ACL

Language Fusion for Parameter-Efficient Cross-lingual Transfer

Philipp Borchert, Ivan Vulić, Marie-Francine Moens, Jochen De Weerdt

机构 * Research Centre for Information Systems Engineering, KU Leuven, Belgium（信息系统工程研究中心，鲁汶大学） ； IESEG School of Management, France（IESEG管理学院，法国） ； Language Technology Lab, University of Cambridge, United Kingdom（语言技术实验室，剑桥大学） ； Department of Computer Science, KU Leuven, Belgium（计算机科学系，鲁汶大学） 纠错

Comments ACL 2025

Registering Source Tokens to Target Language Spaces in Multilingual Neural Machine Translation

Zhi Qu, Yiran Wang, Jiannan Mao, Chenchen Ding, Hideki Tanaka, Masao Utiyama, Taro Watanabe

机构 * Nara Institute of Science and Technology（奈良科学技术研究所） ； National Institute of Information and Communications Technology（信息与通信技术国家研究所） 纠错

Comments Accepted by ACL 2025 (main)

ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty

Qing Zong, Zhaowei Wang, Tianshi Zheng, Xiyu Ren, Yangqiu Song

机构 * Department of Computer Science and Engineering, HKUST（计算机科学与工程系，香港科技大学） 纠错

Comments Accepted to ACL 2025 findings

Segment-Level Diffusion: A Framework for Controllable Long-Form Generation with Diffusion Language Models

Xiaochen Zhu, Georgi Karadzhov, Chenxi Whitehouse, Andreas Vlachos

机构 * University of Cambridge（剑桥大学） 纠错

Comments 9 pages (main body), 3 figures (main body), ACL 2025 Main

Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models

Di Wu, Xin Lu, Yanyan Zhao, Bing Qin

机构 * Research Center for Social Computing and Information Retrieval（社会计算与信息检索研究中心） ； Harbin Institute of Technology（哈尔滨工业大学） 纠错

Comments 16 pages, 14 figures. Camera-ready for ACL2025 findings

MALAMUTE: A Multilingual, Highly-granular, Template-free, Education-based Probing Dataset

Sagi Shaier, George Arthur Baker, Chiranthan Sridhar, Lawrence E Hunter, Katharina von der Wense

机构 * University of Colorado Boulder（科罗拉多大学波得尔分校） ； University of Chicago, Department of Pediatrics（芝加哥大学医学院） ； Johannes Gutenberg University Mainz（美因茨约翰尼斯·古滕贝格大学） 纠错

Comments Accepted to ACL Findings 2025

Patent-CR: A Dataset for Patent Claim Revision

Lekang Jiang, Pascal A Scherz, Stephan Goetz

机构 * University of Cambridge（剑桥大学） 纠错

Comments Accepted to NAACL 2025. 15 pages, 6 tables, 3 figures

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 2300-2314

Attacking Vision-Language Computer Agents via Pop-ups

Yanzhe Zhang, Tao Yu, Diyi Yang

机构 * Georgia Tech（佐治亚理工学院） ； The University of Hong Kong（香港大学） ； Stanford University（斯坦福大学） 纠错

Comments ACL 2025

Conformity in Large Language Models

Xiaochen Zhu, Caiqi Zhang, Tom Stafford, Nigel Collier, Andreas Vlachos

Comments 9 pages (main body), 9 figures (main body), ACL 2025 Main

MAPLE: Enhancing Review Generation with Multi-Aspect Prompt LEarning in Explainable Recommendation

Ching-Wen Yang, Zhi-Quan Feng, Ying-Jia Lin, Che-Wei Chen, Kun-da Wu, Hao Xu, Jui-Feng Yao, Hung-Yu Kao

机构 * Department of Computer Science and Information Engineering, National Cheng-Kung University（资讯工程系，国立成功大学） ； Google（谷歌） 纠错

Comments 9 main pages, 10 pages for appendix. ACL'25 Main

Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling

Xianzhen Luo, Yixuan Wang, Qingfu Zhu, Zhiming Zhang, Xuanyu Zhang, Qing Yang, Dongliang Xu

机构 * Harbin Institute of Technology（哈尔滨工业大学） ； Du Xiaoman (Beijing) Science Technology Co., Ltd.（杜小满（北京）科技有限公司） 纠错

Comments Accepted by ACL2025. Code is [here](https://github.com/Luowaterbi/TokenRecycling). Token Recycling has already merged into [SpecBench](https://github.com/hemingkx/Spec-Bench)

Can Large Language Models Generate High-quality Patent Claims?

Lekang Jiang, Caiqi Zhang, Pascal A Scherz, Stephan Goetz

机构 * University of Cambridge（剑桥大学） 纠错

Comments Accepted to NAACL 2025. 16 pages, 2 figures, 12 tables

Journal ref Findings of the Association for Computational Linguistics: NAACL 2025, pages 1272-1287

USDC: A Dataset of $\underline{U}$ser $\underline{S}$tance and $\underline{D}$ogmatism in Long $\underline{C}$onversations

Mounika Marreddy, Subba Reddy Oota, Venkata Charan Chinni, Manish Gupta, Lucie Flek

机构 * University of Bonn（波恩大学） ； TU Berlin（柏林技术大学） ； Microsoft（微软） 纠错

Comments 45 pages, 22 figures, Findings of the Association for Computational Linguistics, ACL-2025 (Long)

Journal ref ACL Findings (Long), 2025, Vienna, Austria

On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation

Xueru Wen, Jie Lou, Xinyu Lu, Ji Yuqiu, Xinyan Guan, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, Debing Zhang, Le Sun

机构 * Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, China（中国科学院软件研究所信息处理实验室，北京，中国） ； University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国） ； Xiaohongshu Inc（小红书公司） 纠错

Comments Accepted as ACL 2025 Findings

UniICL: An Efficient Unified Framework Unifying Compression, Selection, and Generation

Jun Gao, Qi Lv, Zili Wang, Tianxiang Wu, Ziqiang Cao, Wenjie Li

机构 * School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院） ； Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）） ； Hong Kong Polytechnic University（香港理工大学） ； Stepfun 纠错

Comments ACL2025

Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation

Dongjin Kang, Sunghwan Kim, Taeyoon Kwon, Seungjun Moon, Hyunsouk Cho, Youngjae Yu, Dongha Lee, Jinyoung Yeo

机构 * Yonsei University（延世大学） ； Ajou University（安江大学） 纠错

Comments Accepted to ACL 2024, Outstanding Paper

Focus on What Matters: Enhancing Medical Vision-Language Models with Automatic Attention Alignment Tuning

Aofei Chang, Le Huang, Alex James Boyd, Parminder Bhatia, Taha Kass-Hout, Cao Xiao, Fenglong Ma

Comments Accepted to ACL2025 (main)

Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systems

Hansa Meghwani, Amit Agarwal, Priyaranjan Pattnayak, Hitesh Laxmichand Patel, Srikant Panda

机构 * Oracle AI 纠错

Comments Accepted to ACL 2025

CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games

Shuhang Xu, Fangwei Zhong

Comments To Appear at ACL 2025 (Main)

DocAgent: A Multi-Agent System for Automated Code Documentation Generation

Dayu Yang, Antoine Simoulin, Xin Qian, Xiaoyi Liu, Yuwei Cao, Zhaopu Teng, Grey Yang

Comments Accepted by ACL 2025. Code: github.com/facebookresearch/DocAgent

ACECODER: Acing Coder RL via Automated Test-Case Synthesis

Huaye Zeng, Dongfu Jiang, Haozhe Wang, Ping Nie, Xiaotong Chen, Wenhu Chen

Comments 9 pages, 4 figure, 11 tables. Accepted to ACL 2025 main conference

EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents

Cheng Qian, Peixuan Han, Qinyu Luo, Bingxiang He, Xiusi Chen, Yuji Zhang, Hongyi Du, Jiarui Yao, Xiaocheng Yang, Denghui Zhang, Yunzhu Li, Heng Ji

Comments 23 pages, 15 figures, ACL 2025 Main Conference

MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models

Boyang Xue, Hongru Wang, Rui Wang, Sheng Wang, Zezhong Wang, Yiming Du, Bin Liang, Wenxuan Zhang, Kam-Fai Wong

Comments Accepted in ACL2025 Findings

EXECUTE: A Multilingual Benchmark for LLM Token Understanding

Lukas Edman, Helmut Schmid, Alexander Fraser

Comments Accepted to Findings of ACL 2025

SweEval: Do LLMs Really Swear? A Safety Benchmark for Testing Limits for Enterprise Use

Hitesh Laxmichand Patel, Amit Agarwal, Arion Das, Bhargava Kumar, Srikant Panda, Priyaranjan Pattnayak, Taki Hasan Rafi, Tejaswini Kumar, Dong-Kyu Chae

机构 * Oracle AI ； Indian Institute of Information Technology Ranchi（印度拉奇信息与技术学院） ； TD Securities（TD证券） ； Columbia University（哥伦比亚大学） ； Hanyang University（翰阳大学） 纠错

Comments Published in the Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2025), Industry Track, pages 558-582

Large Language Models for Predictive Analysis: How Far Are They?

Qin Chen, Yuanyi Ren, Xiaojun Ma, Yuyang Shi

机构 * Peking University（北京大学） ； Harvard University（哈佛大学） 纠错

Comments Accepted to ACL 2025 Findings

MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Models

Bohan Jin, Shuhan Qi, Kehai Chen, Xinyi Guo, Xuan Wang

机构 * Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）） ； Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies（广东省新型安全智能技术重点实验室） ； University of Barcelona（巴塞罗那大学） 纠错

Comments Findings of ACL 2025

Mechanistic Interpretability of GPT-like Models on Summarization Tasks

Anurag Mishra

机构 * Rochester Institute of Technology（罗切斯特技术研究所） 纠错

Comments 8 pages (6 content + 2 references/appendix), 6 figures, 2 tables; under review for the ACL 2025 Student Research Workshop

The AI Gap: How Socioeconomic Status Affects Language Technology Interactions

Elisa Bassignana, Amanda Cercas Curry, Dirk Hovy

机构 * IT University of Copenhagen（丹麦技术大学） ； CENTAI Institute（CENTAI研究所） ； Bocconi University（博科尼大学） 纠错

Comments Accepted at ACL Main 2025

ConceptCarve: Dynamic Realization of Evidence

Eylon Caplan, Dan Goldwasser

Comments Accepted to ACL 2025 Main Conference