ACL

Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law

Qiming Ge, Shuhao Xing, Songyang Gao, Yunhua Zhou, Yicheng Zou, Songyang Zhang, Zhi Chen, Hang Yan, Qi Zhang, Qipeng Guo, Kai Chen

机构 * Shanghai AI Laboratory（上海人工智能实验室） ； College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院） 纠错

Comments 9 pages, 9 figures, ACL2025

SPOT: Bridging Natural Language and Geospatial Search for Investigative Journalists

Lynn Khellaf, Ipek Baris Schlicht, Tilman Mirass, Julia Bayer, Tilman Wagner, Ruben Bouwmeester

机构 * Deutsche Welle Innovation（德国之声创新） 纠错

Comments Accepted to ACL 2025

Just Go Parallel: Improving the Multilingual Capabilities of Large Language Models

Muhammad Reza Qorib, Junyi Li, Hwee Tou Ng

机构 * Department of Computer Science, National University of Singapore（计算机科学系，新加坡国立大学） 纠错

Comments ACL 2025

Multi-document Summarization through Multi-document Event Relation Graph Reasoning in LLMs: a case study in Framing Bias Mitigation

Yuanyuan Lei, Ruihong Huang

机构 * Department of Computer Science and Engineering（计算机科学与工程系） 纠错

Comments Accepted to ACL 2025

CliniDial: A Naturally Occurring Multimodal Dialogue Dataset for Team Reflection in Action During Clinical Operation

Naihao Deng, Kapotaksha Das, Rada Mihalcea, Vitaliy Popov, Mohamed Abouelenien

机构 * University of Michigan, Ann Arbor（密歇根大学安娜堡分校） ； University of Michigan, Dearborn（密歇根大学德雷本分校） 纠错

Comments Accepted to ACL 2025 Findings

JEBS: A Fine-grained Biomedical Lexical Simplification Task

William Xia, Ishita Unde, Brian Ondov, Dina Demner-Fushman

机构 * Tufts University（塔夫茨大学） ； Johns Hopkins University（约翰霍普金斯大学） ； Yale University（耶鲁大学） ； National Library of Medicine（国家医学图书馆） 纠错

Comments 13 pages, 2 figures, to be published in Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics

ArgHiTZ at ArchEHR-QA 2025: A Two-Step Divide and Conquer Approach to Patient Question Answering for Top Factuality

Adrián Cuadrón, Aimar Sagasti, Maitane Urruela, Iker De la Iglesia, Ane G Domingo-Aldama, Aitziber Atutxa, Josu Goikoetxea, Ander Barrena

机构 * HiTZ Center - Ixa, University of the Basque Country UPV/EHU（HiTZ中心-伊萨，巴斯克大学UPV/EHU） 纠错

Comments This paper has been accepted for publication in Proceedings of the 24th Workshop on Biomedical Natural Language Processing (BioNLP) at ACL 2025

Profiling News Media for Factuality and Bias Using LLMs and the Fact-Checking Methodology of Human Experts

Zain Muhammad Mujahid, Dilshod Azizov, Maha Tufail Agro, Preslav Nakov

机构 * Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） ； University of Copenhagen（哥本哈根大学） 纠错

Comments Accepted to Findings of the Association for Computational Linguistics (ACL) 2025

Towards Fairness Assessment of Dutch Hate Speech Detection

Julie Bauer, Rishabh Kaushal, Thales Bertaglia, Adriana Iamnitchi

机构 * Maastricht University（马斯特里赫特大学） ； Indira Gandhi Delhi Technical University for Women（英迪拉·甘地德里技术学院女子大学） ； Utrecht University（埃因霍温大学） 纠错

Comments Accepted for publication at the 9th Workshop on Online Abuse and Harms (WOAH) held in conjunction with ACL 2025

TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks

Zhou Chen, Zhiqiang Wei, Yuqi Bai, Xue Xiong, Jianmin Wu

机构 * Tsinghua University（清华大学） ； AI Cloud Group, Baidu Inc.（百度AI云部门） 纠错

Comments ACL 2025, 26 pages, 13 figures, 14 tables

Group then Scale: Dynamic Mixture-of-Experts Multilingual Language Model

Chong Li, Yingzhuo Deng, Jiajun Zhang, Chengqing Zong

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS, Beijing, China（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院，北京） ； School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China（人工智能学院，中国科学院大学，北京） 纠错

Comments ACL 2025, our codes and models are available at https://github.com/ZNLP/DMoE

Model Merging for Knowledge Editing

Zichuan Fu, Xian Wu, Guojing Li, Yingying Zhang, Yefeng Zheng, Tianshi Ming, Yejing Wang, Wanyu Wang, Xiangyu Zhao

机构 * City University of Hong Kong（香港城市大学） ； Tencent Jarvis Lab（腾讯 Jarvis 实验室） ； Westlake University（西湖大学） ； Tongji University（同济大学） 纠错

Comments 11 pages, 3 figures

Journal ref ACL 2025 (Industry) Oral

Training-free LLM Merging for Multi-task Learning

Zichuan Fu, Xian Wu, Yejing Wang, Wanyu Wang, Shanshan Ye, Hongzhi Yin, Yi Chang, Yefeng Zheng, Xiangyu Zhao

机构 * City University of Hong Kong（香港城市大学） ； Tencent Jarvis Lab（腾讯 Jarvis 实验室） ； University of Technology Sydney（悉尼大学） ； University of Queensland（昆士兰大学） ； Jilin University（吉林大学） ； Westlake University（西湖大学） 纠错

Comments 14 pages, 6 figures

Journal ref ACL 2025 Main

When Detection Fails: The Power of Fine-Tuned Models to Generate Human-Like Social Media Text

Hillary Dawkins, Kathleen C. Fraser, Svetlana Kiritchenko

机构 * National Research Council Canada（加拿大国家研究理事会） 纠错

Comments to appear in ACL Findings

Team Anotheroption at SemEval-2025 Task 8: Bridging the Gap Between Open-Source and Proprietary LLMs in Table QA

Nikolas Evkarpidi, Elena Tutubalina

机构 * HSE University（俄罗斯伏尔加格勒国立大学） ； AIRI Sber AI Kazan Federal University（卡兹别克联邦大学） 纠错

Comments Accepted for publication at the 19th International Workshop on Semantic Evaluation (SemEval-2025), to be held in conjunction with ACL 2025. 15 pages, 5 figures; full paper title was added

MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion

Qizhi Pei, Lijun Wu, Zhuoshi Pan, Yu Li, Honglin Lin, Chenlin Ming, Xin Gao, Conghui He, Rui Yan

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学北京校区人工智能学院） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Tsinghua University（清华大学） ； Shanghai Jiao Tong University（上海交通大学） ； Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE（教育部下一代智能搜索与推荐工程技术研究中心） ； School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院） 纠错

Comments Accepted by ACL 2025 (main)

InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Model

Siqi Ouyang, Xi Xu, Lei Li

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Language Technologies Institute（语言技术研究所） 纠错

Comments ACL 2025 Findings

A Training-free LLM-based Approach to General Chinese Character Error Correction

Houquan Zhou, Bo Zhang, Zhenghua Li, Ming Yan, Min Zhang

Comments Accepted at Main Conference of ACL 2025, 26 pages, 12 figures

Entity Framing and Role Portrayal in the News

Tarek Mahmoud, Zhuohan Xie, Dimitar Dimitrov, Nikolaos Nikolaidis, Purificação Silvano, Roman Yangarber, Shivam Sharma, Elisa Sartori, Nicolas Stefanovitch, Giovanni Da San Martino, Jakub Piskorski, Preslav Nakov

机构 * MBZUAI, UAE（阿联酋MBZUAI） ； Sofia University "St. Kliment Ohridski", Bulgaria（保加利亚索菲亚大学） ； Athens University of Economics and Business, Greece（希腊雅典经济与商业大学） ； University of Porto, Portugal（葡萄牙波尔图大学） ； University of Helsinki, Finland（芬兰赫尔辛基大学） ； Indian Institute of Technology Delhi, India（印度德里印度理工学院） ； University of Padova, Italy（意大利帕多瓦大学） ； European Commission Joint Research Centre, Italy（意大利欧盟联合研究中心） ； Institute of Computer Science, Polish Academy of Sciences, Poland（波兰科学院计算机科学研究所） 纠错

Comments 25 pages, 13 figures. Accepted to ACL 2025

ProMedTS: A Self-Supervised, Prompt-Guided Multimodal Approach for Integrating Medical Text and Time Series

Shuai Niu, Jing Ma, Hongzhan Lin, Liang Bai, Zhihua Wang, Wei Bi, Yida Xu, Guo Li, 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（浙江大学上海研究院） ； Tencent AI Lab（腾讯人工智能实验室） ； Manchester Metropolitan University（曼彻斯特 Metropolitan 大学） ； The University of Manchester（曼彻斯特大学） 纠错

Comments This paper is accepted by ACL2025(Findings)

CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis

Bohan Zhang, Xiaokang Zhang, Jing Zhang, Jifan Yu, Sijia Luo, Jie Tang

机构 * School of Information, Renmin University of China（中国人民大学信息学院） ； Tsinghua University（清华大学） ； Key Laboratory of Data Engineering and Knowledge Engineering, Beijing, China（数据工程与知识工程重点实验室） 纠错

Comments Accepted as Main of ACL2025

From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection

Haowei Wang, Rupeng Zhang, Junjie Wang, Mingyang Li, Yuekai Huang, Dandan Wang, Qing Wang

机构 * State Key Laboratory of Intelligent Game（智能游戏国家重点实验室） ； Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所） ； University of Chinese Academy of Sciences（中国科学院大学） 纠错

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), pages 2009-2028

ReflecTool: Towards Reflection-Aware Tool-Augmented Clinical Agents

Yusheng Liao, Shuyang Jiang, Yanfeng Wang, Yu Wang

机构 * Shanghai Jiao Tong University（上海交通大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Fudan University（复旦大学） 纠错

Comments ACL 2025 Main Paper

Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning

Yexing Du, Youcheng Pan, Ziyang Ma, Bo Yang, Yifan Yang, Keqi Deng, Xie Chen, Yang Xiang, Ming Liu, Bing Qin

机构 * Harbin Institute of Technology（哈尔滨工业大学） ； Pengcheng Laboratory（鹏城实验室） ； Shanghai Jiao Tong University（上海交通大学） ； University of Cambridge（剑桥大学） 纠错

Comments Accepted in ACL 2025 (Main)

Fast-and-Frugal Text-Graph Transformers are Effective Link Predictors

Andrei C. Coman, Christos Theodoropoulos, Marie-Francine Moens, James Henderson

机构 * Idiap Research Institute（Idiap研究机构） ； EPFL（瑞士联邦理工学院） ； KU Leuven（根特大学） 纠错

Comments Accepted to ACL 2025 Findings

PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference

Jiaming Ji, Donghai Hong, Borong Zhang, Boyuan Chen, Juntao Dai, Boren Zheng, Tianyi Qiu, Jiayi Zhou, Kaile Wang, Boxuan Li, Sirui Han, Yike Guo, Yaodong Yang

机构 * Peking University（北京大学） ； The Hong Kong University of Science and Technology（香港科学与技术大学） ； Infinigence-AI 纠错

Comments Accepted by ACL2025 Main, a sibling project to SafeRLHF and BeaverTails

Could Chemical LLMs benefit from Message Passing

Jiaqing Xie, Ziheng Chi

机构 * Department of Computer Science（计算机科学系） ； ETH Zurich（苏黎世联邦理工学院） 纠错

Comments Accepted at ACL @ Languages and Molecules 2024. In Proceedings of ACL 2024

Unveiling Confirmation Bias in Chain-of-Thought Reasoning

Yue Wan, Xiaowei Jia, Xiang Lorraine Li

机构 * University of Pittsburgh（匹兹堡大学） 纠错

Journal ref ACL 2025 Findings

Can LLMs Generate High-Quality Test Cases for Algorithm Problems? TestCase-Eval: A Systematic Evaluation of Fault Coverage and Exposure

Zheyuan Yang, Zexi Kuang, Xue Xia, Yilun Zhao

机构 * Tongji University（同济大学） ； Northeastern University（东北大学） ； HKUST（香港科技大学） ； Yale University（耶鲁大学） 纠错

Comments ACL 2025

The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogs

Avinash Baidya, Kamalika Das, Xiang Gao

机构 * Intuit AI Research（Intuit AI研究院） 纠错

Comments ACL 2025; 18 pages, 8 figures