ACL

Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement

Xunjian Yin, Xinyi Wang, Liangming Pan, Li Lin, Xiaojun Wan, William Yang Wang

机构 * Peking University（北京大学） ； University of California, Santa Barbara（加州大学圣巴巴拉分校） ； University of Arizona（亚利桑那大学） 纠错

Comments ACL 2025 main. The code can be found at https://github.com/Arvid-pku/Godel_Agent

Can Language Models Reason about Individualistic Human Values and Preferences?

Liwei Jiang, Taylor Sorensen, Sydney Levine, Yejin Choi

机构 * University of Washington（华盛顿大学） ； Google DeepMind（谷歌DeepMind） ； Stanford University（斯坦福大学） ； Allen Institute for Artificial Intelligence（人工智能研究院） 纠错

Comments Camera Ready at ACL Main 2025

ReflectDiffu:Reflect between Emotion-intent Contagion and Mimicry for Empathetic Response Generation via a RL-Diffusion Framework

Jiahao Yuan, Zixiang Di, Zhiqing Cui, Guisong Yang, Usman Naseem

机构 * University of Shanghai for Science and Technology（上海理工大学） ； East China Normal University（华东师范大学） ； Nanjing University of Information Science and Technology（南京信息工程大学） ； Macquarie University（麦考瑞大学） 纠错

Comments Accepted by ACL 2025 Main Conference

WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks

Anudeex Shetty, Qiongkai Xu, Jey Han Lau

机构 * School of Computing and Information System, the University of Melbourne（计算机与信息系统学院，墨尔本大学） ； School of Computing, FSE, Macquarie University（计算机学院，麦觉里大学） 纠错

Comments Accepted to ACL 2025 (Main Proceedings)

Awes, Laws, and Flaws From Today's LLM Research

Adrian de Wynter

机构 * Microsoft（微软公司） ； University of York（约克大学） 纠错

Comments Accepted to ACL 2025 (Findings)

Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models

Jinyang Wu, Shuai Zhang, Feihu Che, Mingkuan Feng, Chuyuan Zhang, Pengpeng Shao, Jianhua Tao

机构 * Department of Automation, Tsinghua University（自动化系，清华大学） ； Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心） 纠错

Comments ACL 2025 Main

LETS-C: Leveraging Text Embedding for Time Series Classification

Rachneet Kaur, Zhen Zeng, Tucker Balch, Manuela Veloso

机构 * J.P. Morgan AI Research（摩根大通人工智能研究） 纠错

Comments ACL 2025 (Main Conference)

Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models

Sangmin Woo, Donguk Kim, Jaehyuk Jang, Yubin Choi, Changick Kim

机构 * KAIST（韩国科学技术院） 纠错

Comments ACL 2025 Findings; Project: https://sangminwoo.github.io/AvisC/

Anchored Answers: Unravelling Positional Bias in GPT-2's Multiple-Choice Questions

Ruizhe Li, Yanjun Gao

机构 * Department of Computing Science, University of Aberdeen, UK（阿伯丁大学计算机科学系） ； University of Colorado Anschutz Medical Campus, United States（科罗拉多大学安舒茨医学校区） 纠错

Comments ACL 2025 Findings

LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs

Kaibo Liu, Zhenpeng Chen, Yiyang Liu, Jie M. Zhang, Mark Harman, Yudong Han, Yun Ma, Yihong Dong, Ge Li, Gang Huang

机构 * Peking University（北京大学） ； Nanyang Technological University（南洋理工大学） ； King’s College London（伦敦国王学院） ； University College London（伦敦大学学院） ； National Key Laboratory of Data Space Technology and System（数据空间技术与系统国家重点实验室） 纠错

Comments Accepted by the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025) Main Track

SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition

Shuangrui Ding, Zihan Liu, Xiaoyi Dong, Pan Zhang, Rui Qian, Junhao Huang, Conghui He, Dahua Lin, Jiaqi Wang

机构 * The Chinese University of Hong Kong（中国香港大学） ； Beihang University（北航） ； Shanghai AI Laboratory（上海人工智能实验室） ； CPII under InnoHK（创新香港下的CPII） 纠错

Comments ACL 2025 main. project page: https://pjlab-songcomposer.github.io/ code: https://github.com/pjlab-songcomposer/songcomposer

Drop Dropout on Single-Epoch Language Model Pretraining

Houjun Liu, John Bauer, Christopher D. Manning

机构 * Stanford University（斯坦福大学） 纠错

Comments Accepted to ACL Findings; 5 pages, 2 figures, 4 pages of appendix

Don't Reinvent the Wheel: Efficient Instruction-Following Text Embedding based on Guided Space Transformation

Yingchaojie Feng, Yiqun Sun, Yandong Sun, Minfeng Zhu, Qiang Huang, Anthony K. H. Tung, Wei Chen

机构 * State Key Lab of CAD&CG（CAD与CG国家重点实验室） ； School of Computing（计算机学院） ； National University of Singapore（新加坡国立大学） ； School of Intelligence Science and Engineering（智能科学与工程学院） ； Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）） 纠错

Comments Accepted to ACL 2025

CoRet: Improved Retriever for Code Editing

Fabio Fehr, Prabhu Teja Sivaprasad, Luca Franceschi, Giovanni Zappella

机构 * EPFL（苏黎世联邦理工学院） ； Idiap Research Institute（伊迪亚普研究机构） ； AWS AI Labs（亚马逊AI实验室） 纠错

Comments ACL 2025

FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation

Junyu Luo, Zhizhuo Kou, Liming Yang, Xiao Luo, Jinsheng Huang, Zhiping Xiao, Jingshu Peng, Chengzhong Liu, Jiaming Ji, Xuanzhe Liu, Sirui Han, Ming Zhang, Yike Guo

机构 * State Key Laboratory for Multimedia Information Processing, PKU-Anker LLM Lab（多媒体信息处理国家重点实验室，PKU-Anker LLM实验室） ； School of Computer Science, Peking University（北京大学计算机学院） ； HKUST（香港科技大学） ； University of California, Los Angeles（加州大学洛杉矶分校） ； University of Washington（华盛顿大学） 纠错

Comments ACL 2025 Main Conference

PRISM: A Framework for Producing Interpretable Political Bias Embeddings with Political-Aware Cross-Encoder

Yiqun Sun, Qiang Huang, Anthony K. H. Tung, Jun Yu

机构 * School of Computing, National University of Singapore（新加坡国立大学计算机学院） ； School of Intelligence Science and Engineering, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）智能科学与工程学院） 纠错

Comments Accepted to ACL 2025

Disentangling Language and Culture for Evaluating Multilingual Large Language Models

Jiahao Ying, Wei Tang, Yiran Zhao, Yixin Cao, Yu Rong, Wenxuan Zhang

机构 * Singapore Management University（新加坡管理学院） ； University of Science and Technology of China（中国科学技术大学） ； National University of Singapore（新加坡国立大学） ； Institute of Trustworthy Embodied AI, Fudan University（复旦大学可信具身人工智能研究院） ； DAMO Academy, Alibaba Group（阿里集团大模型实验室） ； Singapore University of Technology and Design（新加坡科技设计大学） 纠错

Comments Accepted to ACL 2025 (Main Conference)

NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization

Hyuntak Kim, Byung-Hak Kim

机构 * CJ Corporation（CJ公司） 纠错

Comments Accepted to the main track of ACL 2025

Improving Language and Modality Transfer in Translation by Character-level Modeling

Ioannis Tsiamas, David Dale, Marta R. Costa-jussà

机构 * FAIR at Meta, Paris（Meta巴黎FAIR实验室） ； Universitat Politècnica de Catalunya, Barcelona（巴塞罗那理工大学） 纠错

Comments ACL 2025

Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectors

Andrea Pedrotti, Michele Papucci, Cristiano Ciaccio, Alessio Miaschi, Giovanni Puccetti, Felice Dell'Orletta, Andrea Esuli

机构 * Department of Computer Science, University of Pisa（比萨大学计算机科学系） 纠错

Comments Accepted at Findings of ACL 2025

RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation

Zhentao Xie, Chengcheng Han, Jinxin Shi, Wenjun Cui, Xin Zhao, Xingjiao Wu, Jiabao Zhao

机构 * East China Normal University（华东师范大学） ； Meituan Inc.（美团公司） ； Donghua University（东华大学） ； Tsinghua University（清华大学） 纠错

Comments Accepted by ACL 2025 (Findings)

Donate or Create? Comparing Data Collection Strategies for Emotion-labeled Multimodal Social Media Posts

Christopher Bagdon, Aidan Combs, Carina Silberer, Roman Klinger

机构 * Fundamentals of Natural Language Processing, University of Bamberg（自然语言处理基础，巴姆伯格大学） ； Department of Sociology, The Ohio State University（社会学系，俄亥俄州立大学） ； Institut für Maschinelle Sprachverarbeitung, University of Stuttgart（机械语言处理研究所，斯图加特大学） 纠错

Comments Published at ACL 2025

Adversarial Preference Learning for Robust LLM Alignment

Yuanfu Wang, Pengyu Wang, Chenyang Xi, Bo Tang, Junyi Zhu, Wenqiang Wei, Chen Chen, Chao Yang, Jingfeng Zhang, Chaochao Lu, Yijun Niu, Keming Mao, Zhiyu Li, Feiyu Xiong, Jie Hu, Mingchuan Yang

Comments Accepted at ACL2025 Findings

Unifying Language Agent Algorithms with Graph-based Orchestration Engine for Reproducible Agent Research

Qianqian Zhang, Jiajia Liao, Heting Ying, Yibo Ma, Haozhan Shen, Jingcheng Li, Peng Liu, Lu Zhang, Chunxin Fang, Kyusong Lee, Ruochen Xu, Tiancheng Zhao

机构 * Om AI Research（Om AI研究机构） ； Binjiang Institute of Zhejiang University（浙江大学滨江学院） ； College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院） 纠错

Comments Accepted by ACL 2025 Demo

Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings

Shujian Yang, Shiyao Cui, Chuanrui Hu, Haicheng Wang, Tianwei Zhang, Minlie Huang, Jialiang Lu, Han Qiu

机构 * Shanghai Jiao Tong University（上海交通大学） ； Tsinghua University（清华大学） ； Qihoo 360（奇安信） ； Nanyang Technological University（南洋理工大学） 纠错

Comments Accepted to ACL 2025 (Findings). Camera-ready version

Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations

Xin Quan, Marco Valentino, Louise A. Dennis, André Freitas

Comments Camera-ready for ACL 2025

Proactive Guidance of Multi-Turn Conversation in Industrial Search

Xiaoyu Li, Xiao Li, Li Gao, Yiding Liu, Xiaoyang Wang, Shuaiqiang Wang, Junfeng Wang, Dawei Yin

机构 * Baidu Inc.（百度公司） 纠错

Comments ACL'25 (Industry)

Mamba Knockout for Unraveling Factual Information Flow

Nir Endy, Idan Daniel Grosbard, Yuval Ran-Milo, Yonatan Slutzky, Itay Tshuva, Raja Giryes

机构 * Tel Aviv University（特拉维夫大学） 纠错

Comments Accepted to ACL 2025

ERU-KG: Efficient Reference-aligned Unsupervised Keyphrase Generation

Lam Thanh Do, Aaditya Bodke, Pritom Saha Akash, Kevin Chen-Chuan Chang

Comments Accepted to ACL 2025

Are Any-to-Any Models More Consistent Across Modality Transfers Than Specialists?

Jiwan Chung, Janghan Yoon, Junhyeong Park, Sangeyl Lee, Joowon Yang, Sooyeon Park, Youngjae Yu

机构 * Yonsei University（延世大学） 纠错

Journal ref ACL 2025