ACL

Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step

Wenxuan Wang, Kuiyi Gao, Youliang Yuan, Jen-tse Huang, Qiuzhi Liu, Shuai Wang, Wenxiang Jiao, Zhaopeng Tu

机构 * Renmin University of China（中国人民大学） ； Chinese University of Hong Kong（香港大学） ； Chinese University of Hong Kong, Shenzhen（香港大学（深圳）） ； Johns Hopkins University（约翰霍普金斯大学） ； Tencent（腾讯） ； Hong Kong University of Science and Technology（香港科技大学） 纠错

Comments Accepted by ACL 2025 Findings

It's Not a Walk in the Park! Challenges of Idiom Translation in Speech-to-text Systems

Iuliia Zaitova, Badr M. Abdullah, Wei Xue, Dietrich Klakow, Bernd Möbius, Tania Avgustinova

机构 * Saarland University（萨尔兰大学） ； Xi’an Jiaotong University（西安交通大学） 纠错

Comments 13 pages, 3 figures, ACL 2025

IMPARA-GED: Grammatical Error Detection is Boosting Reference-free Grammatical Error Quality Estimator

Yusuke Sakai, Takumi Goto, Taro Watanabe

机构 * Nara Institute of Science and Technology（奈良科学技术大学） 纠错

Comments ACL 2025 Findings

ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations

Ekaterina Grishina, Mikhail Gorbunov, Maxim Rakhuba

机构 * HSE University（俄罗斯高等经济大学） 纠错

Comments Accepted by ACL Findings

Open-Set Living Need Prediction with Large Language Models

Xiaochong Lan, Jie Feng, Yizhou Sun, Chen Gao, Jiahuan Lei, Xinlei Shi, Hengliang Luo, Yong Li

机构 * Department of Electronic Engineering, BNRist, Tsinghua University（电子工程系，BNRist，清华大学） 纠错

Comments ACL 2025 Findings

On Generalization across Measurement Systems: LLMs Entail More Test-Time Compute for Underrepresented Cultures

Minh Duc Bui, Kyung Eun Park, Goran Glavaš, Fabian David Schmidt, Katharina von der Wense

机构 * Johannes Gutenberg University Mainz（明斯特-雅各布大学） ； University of Mannheim（曼海姆大学） ； Center For Artificial Intelligence and Data Science, University of Würzburg（乌尔姆大学人工智能与数据科学中心） ； University of Colorado Boulder（科罗拉多大学博尔德分校） 纠错

Comments Accepted to ACL 2025 Main (Camera-Ready Version)

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference

Ping Gong, Jiawei Yi, Shengnan Wang, Juncheng Zhang, Zewen Jin, Ouxiang Zhou, Ruibo Liu, Guanbin Xu, Youhui Bai, Bowen Ye, Kun Yuan, Tong Yang, Gong Zhang, Renhai Chen, Feng Wu, Cheng Li

机构 * University of Science and Technology of China（中国科学技术大学） ； Institute of Artificial Intelligence（人工智能研究院） ； Hefei Comprehensive National Science Center（合肥综合性国家科学中心） ； Huawei Technologies（华为技术有限公司） ； Peking University（北京大学） 纠错

Comments ACL 2025 findings

Towards Generating Controllable and Solvable Geometry Problem by Leveraging Symbolic Deduction Engine

Zhuoxuan Jiang, Tianyang Zhang, Peiyan Peng, Jing Chen, Yinong Xun, Haotian Zhang, Lichi Li, Yong Li, Shaohua Zhang

机构 * Shanghai Business School（上海商学院） ； Shanghai Jiaotong University（上海交通大学） ； Cisco Systems Inc.（思科系统公司） ； Beijing Shangruitong Education Technology Co., Ltd.（北京尚润通教育科技有限公司） 纠错

Comments To Appear in ACL'25

ReasoningFlow: Semantic Structure of Complex Reasoning Traces

Jinu Lee, Sagnik Mukherjee, Dilek Hakkani-Tur, Julia Hockenmaier

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

Comments 10 pages, 6 figures. ArgMining 2025 Workshop (Non-archival) @ ACL 2025

Learning Together to Perform Better: Teaching Small-Scale LLMs to Collaborate via Preferential Rationale Tuning

Sohan Patnaik, Milan Aggarwal, Sumit Bhatia, Balaji Krishnamurthy

Comments Accepted at ACL Main 2025

SingaKids: A Multilingual Multimodal Dialogic Tutor for Language Learning

Zhengyuan Liu, Geyu Lin, Hui Li Tan, Huayun Zhang, Yanfeng Lu, Xiaoxue Gao, Stella Xin Yin, He Sun, Hock Huan Goh, Lung Hsiang Wong, Nancy F. Chen

机构 * Nanyang Technological University, Singapore（新加坡南洋理工大学） ； National Institute of Education (NIE), Singapore（新加坡国家教育研究所） ； Institute for Infocomm Research (I 2 R), A*STAR, Singapore（新加坡资讯与通信研究院（I2R）） 纠错

Comments ACL 2025 Industry Track

Consultant Decoding: Yet Another Synergistic Mechanism

Chuanghao Ding, Jiaping Wang, Ziqing Yang, Xiaoliang Wang, Dahua Lin, Cam-Tu Nguyen, Fei Tan

机构 * State Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室，南京大学） ； East China Normal University（华东师范大学） ； The Chinese University of Hong Kong（香港中文大学） 纠错

Comments ACL 2025 findings

Exploring Explanations Improves the Robustness of In-Context Learning

Ukyo Honda, Tatsushi Oka

机构 * CyberAgent ； Keio University（庆应大学） 纠错

Comments Accepted to ACL 2025 (Main Conference)

RATE-Nav: Region-Aware Termination Enhancement for Zero-shot Object Navigation with Vision-Language Models

Junjie Li, Nan Zhang, Xiaoyang Qu, Kai Lu, Guokuan Li, Jiguang Wan, Jianzong Wang

机构 * Huazhong University of Science and Technology（华中科技大学） ； Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司） 纠错

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

DIAMOND: An LLM-Driven Agent for Context-Aware Baseball Highlight Summarization

Jeonghun Kang, Soonmok Kwon, Joonseok Lee, Byung-Hak Kim

机构 * Seoul National University（首尔国立大学） ； CJ Corporation（CJ公司） 纠错

Comments To appear in the First REALM (Research on Agent Language Models) workshop at ACL 2025

One Missing Piece for Open-Source Reasoning Models: A Dataset to Mitigate Cold-Starting Short CoT LLMs in RL

Hyungjoo Chae, Dongjin Kang, Jihyuk Kim, Beong-woo Kwak, Sunghyun Park, Haeju Park, Jinyoung Yeo, Moontae Lee, Kyungjae Lee

机构 * Yonsei University（延世大学） ； LG AI Research（LG AI研究） ； University of Illinois Chicago（伊利诺伊大学芝加哥分校） 纠错

Comments ACL 2025 Industry

Explain-then-Process: Using Grammar Prompting to Enhance Grammatical Acceptability Judgments

Russell Scheinberg, Ameeta Agrawal, Amber Shore, So Young Lee

机构 * Portland State University（波特兰州立大学） ； Miami University（迈阿密大学） 纠错

Comments Accepted at ACL 2025 Findings

Different Speech Translation Models Encode and Translate Speaker Gender Differently

Dennis Fucci, Marco Gaido, Matteo Negri, Luisa Bentivogli, Andre Martins, Giuseppe Attanasio

机构 * University of Trento（特伦托大学） ； Fondazione Bruno Kessler（布鲁诺·克塞勒基金会） ； Unbabel ； Instituto Superior Técnico（技术高级学院） ； Instituto de Telecomunicações（电信研究所） 纠错

Comments Accepted at ACL 2025

Assigning Distinct Roles to Quantized and Low-Rank Matrices Toward Optimal Weight Decomposition

Yoonjun Cho, Soeun Kim, Dongjae Jeon, Kyelim Lee, Beomsoo Lee, Albert No

机构 * Department of Computer Science, Yonsei University（yonsei大学计算机科学系） ； Department of Artificial Intelligence, Yonsei University（yonsei大学人工智能系） ； Department of Electronic & Electrical Convergence Engineering, Hongik University（hongik大学电子与电气融合工程系） 纠错

Comments Accepted to Findings of ACL 2025

Enhancing Multimodal Continual Instruction Tuning with BranchLoRA

Duzhen Zhang, Yong Ren, Zhong-Zhi Li, Yahan Yu, Jiahua Dong, Chenxing Li, Zhilong Ji, Jinfeng Bai

机构 * Mohamed bin Zayed University of Artificial Intelligence（Mohamed bin Zayed大学人工智能学院） ； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； Kyoto University（京都大学） ； Tencent AI Lab（腾讯AI实验室） ； Tomorrow Advancing Life（明天生命科技） 纠错

Comments Accepted by ACL2025 Main Conference

MaXIFE: Multilingual and Cross-lingual Instruction Following Evaluation

Yile Liu, Ziwei Ma, Xiu Jiang, Jinglu Hu, Jing Chang, Liang Li

Comments ACL 2025 Main Conference

STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework

Wenhao Liu, Zhenyi Lu, Xinyu Hu, Jierui Zhang, Dailin Li, Jiacheng Cen, Huilin Cao, Haiteng Wang, Yuhan Li, Kun Xie, Dandan Li, Pei Zhang, Chengbo Zhang, Yuxiang Ren, Xiaohong Huang, Yan Ma

Comments accepted by ACL2025

COMPKE: Complex Question Answering under Knowledge Editing

Keyuan Cheng, Zijian Kan, Zhixian He, Zhuoran Zhang, Muhammad Asif Ali, Ke Xu, Lijie Hu, Di Wang

机构 * Provable Responsible AI and Data Analytics (PRADA) Lab（可证明负责任的人工智能与数据分析实验室） ； King Abdullah University of Science and Technology（卡布斯大学） ； Peking University（北京大学） ； South China University of Technology（华南理工大学） ； Sun Yat-sen University（中山大学） 纠错

Comments Accepted by ACL 2025 Findings

Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models

Boheng Sheng, Jiacheng Yao, Meicong Zhang, Guoxiu He

机构 * East China Normal University（华东师范大学） 纠错

Comments Accepted by ACL 2025 Main Conference

Improving Dialogue State Tracking through Combinatorial Search for In-Context Examples

Haesung Pyun, Yoonah Park, Yohan Jo

机构 * Graduate School of Data Science, Seoul National University（数据科学研究生院，首尔国立大学） ； Department of Computer Science and Engineering, Seoul National University（计算机科学与工程系，首尔国立大学） 纠错

Comments This paper has been accepted for publication at ACL 2025

CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention

Yuxi Sun, Aoqi Zuo, Wei Gao, Jing Ma

机构 * Department of Computer Science, Hong Kong Baptist University（香港 Baptist 大学计算机科学系） ； School of Mathematics and Statistics, The University of Melbourne（墨尔本大学数学与统计学学院） ； School of Computing and Information Systems, Singapore Management University（新加坡管理大学计算与信息系统学院） 纠错

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

Transforming Podcast Preview Generation: From Expert Models to LLM-Based Systems

Winstead Zhu, Ann Clifton, Azin Ghazimatin, Edgar Tanaka, Edward Ronan

Comments 9 pages, 2 figures, accepted at ACL 2025 Industry Track

Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms

Mengru Wang, Ziwen Xu, Shengyu Mao, Shumin Deng, Zhaopeng Tu, Huajun Chen, Ningyu Zhang

机构 * Zhejiang University（浙江大学） ； Tencent（腾讯） ； National University of Singapore（新加坡国立大学） ； NUS-NCS Joint Lab（新加坡国立大学NCS联合实验室） 纠错

Comments ACL 2025

HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation

Jinyu Guo, Xunlei Chen, Qiyang Xia, Zhaokun Wang, Jie Ou, Libo Qin, Shunyu Yao, Wenhong Tian

Comments Accepted at Findings of ACL 2025

Multi-Hop Question Generation via Dual-Perspective Keyword Guidance

Maodong Li, Longyin Zhang, Fang Kong

机构 * School of Computer Science and Technology, Soochow University, China（苏州大学计算机科学与技术学院） ； Institute for Infocomm Research, A*STAR, Singapore（新加坡*STAR信息通信研究所） 纠错

Comments 17 pages, 5 figures, accepted to the Findings of ACL 2025