ACL

InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning

Zifu Wan, Yaqi Xie, Ce Zhang, Zhiqiu Lin, Zihan Wang, Simon Stepputtis, Deva Ramanan, Katia Sycara

机构 * Robotics Institute, Carnegie Mellon University（机器人研究所，卡内基梅隆大学） 纠错

Comments Accepted by ACL 2025 Main. Project page: https://zifuwan.github.io/InstructPart/

TransBench: Breaking Barriers for Transferable Graphical User Interface Agents in Dynamic Digital Environments

Yuheng Lu, Qian Yu, Hongru Wang, Zeming Liu, Wei Su, Yanping Liu, Yuhang Guo, Maocheng Liang, Yunhong Wang, Haifeng Wang

机构 * Beihang University（北京航空航天大学） ； The Chinese University of Hong Kong（香港中文大学） ； Beijing Institute of Technology（北京理工大学） ； Baidu Inc.（百度公司） 纠错

Comments Accepted by ACL 2025 Findings

Systematic Generalization in Language Models Scales with Information Entropy

Sondre Wold, Lucas Georges Gabriel Charpentier, Étienne Simon

机构 * Language Technology Group University of Oslo（奥斯陆大学语言技术组） 纠错

Comments Accepted to ACL 2025: Findings

Retrospex: Language Agent Meets Offline Reinforcement Learning Critic

Yufei Xiang, Yiqun Shen, Yeqin Zhang, Cam-Tu Nguyen

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） ； Nanjing University School of Artificial Intelligence（南京大学人工智能学院） 纠错

Comments 17 pages, Published in EMNLP 2024 (Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing)

Journal ref Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 4650-4666, ACL Anthology, 2024

Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders

Boyi Deng, Yu Wan, Yidan Zhang, Baosong Yang, Fuli Feng

机构 * University of Science and Technology of China（中国科学技术大学） ； Sichuan University（四川大学） 纠错

Comments ACL 2025 main

Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs

Weixiang Zhao, Yulin Hu, Yang Deng, Jiahe Guo, Xingyu Sui, Xinyang Han, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

机构 * Harbin Institute of Technology（哈尔滨工业大学） ； Singapore Management University（新加坡管理大学） ； National University of Singapore（国立新加坡大学） 纠错

Comments To appear at ACL 2025 (Main)

Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases

Michael Y. Hu, Jackson Petty, Chuan Shi, William Merrill, Tal Linzen

机构 * Center for Data Science（数据科学中心） ； Department of Linguistics（语言学系） 纠错

Comments ACL 2025 Camera Ready

Learning to Align Multi-Faceted Evaluation: A Unified and Robust Framework

Kaishuai Xu, Tiezheng Yu, Wenjun Hou, Yi Cheng, Liangyou Li, Xin Jiang, Lifeng Shang, Qun Liu, Wenjie Li

机构 * The Hong Kong Polytechnic University（香港理工大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

Comments accepted as ACL 2025 findings

Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning

Xinghao Chen, Zhijing Sun, Wenjin Guo, Miaoran Zhang, Yanjun Chen, Yirong Sun, Hui Su, Yijie Pan, Dietrich Klakow, Wenjie Li, Xiaoyu Shen

机构 * Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算机系） ； Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative（宁波空间智能与数字衍生关键实验室） ； Institute of Digital Twin, EIT（数字孪生研究院） ； Saarland University（萨尔兰大学） ； Meituan Inc.（美团公司） 纠错

Comments ACL 2025 Findings

Predicting Through Generation: Why Generation Is Better for Prediction

Md Kowsher, Nusrat Jahan Prottasha, Prakash Bhat, Chun-Nam Yu, Mojtaba Soltanalian, Ivan Garibay, Ozlem Garibay, Chen Chen, Niloofar Yousefi

机构 * University of Central Florida（佛罗里达中央大学） ； DotStar Inc（DotStar公司） ； Nokia Bell Labs（诺基亚贝尔实验室） ； University of Illinois Chicago（伊利诺伊大学香槟分校） 纠错

Comments ACL Accepted paper

Behavioral Analysis of Information Salience in Large Language Models

Jan Trienes, Jörg Schlötterer, Junyi Jessy Li, Christin Seifert

Comments Accepted at ACL 2025 (Findings)

Can Community Notes Replace Professional Fact-Checkers?

Nadav Borenstein, Greta Warren, Desmond Elliott, Isabelle Augenstein

机构 * University of Copenhagen（哥本哈根大学） 纠错

Comments Accepted to the main proceedings of ACL 2025

Task-Informed Anti-Curriculum by Masking Improves Downstream Performance on Text

Andrei Jarca, Florinel Alin Croitoru, Radu Tudor Ionescu

机构 * University of Bucharest（布加勒斯特大学） 纠错

Comments Accepted at ACL 2025

SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs

Yige Xu, Xu Guo, Zhiwei Zeng, Chunyan Miao

机构 * Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly（联合NTU-UBC老年人积极生活卓越研究中心） ； College of Computing and Data Science（计算与数据科学学院） 纠错

Comments Camera-ready for ACL 2025 (main conference)

MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models

Jiahao Huo, Yibo Yan, Xu Zheng, Yuanhuiyi Lyu, Xin Zou, Zhihua Wei, Xuming Hu

Comments Accepted as ACL 2025 Findings

ProgCo: Program Helps Self-Correction of Large Language Models

Xiaoshuai Song, Yanan Wu, Weixun Wang, Jiaheng Liu, Wenbo Su, Bo Zheng

Comments Accpeted at ACL2025 Main

Knowledge Boundary of Large Language Models: A Survey

Moxin Li, Yong Zhao, Wenxuan Zhang, Shuaiyi Li, Wenya Xie, See-Kiong Ng, Tat-Seng Chua, Yang Deng

机构 * National University of Singapore（国立新加坡大学） ； Singapore Management University（新加坡管理大学） ； Singapore University of Technology and Design（新加坡科技设计大学） ； The Chinese University of Hong Kong（香港中文大学） ； University of Minnesota - Twin Cities（明尼苏达大学双城分校） 纠错

Comments Accepted to ACL 2025 (main)

DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization

Hexuan Deng, Wenxiang Jiao, Xuebo Liu, Jing Li, Min Zhang, Zhaopeng Tu

机构 * Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China（计算与智能研究院，哈尔滨工业大学深圳校区） 纠错

Comments Accepted by ACL 2025 Main Conference

Efficient and Accurate Prompt Optimization: the Benefit of Memory in Exemplar-Guided Reflection

Cilin Yan, Jingyun Wang, Lin Zhang, Ruihui Zhao, Xiaopu Wu, Kai Xiong, Qingsong Liu, Guoliang Kang, Yangyang Kang

机构 * Beihang University（北京航空航天大学） ； ByteDance（字节跳动） ； Zhejiang University（浙江大学） 纠错

Comments ACL 2025 Main

Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch

Yuyang Ding, Xinyu Shi, Xiaobo Liang, Juntao Li, Zhaopeng Tu, Qiaoming Zhu, Min Zhang

机构 * Soochow University（苏州大学） ； Tencent AI Lab（腾讯AI实验室） 纠错

Comments ACL 2025

Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System

Haoyang Su, Renqi Chen, Shixiang Tang, Zhenfei Yin, Xinzhe Zheng, Jinzhe Li, Biqing Qi, Qi Wu, Hui Li, Wanli Ouyang, Philip Torr, Bowen Zhou, Nanqing Dong

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Shanghai Innovation Institute（上海创新研究院） ； Department of Engineering Science, University of Oxford（牛津大学工程科学系） ； Shanghai Institute for Science of Science（上海科学研究院） ； Department of Information Engineering, Chinese University of Hong Kong（香港中文大学信息工程系） ； Department of Electronic Engineering, Tsinghua University（清华大学电子工程系） 纠错

Comments Accepted by ACL 2025 Main Conference

Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing

Kaishuai Xu, Tiezheng Yu, Wenjun Hou, Yi Cheng, Chak Tou Leong, Liangyou Li, Xin Jiang, Lifeng Shang, Qun Liu, Wenjie Li

机构 * The Hong Kong Polytechnic University（香港理工大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

Comments accepted as ACL 2025 main

Rethinking Semantic Parsing for Large Language Models: Enhancing LLM Performance with Semantic Hints

Kaikai An, Shuzheng Si, Helan Hu, Haozhe Zhao, Yuchi Wang, Qingyan Guo, Baobao Chang

机构 * National Key Laboratory for Multimedia Information Processing, Peking University（北京大学多媒体信息处理国家重点实验室） ； School of Software and Microelectronics, Peking University（北京大学软件与微电子学院） ； Tsinghua University（清华大学） 纠错

Comments Accepted by ACL 2025

Multimodal Causal Reasoning Benchmark: Challenging Vision Large Language Models to Discern Causal Links Across Modalities

Zhiyuan Li, Heng Wang, Dongnan Liu, Chaoyi Zhang, Ao Ma, Jieting Long, Weidong Cai

机构 * School of Computer Science, The University of Sydney（计算机科学学院，悉尼大学） 纠错

Comments ACL2025 Findings

Autoregressive Speech Synthesis without Vector Quantization

Lingwei Meng, Long Zhou, Shujie Liu, Sanyuan Chen, Bing Han, Shujie Hu, Yanqing Liu, Jinyu Li, Sheng Zhao, Xixin Wu, Helen Meng, Furu Wei

机构 * The Chinese University of Hong Kong（香港中文大学） ； Microsoft Corporation（微软公司） 纠错

Comments Accepted to ACL 2025 Main

Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs

Haritz Puerto, Tilek Chubakov, Xiaodan Zhu, Harish Tayyar Madabushi, Iryna Gurevych

机构 * Ubiquitous Knowledge Processing Lab (UKP Lab), TU Darmstadt and ATHENE National Research Center for Applied Cybersecurity, Germany（图宾根大学知识处理实验室（UKP Lab）及德国应用网络安全国家研究中心ATHENE） ； Dept. of ECE & Ingenuity Labs Research Institute, Queen’s University, Canada（皇后大学电子工程系及创新实验室研究机构） ； University of Bath, UK（巴斯大学） 纠错

Comments ACL 2025 Main

GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement

Yifan Yang, Zheshu Song, Jianheng Zhuo, Mingyu Cui, Jinpeng Li, Bo Yang, Yexing Du, Ziyang Ma, Xunying Liu, Ziyuan Wang, Ke Li, Shuai Fan, Kai Yu, Wei-Qiang Zhang, Guoguo Chen, Xie Chen

机构 * X-LANCE Lab, SCS, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University（X-LANCE实验室、SCS、人工智能MoE重点实验室、上海交通大学） ； Pengcheng Laboratory（鹏城实验室） ； The Chinese University of Hong Kong（香港中文大学） ； Dept EE, Tsinghua University（清华大学电子工程系） ； SII ； Harbin Institute of Technology（哈尔滨工业大学） ； Birch AI ； Dataocean AI ； AISpeech Ltd（AISpeech有限公司） ； Seasalt AI Inc（Seasalt AI公司） ； SpeechColab 纠错

Comments Accepted in ACL 2025 (Main)

Retrieve to Explain: Evidence-driven Predictions for Explainable Drug Target Identification

Ravi Patel, Angus Brayne, Rogier Hintzen, Daniel Jaroslawicz, Georgiana Neculae, Dane Corneil

机构 * BenevolentAI 纠错

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

Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery

Yifan Sun, Danding Wang, Qiang Sheng, Juan Cao, Jintao Li

机构 * University of Chinese Academy of Sciences（中国科学院大学） ； Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所） ； Media Synthesis and Forensics Lab（媒体合成与取证实验室） 纠错

Comments ACL 2025 Findings

UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models

Xueyan Zhang, Jinman Zhao, Zhifei Yang, Yibo Zhong, Shuhao Guan, Linbo Cao, Yining Wang

Comments 20 pages, 2 figures, 15 tables

Journal ref ACL 2025