ACL

What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices

Zhi Chen, Qiguang Chen, Libo Qin, Qipeng Guo, Haijun Lv, Yicheng Zou, Wanxiang Che, Hang Yan, Kai Chen, Dahua Lin

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Research Center for Social Computing and Interactive Robotics（社会计算与交互机器人研究中心） ； Harbin Institute of Technology（哈尔滨工业大学） ； School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院） 纠错

Comments ACL 2025 Camera Ready. Code is available at: https://github.com/WowCZ/LongMIT

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

Mengzhao Chen, Wenqi Shao, Peng Xu, Jiahao Wang, Peng Gao, Kaipeng Zhang, Ping Luo

机构 * The University of Hong Kong（香港大学） ； Shanghai AI Laboratory（上海人工智能实验室） 纠错

Comments ACL 2025 Main, camera ready version

A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding

Jinghui Lu, Haiyang Yu, Yanjie Wang, Yongjie Ye, Jingqun Tang, Ziwei Yang, Binghong Wu, Qi Liu, Hao Feng, Han Wang, Hao Liu, Can Huang

机构 * ByteDance Inc.（字节跳动公司） ； Fudan University（复旦大学） 纠错

Comments Accept to ACL2025 Findings

Task Facet Learning: A Structured Approach to Prompt Optimization

Gurusha Juneja, Gautam Jajoo, Nagarajan Natarajan, Hua Li, Jian Jiao, Amit Sharma

机构 * UC Santa Barbara（加州大学圣芭芭拉分校） ； BITS Pilani（比哈尔理工学院） ； Microsoft Research（微软研究院） ； Microsoft Bing Ads（微软Bing广告） 纠错

Comments Appearing in ACL Findings 2025

From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets

Manuel Tonneau, Diyi Liu, Samuel Fraiberger, Ralph Schroeder, Scott A. Hale, Paul Röttger

机构 * University of Oxford（牛津大学） ； World Bank（世界银行） ； New York University（纽约大学） ； Massachusetts Institute of Technology（麻省理工学院） ； Meedan ； Bocconi University（博科尼大学） 纠错

Comments Accepted at WOAH (NAACL 2024). Please cite the ACL Anthology version: https://aclanthology.org/2024.woah-1.23/

Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing

Jiakuan Xie, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

机构 * School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所认知与决策智能复杂系统实验室） 纠错

Comments Accepted by ACL 2025 main

Chain-Talker: Chain Understanding and Rendering for Empathetic Conversational Speech Synthesis

Yifan Hu, Rui Liu, Yi Ren, Xiang Yin, Haizhou Li

机构 * Inner Mongolia University（内蒙古大学） ； ByteDance（字节跳动） ； SRIBD, School of Data Science, The Chinese University of Hong Kong, Shenzhen（SRIBD，数据科学学院，香港中文大学（深圳）） 纠错

Comments 16 pages, 5 figures, 5 tables. Accepted by ACL 2025 (Findings)

SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignment

Wenqiao Zhu, Ji Liu, Lulu Wang, Jun Wu, Yulun Zhang

Comments 18 pages, to appear in ACL'25

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement

Peng Ding, Jun Kuang, Zongyu Wang, Xuezhi Cao, Xunliang Cai, Jiajun Chen, Shujian Huang

机构 * National Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室） ； Meituan Inc., China（美团公司） 纠错

Comments Acccepted by ACL 2025 Findings, 21 pages, 9 figures, 14 tables

Towards Comprehensive Argument Analysis in Education: Dataset, Tasks, and Method

Yupei Ren, Xinyi Zhou, Ning Zhang, Shangqing Zhao, Man Lan, Xiaopeng Bai

机构 * Lab of Artificial Intelligence for Education, East China Normal University（教育人工智能实验室，华东师范大学） ； Shanghai Institute of Artificial Intelligence for Education, East China Normal University（教育人工智能上海研究院，华东师范大学） ； School of Computer Science and Technology, East China Normal University（计算机科学与技术学院，华东师范大学） ； Department of Chinese Language and Literature, East China Normal University（中文语言文学系，华东师范大学） ； College of Education, Zhejiang University（教育学院，浙江大学） 纠错

Comments Accepted to ACL 2025; 13 pages, 3 figures

Neuro-Symbolic Query Compiler

Yuyao Zhang, Zhicheng Dou, Xiaoxi Li, Jiajie Jin, Yongkang Wu, Zhonghua Li, Qi Ye, Ji-Rong Wen

机构 * Renmin University of China（中国人民大学） ； Huawei Poisson Lab（华为Poisson实验室） 纠错

Comments Findings of ACL2025, codes are available at this url: https://github.com/YuyaoZhangQAQ/Query_Compiler

Recursive Question Understanding for Complex Question Answering over Heterogeneous Personal Data

Philipp Christmann, Gerhard Weikum

机构 * Max Planck Institute for Informatics（马克斯·普朗克研究所信息学研究所） 纠错

Comments Accepted at ACL 2025 (Findings)

AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting

Yang Xiao, Tianyi Peng, Rohan Kumar Das, Yuchen Hu, Huiping Zhuang

机构 * The University of Melbourne（墨尔本大学） ； Fortemedia Singapore（Fortemedia新加坡） ； Nanyang Technological University（南洋理工大学） ； South China University of Technology（华南理工大学） 纠错

Comments Accepted by ACL 2025

BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering

Taolin Zhang, Dongyang Li, Qizhou Chen, Chengyu Wang, Xiaofeng He

机构 * School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机科学与信息工程学院） ； Shanghai University of Electric Power（上海电力大学） ； Alibaba Group（阿里巴巴集团） ； East China Normal University（华东师范大学） 纠错

Comments Accepted by ACL2025 main track

Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation

Wenyu Huang, Pavlos Vougiouklis, Mirella Lapata, Jeff Z. Pan

机构 * School of Informatics, University of Edinburgh（信息学院，爱丁堡大学） ； Huawei Edinburgh Research Centre, Poisson Lab, CSI, UK（华为爱丁堡研究中心，波isson实验室，CSI，英国） 纠错

Comments ACL 2025 main

Evaluating Design Decisions for Dual Encoder-based Entity Disambiguation

Susanna Rücker, Alan Akbik

机构 * Humboldt-Universität zu Berlin（柏林洪堡大学） 纠错

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

Trans-Zero: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data

Wei Zou, Sen Yang, Yu Bao, Shujian Huang, Jiajun Chen, Shanbo Cheng

机构 * National Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家实验室，南京大学） ； ByteDance Research（字节跳动研究） 纠错

Comments 11 pages, 4 figures, accepted by ACL 2025 as findings

DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation

Hanghui Guo, Jia Zhu, Shimin Di, Weijie Shi, Zhangze Chen, Jiajie Xu

机构 * Zhejiang Key Laboratory of Intelligent Education Technology and Application, Zhejiang Normal University（浙江智能教育技术与应用重点实验室，浙江师范大学） ； School of Computer Science and Technology, Zhejiang Normal University（浙江师范大学计算机科学与技术学院） ； School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院） ； Department of Computer Science and Engineering, Hong Kong University of Science and Technology（香港科技大学计算机科学与工程系） ； School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院） 纠错

Comments Accepted to ACL2025 Main

MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment

Weicong Qin, Yi Xu, Weijie Yu, Chenglei Shen, Ming He, Jianping Fan, Xiao Zhang, Jun Xu

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院） ； University of International Business and Economics（国际商务经济大学） ； AI Lab at Lenovo Research, Lenovo Group Limited（联想集团研究院人工智能实验室） 纠错

Comments accepted to ACL 2025 main conference

VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation

Xinlong Chen, Yuanxing Zhang, Chongling Rao, Yushuo Guan, Jiaheng Liu, Fuzheng Zhang, Chengru Song, Qiang Liu, Di Zhang, Tieniu Tan

机构 * New Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA)（模式识别新技术实验室，自动化研究所，中国科学院（CASIA）） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； Kuaishou Technology（快手科技） ； Nanjing University（南京大学） 纠错

Comments Accepted to Findings of ACL 2025

CLaMP 3: Universal Music Information Retrieval Across Unaligned Modalities and Unseen Languages

Shangda Wu, Zhancheng Guo, Ruibin Yuan, Junyan Jiang, Seungheon Doh, Gus Xia, Juhan Nam, Xiaobing Li, Feng Yu, Maosong Sun

机构 * Page 9（页面9） 纠错

Comments 20 pages, 8 figures, 12 tables, accepted by ACL 2025

Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement

Junyu Lu, Kai Ma, Kaichun Wang, Kelaiti Xiao, Roy Ka-Wei Lee, Bo Xu, Liang Yang, Hongfei Lin

机构 * Key Laboratory of Social Computing and Cognitive Intelligence, Dalian University of Technology（大连理工大学社会计算与认知智能重点实验室） ； School of Computer Science and Technology, Xinjiang Normal University（新疆师范大学计算机科学与技术学院） ； Social AI Studio, Singapore University of Technology and Design（新加坡科技设计大学社会AI工作室） 纠错

Comments 18 pages, accepted at the ACL 2025

VLSBench: Unveiling Visual Leakage in Multimodal Safety

Xuhao Hu, Dongrui Liu, Hao Li, Xuanjing Huang, Jing Shao

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Fudan University（复旦大学） ； Beihang University（北京航空航天大学） 纠错

Comments ACL2025 Main

CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution

Ruiyang Xu, Jialun Cao, Yaojie Lu, Ming Wen, Hongyu Lin, Xianpei Han, Ben He, Shing-Chi Cheung, Le Sun

机构 * Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所信息处理实验室） ； University of Chinese Academy of Sciences（中国科学院大学） ； The Hong Kong University of Science and Technology（香港科技大学） ； Huazhong University of Science and Technology（华中科技大学） 纠错

Comments 18pages, Accepted to ACL 2025 Main Conference

DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoising

Zhenhao Li, Huichi Zhou, Marek Rei, Lucia Specia

机构 * Language and Multimodal AI (LAMA) Lab（语言与多模态AI实验室） 纠错

Comments Accepted to ACL 2025

On the Role of Speech Data in Reducing Toxicity Detection Bias

Samuel J. Bell, Mariano Coria Meglioli, Megan Richards, Eduardo Sánchez, Christophe Ropers, Skyler Wang, Adina Williams, Levent Sagun, Marta R. Costa-jussà

机构 * Meta FAIR ； New York University（纽约大学） ； University College London（伦敦大学学院） ； McGill University（麦吉尔大学） 纠错

Comments Accepted at NAACL 2025

Journal ref In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (Volume 1), pages 1454-1468

Can Authorship Attribution Models Distinguish Speakers in Speech Transcripts?

Cristina Aggazzotti, Nicholas Andrews, Elizabeth Allyn Smith

机构 * Johns Hopkins University（约翰霍普金斯大学） ； Université du Québec à Montréal（魁北克大学蒙特利尔分校） 纠错

Comments Published in Transactions of the Association for Computational Linguistics; 1st revision includes additional experiments and evaluations; 2nd revision includes minor tweak to TFIDF table numbers

Towards Better Evaluation for Generated Patent Claims

Lekang Jiang, Pascal A Scherz, Stephan Goetz

机构 * University of Cambridge（剑桥大学） 纠错

Comments Accepted to ACL 2025. 14 pages, 8 tables

Accurate KV Cache Quantization with Outlier Tokens Tracing

Yi Su, Yuechi Zhou, Quantong Qiu, Juntao Li, Qingrong Xia, Ping Li, Xinyu Duan, Zhefeng Wang, Min Zhang

机构 * School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院） ； Key Laboratory of Data Intelligence and Advanced Computing, Soochow University（苏州大学数据智能与先进计算重点实验室） ； Huawei Cloud（华为云） 纠错

Comments ACL2025 Main

Improve Rule Retrieval and Reasoning with Self-Induction and Relevance ReEstimate

Ziyang Huang, Wangtao Sun, Jun Zhao, Kang Liu

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； University of Chinese Academy of Sciences（中国科学院大学） 纠错

Comments ACL 2025