ACL

CLaSp: In-Context Layer Skip for Self-Speculative Decoding

Longze Chen, Renke Shan, Huiming Wang, Lu Wang, Ziqiang Liu, Run Luo, Jiawei Wang, Hamid Alinejad-Rokny, Min Yang

机构 * Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学） ； Singapore University of Technology and Design（新加坡科技设计大学） ； School of Biomedical Engineering, UNSW Sydney（新南威尔士大学生物医学工程学院） 纠错

Comments 11 pages, 7 figures, ACL 2025

Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation

Ryota Miyano, Yuki Arase

机构 * Grad. Sch. of Information Science and Tech.（信息科学与技术研究生学校） ； Osaka University（大阪大学） ； School of Computing（计算学部） ； Institute of Science（科学研究所） 纠错

Comments Accepted at ACL2025 Findings

Tag-Evol: Achieving Efficient Instruction Evolving via Tag Injection

Yixuan Wang, Shiqi Zhou, Chuanzhe Guo, Qingfu Zhu

机构 * Research Center for Social Computing and Interactive Robotics（社会计算与交互机器人研究院） 纠错

Comments Accepted as Findings of ACL 2025

Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability

Chiwei Zhu, Benfeng Xu, An Yang, Junyang Lin, Quan Wang, Chang Zhou, Zhendong Mao

Comments To be published in ACL 2025 Findings. (Work originally done in Jan 2024)

Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs

Ziling Cheng, Meng Cao, Marc-Antoine Rondeau, Jackie Chi Kit Cheung

机构 * Mila – Quebec Artificial Intelligence Institute（魁北克人工智能研究所） ； McGill University（麦吉尔大学） ； Canada CIFAR AI Chair（加拿大CIFAR人工智能主席） 纠错

Comments Accepted to ACL 2025 (Main Conference)

BAR: A Backward Reasoning based Agent for Complex Minecraft Tasks

Weihong Du, Wenrui Liao, Binyu Yan, Hongru Liang, Anthony G. Cohn, Wenqiang Lei

Journal ref ACL 2025

Query-driven Document-level Scientific Evidence Extraction from Biomedical Studies

Massimiliano Pronesti, Joao Bettencourt-Silva, Paul Flanagan, Alessandra Pascale, Oisin Redmond, Anya Belz, Yufang Hou

机构 * First Author Affiliation（第一作者机构） ； Second Author Affiliation（第二作者机构） 纠错

Comments Accepted at ACL 2025 Main Conference

What's the Difference? Supporting Users in Identifying the Effects of Prompt and Model Changes Through Token Patterns

Michael A. Hedderich, Anyi Wang, Raoyuan Zhao, Florian Eichin, Jonas Fischer, Barbara Plank

机构 * MaiNLP, Center for Information and Language Processing, LMU Munich（MaiNLP，信息与语言处理中心，慕尼黑大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心） ； Department for Computer Vision and Machine Learning, Max Planck Institute for Informatics（计算机视觉与机器学习部门，马克斯·普朗克信息研究所） 纠错

Comments Accepted at ACL'25

From Misleading Queries to Accurate Answers: A Three-Stage Fine-Tuning Method for LLMs

Guocong Li, Weize Liu, Yihang Wu, Ping Wang, Shuaihan Huang, Hongxia Xu, Jian Wu

机构 * Zhejiang University（浙江大学） ； Renmin University of China（中国人民大学） ； AI Research Center, WeDoctor Cloud（WeDoctor Cloud人工智能研究中心） 纠错

Comments Accepted to ACL 2025 (Findings)

GUM-SAGE: A Novel Dataset and Approach for Graded Entity Salience Prediction

Jessica Lin, Amir Zeldes

机构 * Department of Linguistics（语言学系） ； Georgetown University（乔治城大学） 纠错

Comments Camera-ready for ACL Findings 2025

Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models

Adrián Bazaga, Rexhina Blloshmi, Bill Byrne, Adrià de Gispert

机构 * University of Cambridge（剑桥大学） ； Amazon AGI（亚马逊人工智能研究院） 纠错

Comments ACL 2025 (Main)

LEMMA: Learning from Errors for MatheMatical Advancement in LLMs

Zhuoshi Pan, Yu Li, Honglin Lin, Qizhi Pei, Zinan Tang, Wei Wu, Chenlin Ming, H. Vicky Zhao, Conghui He, Lijun Wu

机构 * Tsinghua University（清华大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； Renmin University of China（中国人民大学） ； University of Science and Technology of China（中国科学技术大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

Comments ACL'25 Findings, Code is available at https://github.com/pzs19/LEMMA

TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship Classification

Junnan Zhu, Min Xiao, Yining Wang, Feifei Zhai, Yu Zhou, Chengqing Zong

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS（多模态人工智能系统国家重点实验室，自动化研究所） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； Fanyu AI Laboratory, Zhongke Fanyu Technology Co., Ltd（中科创始人工智能实验室，中科创始科技有限公司） 纠错

Comments To appear in ACL 2025 (Main)

HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks

Zhilin Wang, Jiaqi Zeng, Olivier Delalleau, Daniel Egert, Ellie Evans, Hoo-Chang Shin, Felipe Soares, Yi Dong, Oleksii Kuchaiev

机构 * NVIDIA 纠错

Comments 23 pages, 2 figures, Accepted to ACL 2025 Main

Vision-Language Models Struggle to Align Entities across Modalities

Iñigo Alonso, Gorka Azkune, Ander Salaberria, Jeremy Barnes, Oier Lopez de Lacalle

机构 * School of Informatics, The University of Edinburgh（信息学院，爱丁堡大学） ； HiTZ Center - Ixa, University of the Basque Country UPV/EHU（巴斯克国家大学HiTZ中心） 纠错

Comments Accepted Findings ACL 2025

SwiLTra-Bench: The Swiss Legal Translation Benchmark

Joel Niklaus, Jakob Merane, Luka Nenadic, Sina Ahmadi, Yingqiang Gao, Cyrill A. H. Chevalley, Claude Humbel, Christophe Gösken, Lorenzo Tanzi, Thomas Lüthi, Stefan Palombo, Spencer Poff, Boling Yang, Nan Wu, Matthew Guillod, Robin Mamié, Daniel Brunner, Julio Pereyra, Niko Grupen

Comments Accepted at ACL main 2025

Do Language Models Understand Honorific Systems in Javanese?

Mohammad Rifqi Farhansyah, Iwan Darmawan, Adryan Kusumawardhana, Genta Indra Winata, Alham Fikri Aji, Derry Tanti Wijaya

机构 * Institut Teknologi Bandung（技术科技大学） ； Monash Indonesia（莫纳什印尼分校） ； Boston University（波士顿大学） ； Capital One ； MBZUAI 纠错

Comments ACL 2025 - Main Conference

Recurrent Knowledge Identification and Fusion for Language Model Continual Learning

Yujie Feng, Xujia Wang, Zexin Lu, Shenghong Fu, Guangyuan Shi, Yongxin Xu, Yasha Wang, Philip S. Yu, Xu Chu, Xiao-Ming Wu

机构 * The Hong Kong Polytechnic University（香港理工大学） ； Tsinghua University（清华大学） ； Peking University（北京大学） ； University of Illinois at Chicago（伊利诺伊大学香槟分校） 纠错

Comments Accepted to ACL 2025 (Main Conference)

StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following

Jinnan Li, Jinzhe Li, Yue Wang, Yi Chang, Yuan Wu

机构 * School of Artificial Intelligence, Jilin University（吉林大学人工智能学院） ； College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院） ； School of Information and Library Science, University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校信息与图书馆科学学院） ； Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, China（知识驱动的人机智能工程研究中心，教育部，中国） ； International Center of Future Science, Jilin University（未来科学国际中心，吉林大学） 纠错

Comments ACL 2025 Findings camera-ready version

You need to MIMIC to get FAME: Solving Meeting Transcript Scarcity with a Multi-Agent Conversations

Frederic Kirstein, Muneeb Khan, Jan Philip Wahle, Terry Ruas, Bela Gipp

机构 * University of Göttingen（哥廷根大学） 纠错

Comments Accepted at ACL 2025 (Findings)

Journal ref ACL 2025 (Findings)

MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training

Hui Huang, Jiaheng Liu, Yancheng He, Shilong Li, Bing Xu, Conghui Zhu, Muyun Yang, Tiejun Zhao

机构 * Faculty of Computing, Harbin Institute of Technology（哈尔滨工业大学计算机学院） ； Nanjing University（南京大学） ； School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院） 纠错

Comments Accepted to ACL2025

GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion

Kangyang Luo, Yuzhuo Bai, Cheng Gao, Shuzheng Si, Yingli Shen, Zhu Liu, Zhitong Wang, Cunliang Kong, Wenhao Li, Yufei Huang, Ye Tian, Xuantang Xiong, Lei Han, Maosong Sun

机构 * Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） ； Institute for AI, Tsinghua University（清华大学人工智能研究院） ； Tencent Robotics X（腾讯机器人X） ； Jiangsu Collaborative Innovation Center for Language Ability（江苏省语言能力协同创新中心） 纠错

Comments Accepted by ACL2025(Findings)

ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models

Hanxing Ding, Shuchang Tao, Liang Pang, Zihao Wei, Jinyang Gao, Bolin Ding, Huawei Shen, Xueqi Cheng

机构 * State Key Laboratory of AI Safety, Institute of Computing Technology, CAS（人工智能安全国家重点实验室，计算技术研究所，中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学） ； Alibaba Group（阿里巴巴集团） 纠错

Comments Accepted to ACL 2025

Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents

Vardaan Pahuja, Yadong Lu, Corby Rosset, Boyu Gou, Arindam Mitra, Spencer Whitehead, Yu Su, Ahmed Awadallah

机构 * The Ohio State University（俄亥俄州立大学） ； Microsoft Research（微软研究院） 纠错

Comments ACL 2025 (Findings)

Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction

Yuting Huang, Chengyuan Liu, Yifeng Feng, Yiquan Wu, Chao Wu, Fei Wu, Kun Kuang

机构 * Zhejiang University（浙江大学） 纠错

Comments 22 pages, 10 figures, accepted to ACL 2025 findings

RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs

Hongliang Li, Jiaxin Zhang, Wenhui Liao, Dezhi Peng, Kai Ding, Lianwen Jin

机构 * South China University of Technology（华南理工大学） ； Intsig Information Co., Ltd.（Intsig信息有限公司） ； INTSIG-SCUT Joint Lab on Document Analysis and Recognition（INTSIG-SCUT文档分析与识别联合实验室） 纠错

Comments ACL 2025 Findings

GeAR: Generation Augmented Retrieval

Haoyu Liu, Shaohan Huang, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Furu Wei, Qi Zhang

机构 * Microsoft Corporation（微软公司） 纠错

Comments In ACL 2025

A Rose by Any Other Name: LLM-Generated Explanations Are Good Proxies for Human Explanations to Collect Label Distributions on NLI

Beiduo Chen, Siyao Peng, Anna Korhonen, Barbara Plank

机构 * MaiNLP, Center for Information and Language Processing, LMU Munich, Germany（MaiNLP，信息与语言处理中心，慕尼黑大学，德国） ； Munich Center for Machine Learning (MCML), Munich, Germany（慕尼黑机器学习中心（MCML），慕尼黑，德国） ； Language Technology Lab, University of Cambridge, United Kingdom（语言技术实验室，剑桥大学，英国） 纠错

Comments Accepted by ACL 2025 Findings, 25 pages, 21 figures

FCMR: Robust Evaluation of Financial Cross-Modal Multi-Hop Reasoning

Seunghee Kim, Changhyeon Kim, Taeuk Kim

机构 * Hanyang University（翰阳大学） 纠错

Comments ACL 2025

RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios

Ruiwen Zhou, Wenyue Hua, Liangming Pan, Sitao Cheng, Xiaobao Wu, En Yu, William Yang Wang

机构 * University of California, Santa Barbara（加州大学圣芭芭拉分校） ； University of Arizona（亚利桑那大学） ； Nanyang Technological University（南洋理工大学） 纠错

Comments ACL 2025 Main Conference