ACL

FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation

Zhuocheng Zhang, Yang Feng, Min Zhang

机构 * Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS)（中国科学院智能信息处理重点实验室） ； University of Chinese Academy of Sciences, China（中国科学院大学） ； Key Laboratory of AI Safety, Chinese Academy of Sciences（中国科学院人工智能安全重点实验室） ； Institute of Computing and Intelligence, Harbin Institute of Technology (Shenzhen), China（哈尔滨工业大学（深圳）计算机与智能信息研究院） 纠错

Comments Accepted by ACL 2025 Demo

Brevity is the soul of sustainability: Characterizing LLM response lengths

Soham Poddar, Paramita Koley, Janardan Misra, Sanjay Podder, Navveen Balani, Niloy Ganguly, Saptarshi Ghosh

机构 * Indian Institute of Technology, Kharagpur（印度理工学院，克哈格布尔分校） ； Indian Statistical Institute, Kolkata（印度统计研究所，科契） ； Accenture Labs, Bangalore（埃森哲实验室，班加罗尔） 纠错

Comments Accepted to appear at the ACL 2025 findings

SConU: Selective Conformal Uncertainty in Large Language Models

Zhiyuan Wang, Qingni Wang, Yue Zhang, Tianlong Chen, Xiaofeng Zhu, Xiaoshuang Shi, Kaidi Xu

机构 * University of Electronic Science and Technology of China（电子科技大学） ； Drexel University（德雷塞尔大学） ； University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校） 纠错

Comments Accepted by ACL 2025 Main

LLM Braces: Straightening Out LLM Predictions with Relevant Sub-Updates

Ying Shen, Lifu Huang

机构 * Computer Science Department University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校计算机科学系） ； Computer Science Department UC Davis（加州大学戴维斯分校计算机科学系） 纠错

Comments ACL 2025, 16 pages, 2 figures

Enough Coin Flips Can Make LLMs Act Bayesian

Ritwik Gupta, Rodolfo Corona, Jiaxin Ge, Eric Wang, Dan Klein, Trevor Darrell, David M. Chan

机构 * University of California, Berkeley（加州大学伯克利分校） 纠错

Comments ACL 2025 Main

Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement

Yaxuan Kong, Yiyuan Yang, Yoontae Hwang, Wenjie Du, Stefan Zohren, Zhangyang Wang, Ming Jin, Qingsong Wen

机构 * University of Oxford（牛津大学） ； PyPOTS Research（PyPOTS研究） ； University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Griffith University（格里菲斯大学） ； Squirrel Ai Learning（Squirrel Ai学习） 纠错

Comments Annual Meeting of the Association for Computational Linguistics (ACL 2025, Main)

I see what you mean: Co-Speech Gestures for Reference Resolution in Multimodal Dialogue

Esam Ghaleb, Bulat Khaertdinov, Aslı Özyürek, Raquel Fernández

机构 * Multimodal Language Department, Max Planck Institute for Psycholinguistics（马克斯·普朗克心理语言学研究所多模态语言部门） ； Donders Institute for Brain, Cognition and Behaviour, Radboud University（拉德堡德大学大脑、认知与行为研究所） ； Department of Advanced Computing Sciences, Maastricht University（马斯特里赫特大学高级计算科学系） ； Institute for Logic, Language and Computation, University of Amsterdam（阿姆斯特丹大学逻辑、语言与计算研究所） 纠错

Comments Accepted to Findings of ACL 2025

Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles

Kuang Wang, Xianfei Li, Shenghao Yang, Li Zhou, Feng Jiang, Haizhou Li

机构 * SRIBD, School of Data Science, The Chinese University of Hong Kong, Shenzhen, Guangdong（香港中文大学（深圳）数据科学学院） ； Artificial Intelligence Research Institute, Shenzhen University of Advanced Technology（深圳先进技术大学人工智能研究院） ； Department of ECE, National University of Singapore（新加坡国立大学电子工程系） 纠错

Comments 9 pages. Accepted to ACL 2025. Camera-ready version

Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization

Yao Xiao, Hai Ye, Linyao Chen, Hwee Tou Ng, Lidong Bing, Xiaoli Li, Roy Ka-wei Lee

机构 * Singapore University of Technology and Design（新加坡科技设计大学） ； National University of Singapore（国立新加坡大学） ； The University of Tokyo（东京大学） ； MiroMind（MiroMind公司） ； Institute for Infocomm Research, A*Star, Singapore（新加坡*星研究院信息与通信研究所） 纠错

Comments ACL25 Main

Mechanistic Interpretability of Emotion Inference in Large Language Models

Ala N. Tak, Amin Banayeeanzade, Anahita Bolourani, Mina Kian, Robin Jia, Jonathan Gratch

机构 * Institute for Creative Technologies, University of Southern California (USC)（创意技术研究所，南加州大学） ； Information Sciences Institute, University of Southern California (USC)（信息科学研究所，南加州大学） ； Department of Computer Science, University of Southern California (USC)（计算机科学系，南加州大学） ； Department of Statistics and Data Science, University of California, Los Angeles (UCLA)（统计与数据科学系，加州大学洛杉矶分校） 纠错

Comments ACL 2025 camera-ready version. First two authors contributed equally

Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modeling

Suvodip Dey, Yi-Jyun Sun, Gokhan Tur, Dilek Hakkani-Tur

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

Comments Accepted at ACL 2025 Main Conference

PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models

Mingyang Song, Zhaochen Su, Xiaoye Qu, Jiawei Zhou, Yu Cheng

Comments Accepted by ACL 2025 Main. Project Page: https://prmbench.github.io/

Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning

Yongxin Xu, Ruizhe Zhang, Xinke Jiang, Yujie Feng, Yuzhen Xiao, Xinyu Ma, Runchuan Zhu, Xu Chu, Junfeng Zhao, Yasha Wang

Comments Accepted to ACL 2025 Main Conference

FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models

Raghav Singhal, Kaustubh Ponkshe, Praneeth Vepakomma

机构 * Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） ； Massachusetts Institute of Technology（麻省理工学院） 纠错

Comments ACL 2025 - Oral. Raghav Singhal and Kaustubh Ponkshe contributed equally to this work

Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph

Roman Vashurin, Ekaterina Fadeeva, Artem Vazhentsev, Lyudmila Rvanova, Akim Tsvigun, Daniil Vasilev, Rui Xing, Abdelrahman Boda Sadallah, Kirill Grishchenkov, Sergey Petrakov, Alexander Panchenko, Timothy Baldwin, Preslav Nakov, Maxim Panov, Artem Shelmanov

Comments Published at TACL 2025, presented at ACL 2025. Roman Vashurin, Ekaterina Fadeeva, Artem Vazhentsev contributed equally

Journal ref Transactions of the Association for Computational Linguistics, 13 (2025) 220-248

MMInA: Benchmarking Multihop Multimodal Internet Agents

Shulin Tian, Ziniu Zhang, Liangyu Chen, Ziwei Liu

机构 * S-Lab, Nanyang Technological University（南洋理工大学S实验室） 纠错

Comments ACL 2025 findings. The live leaderboard is at https://mmina.cliangyu.com/

Psycholinguistic Word Features: a New Approach for the Evaluation of LLMs Alignment with Humans

Javier Conde, Miguel González, María Grandury, Gonzalo Martínez, Pedro Reviriego, Mar Brysbaert

机构 * Universidad Politécnica de Madrid（马德里理工大学） ； Ghent University（根特大学） 纠错

Comments Accepted for the GEM2 workshop at ACL 2025

Data Quality Issues in Multilingual Speech Datasets: The Need for Sociolinguistic Awareness and Proactive Language Planning

Mingfei Lau, Qian Chen, Yeming Fang, Tingting Xu, Tongzhou Chen, Pavel Golik

机构 * Google（谷歌） 纠错

Comments Accepted by ACL 2025 Main Conference

Leveraging In-Context Learning for Political Bias Testing of LLMs

Patrick Haller, Jannis Vamvas, Rico Sennrich, Lena A. Jäger

Comments ACL 2025

Training Language Model to Critique for Better Refinement

Tianshu Yu, Chao Xiang, Mingchuan Yang, Pei Ke, Bosi Wen, Cunxiang Wang, Jiale Cheng, Li Zhang, Xinyu Mu, Chuxiong Sun, Minlie Huang

机构 * China Telecom Research Institute（中国电信研究院） ； The Conversational Artificial Intelligence (CoAI) Group, Tsinghua University（清华大学对话人工智能（CoAI）小组） ； University of Electronic Science and Technology of China（电子科技大学） ； The Knowledge Engineering Group (KEG), Tsinghua University（清华大学知识工程小组） ； Zhipu AI（智谱AI） 纠错

Comments Accepted to ACL 2025 Findings

A Dual-Layered Evaluation of Geopolitical and Cultural Bias in LLMs

Sean Kim, Hyuhng Joon Kim

机构 * Seoul National University（首尔国立大学） 纠错

Comments This paper is accepted to ACL Student Research Workshop (SRW) 2025

Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation

Qiyue Gao, Xinyu Pi, Kevin Liu, Junrong Chen, Ruolan Yang, Xinqi Huang, Xinyu Fang, Lu Sun, Gautham Kishore, Bo Ai, Stone Tao, Mengyang Liu, Jiaxi Yang, Chao-Jung Lai, Chuanyang Jin, Jiannan Xiang, Benhao Huang, Zeming Chen, David Danks, Hao Su, Tianmin Shu, Ziqiao Ma, Lianhui Qin, Zhiting Hu

机构 * UC San Diego ； JHU Cornell Tech ； EPFL ； UMich 纠错

Comments ACL 2025 (Findings)

MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents

Haoran Tan, Zeyu Zhang, Chen Ma, Xu Chen, Quanyu Dai, Zhenhua Dong

机构 * 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研究中心，教育部） ； Gaoling School of Artificial, Renmin University of China（马克思主义学院，中国人民大学） ； Huawei Noah’s Ark Lab（华为诺亚方舟实验室） 纠错

Comments 17 pages, 5 figures. Accepted by ACL 2025 findings

MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence Calibration

Zhitao He, Sandeep Polisetty, Zhiyuan Fan, Yuchen Huang, Shujin Wu, Yi R. Fung

机构 * Hong Kong University of Science and Technology（香港科技大学） ； UMass Amherst（马萨诸塞大学阿姆赫斯特分校） ； University of Southern California（南加州大学） 纠错

Comments 18 pages, ACL 2025

Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs

Jingcheng Niu, Xingdi Yuan, Tong Wang, Hamidreza Saghir, Amir H. Abdi

机构 * University of Toronto（多伦多大学） ； Technical University of Darmstadt（达姆施塔特技术大学） ； Microsoft（微软公司） 纠错

Comments ACL 2025

TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Models

Xinyi He, Yihao Liu, Mengyu Zhou, Yeye He, Haoyu Dong, Shi Han, Zejian Yuan, Dongmei Zhang

机构 * State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（人机混合增强智能国家重点实验室，人工智能与机器人研究院，西安交通大学） ； Peking University（北京大学） ； Microsoft（微软公司） 纠错

Comments Accepted by ACL 2025 main conference, long paper

KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding

Ahmed Heakl, Abdullah Sohail, Mukul Ranjan, Rania Hossam, Ghazi Shazan Ahmad, Mohamed El-Geish, Omar Maher, Zhiqiang Shen, Fahad Khan, Salman Khan

机构 * MBZUAI（马尔瓦大学人工智能研究所） ； Monta AI（蒙塔人工智能） ； Linköping University（林雪平大学） ； Australian National University（澳大利亚国立大学） 纠错

Comments 17 pages, 5 figures, ACL 2025

A Survey of Large Language Models in Psychotherapy: Current Landscape and Future Directions

Hongbin Na, Yining Hua, Zimu Wang, Tao Shen, Beibei Yu, Lilin Wang, Wei Wang, John Torous, Ling Chen

机构 * Australian Artificial Intelligence Institute（澳大利亚人工智能研究所） ； University of Technology Sydney（悉尼科技大学） ； Harvard University（哈佛大学） ； Xi’an Jiaotong-Liverpool University（西安交通大学利物浦大学） ； University of Pennsylvania（宾夕法尼亚大学） 纠错

Comments Accepted by ACL 2025 Findings

End-to-End Long Document Summarization using Gradient Caching

Rohit Saxena, Hao Tang, Frank Keller

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

Comments Accepted to Transactions of the Association for Computational Linguistics (TACL 2025); Pre MIT Press version

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

Qiushi Sun, Kanzhi Cheng, Zichen Ding, Chuanyang Jin, Yian Wang, Fangzhi Xu, Zhenyu Wu, Chengyou Jia, Liheng Chen, Zhoumianze Liu, Ben Kao, Guohao Li, Junxian He, Yu Qiao, Zhiyong Wu

机构 * Shanghai AI Laboratory（上海人工智能实验室） ； The University of Hong Kong（香港大学） ； Johns Hopkins University（约翰霍普金斯大学） ； Shanghai Jiao Tong University（上海交通大学） ； University of Oxford（牛津大学） ； Hong Kong University of Science and Technology（香港科技大学） 纠错

Comments ACL 2025 Camera Ready