv, Ning Ding, Bowen Zhou

机构 * Department of Electronic Engineering, Tsinghua University（清华大学电子工程系） ； Shanghai AI Laboratory（上海人工智能实验室） 纠错

Comments Accepted to ACL 2025, Oral & Panel Discussion

Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding

Qi Feng, Yihong Liu, Hinrich Schütze

机构 * Center for Information and Language Processing, LMU Munich（信息与语言处理中心，慕尼黑大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心） 纠错

Comments 18 pages, 23 figures. To appear in ACL 2025 Student Research Workshop (SRW)

KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding

Zhangchen Xu, Yang Liu, Yueqin Yin, Mingyuan Zhou, Radha Poovendran

机构 * Microsoft GenAI（微软生成人工智能） ； University of Washington（华盛顿大学） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

Comments Accepted by ACL 2025. Codes and Data: https://kodcode-ai.github.io/

A Survey of Automatic Prompt Optimization with Instruction-focused Heuristic-based Search Algorithm

Wendi Cui, Zhuohang Li, Hao Sun, Damien Lopez, Kamalika Das, Bradley A. Malin, Sricharan Kumar, Jiaxin Zhang

机构 * Intuit ； Intuit AI Research ； Vanderbilt University（范德比大学） ； University of Cambridge（剑桥大学） ； Vanderbilt University Medical Center（范德比大学医学中心） 纠错

Comments Accepted to ACL 2025

Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing

Irina Saparina, Mirella Lapata

机构 * Institute for Language, Cognition and Computation, School of Informatics, University of Edinburgh（语言、认知与计算研究所，信息学院，爱丁堡大学） 纠错

Comments Findings of ACL 2025

Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language Models

Shuai Niu, Jing Ma, Hongzhan Lin, Liang Bai, Zhihua Wang, Yida Xu, Yunya Song, Xian Yang

机构 * Hong Kong Baptist University（香港 Baptist 大学） ； Shanxi University（山西大学） ； Shanghai Institute for Advanced Study of Zhejiang University（浙江大学上海先进研究院） ； Hong Kong University of Science and Technology（香港科技大学） ； The University of Manchester（曼彻斯特大学） 纠错

Comments 13 pages. 7 figures

Journal ref This paper is accpeted by ACL2025(Main)

Self-calibration for Language Model Quantization and Pruning

Miles Williams, George Chrysostomou, Nikolaos Aletras

Comments NAACL 2025

Journal ref Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

Evaluation of Attribution Bias in Generator-Aware Retrieval-Augmented Large Language Models

Amin Abolghasemi, Leif Azzopardi, Seyyed Hadi Hashemi, Maarten de Rijke, Suzan Verberne

机构 * Leiden University（莱顿大学） ； University of Strathclyde（斯特拉思克莱德大学） ； eBay Inc.（eBay公司） ； University of Amsterdam（阿姆斯特丹大学） 纠错

Comments Accepted at ACL 2025 (Findings)

READoc: A Unified Benchmark for Realistic Document Structured Extraction

Zichao Li, Aizier Abulaiti, Yaojie Lu, Xuanang Chen, Jia Zheng, Hongyu Lin, Xianpei Han, Le Sun

机构 * Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所信息处理实验室） ； University of Chinese Academy of Sciences（中国科学院大学） ； Ricoh Software Research Center Beijing Co., Ltd（富士通软件研究（北京）有限公司） 纠错

Comments ACL 2025 Findings

SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization

Wendi Cui, Zhuohang Li, Hao Sun, Damien Lopez, Kamalika Das, Bradley Malin, Sricharan Kumar, Jiaxin Zhang

机构 * Intuit ； Intuit AI Research ； Vanderbilt University ； University of Cambridge ； Vanderbilt University Medical Center 纠错

Comments Accepted to ACL 2025 (Main Conference)