ACL

Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning

Ming Li, Pei Chen, Chenguang Wang, Hongyu Zhao, Yijun Liang, Yupeng Hou, Fuxiao Liu, Tianyi Zhou

机构 * University of Maryland（马里兰大学） ； Texas A&M University（德克萨斯A&M大学） ； Stony Brook University（石溪大学） 纠错

Comments ACL2025, Camera-ready

Revisiting Code Similarity Evaluation with Abstract Syntax Tree Edit Distance

Yewei Song, Cedric Lothritz, Daniel Tang, Tegawendé F. Bissyandé, Jacques Klein

Comments ACL 2024 Main

Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluation

Kristian Lum, Jacy Reese Anthis, Kevin Robinson, Chirag Nagpal, Alexander D'Amour

机构 * University of Chicago（芝加哥大学） ； Stanford University（斯坦福大学） ； Google Research（谷歌研究） ； Google DeepMind（谷歌DeepMind） 纠错

Comments Published in ACL 2025

RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought

Yi Lu, Jiawang Cao, Yongliang Wu, Bozheng Li, Licheng Tang, Yangguang Ji, Chong Wu, Jay Wu, Wenbo Zhu

Comments Accepted as ACL 2025 Main

Efficient Knowledge Editing via Minimal Precomputation

Akshat Gupta, Maochuan Lu, Thomas Hartvigsen, Gopala Anumanchipalli

机构 * UC Berkeley（伯克利大学） ； University of Virginia（弗吉尼亚大学） 纠错

Comments ACL 2025 Main Conference

Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis

Kejian Zhu, Shangqing Tu, Zhuoran Jin, Lei Hou, Juanzi Li, Jun Zhao

机构 * The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China（认知与决策智能复杂系统重点实验室，自动化研究所，中国科学院，北京，中国） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学） ； Tsinghua University（清华大学） 纠错

Comments Accepted to ACL 2025 Main Conference

CLAIM: An Intent-Driven Multi-Agent Framework for Analyzing Manipulation in Courtroom Dialogues

Disha Sheshanarayana, Tanishka Magar, Ayushi Mittal, Neelam Chaplot

机构 * Manipal University Jaipur（Manipal大学贾ipur） 纠错

Comments Accepted to SICon 2025 ACL

AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment

Anastasiia Ivanova, Eva Bakaeva, Zoya Volovikova, Alexey K. Kovalev, Aleksandr I. Panov

机构 * LMU（慕尼黑大学） ； MIPT（莫斯科 Institute of Physics and Technology） ； AIRI（空气研究所） 纠错

Comments ACL 2025 (Main Conference)

A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph Reasoning

Zhiyu Zhang, Wei Chen, Youfang Lin, Huaiyu Wan

Journal ref ACL 2025

Lacuna Inc. at SemEval-2025 Task 4: LoRA-Enhanced Influence-Based Unlearning for LLMs

Aleksey Kudelya, Alexander Shirnin

机构 * HSE University（俄罗斯高等经济大学） 纠错

Comments Accepted to SemEval-2025, an ACL 2025 workshop

Think Like a Person Before Responding: A Multi-Faceted Evaluation of Persona-Guided LLMs for Countering Hate

Mikel K. Ngueajio, Flor Miriam Plaza-del-Arco, Yi-Ling Chung, Danda B. Rawat, Amanda Cercas Curry

机构 * Howard University（霍华德大学） ； LIACS, Leiden University（莱顿大学LIACS） ； Genaios（基因奥斯） ； CENTAI Institute（CENTAI研究院） 纠错

Comments Accepted at ACL WOAH 2025

QQSUM: A Novel Task and Model of Quantitative Query-Focused Summarization for Review-based Product Question Answering

An Quang Tang, Xiuzhen Zhang, Minh Ngoc Dinh, Zhuang Li

机构 * RMIT University（拉筹伯大学） 纠错

Comments Paper accepted to ACL 2025 Main Conference

Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter Era

Dan Oneata, Desmond Elliott, Stella Frank

机构 * politehnica Bucharest（布加勒斯特理工大学） ； Pioneer Center for AI（先锋人工智能中心） ； Department of Computer Science, University of Copenhagen（哥本哈根大学计算机科学系） 纠错

Comments ACL Findings 2025

Words of Warmth: Trust and Sociability Norms for over 26k English Words

Saif M. Mohammad

机构 * National Research Council Canada（加拿大国家研究委员会） 纠错

Comments In Proceedings of ACL 2025 Main

Journal ref In Proceedings of ACL 2025 Main

From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed Grounding

Chiwei Zhu, Benfeng Xu, Xiaorui Wang, Zhendong Mao

Comments To be published at ACL 2025

Hanging in the Balance: Pivotal Moments in Crisis Counseling Conversations

Vivian Nguyen, Lillian Lee, Cristian Danescu-Niculescu-Mizil

机构 * Cornell University（康奈尔大学） 纠错

Comments To appear in the Proceedings of ACL 2025. Code and demo available in ConvoKit (convokit.cornell.edu)

Graph Counselor: Adaptive Graph Exploration via Multi-Agent Synergy to Enhance LLM Reasoning

Junqi Gao, Xiang Zou, YIng Ai, Dong Li, Yichen Niu, Biqing Qi, Jianxing Liu

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； School of Mathematics, Harbin Institute of Technology（哈尔滨工业大学数学学院） ； Department of Control Science and Engineering, Harbin Institute of Technology（哈尔滨工业大学控制科学与工程学院） 纠错

Comments Accepted by ACL 2025

The Harmonic Structure of Information Contours

Eleftheria Tsipidi, Samuel Kiegeland, Franz Nowak, Tianyang Xu, Ethan Wilcox, Alex Warstadt, Ryan Cotterell, Mario Giulianelli

机构 * ETH Zürich（苏黎世联邦理工学院） ； TTIC ； Georgetown（乔治城大学） ； UCSD（加州大学圣迭戈分校） 纠错

Comments ACL 2025 (main conference)

Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation

Mingxuan Xia, Haobo Wang, Yixuan Li, Zewei Yu, Jindong Wang, Junbo Zhao, Runze Wu

机构 * Zhejiang University（浙江大学） ； University of Wisconsin Madison（威斯康星大学麦迪逊分校） ； William & Mary（威廉与玛丽学院） ； NetEase Fuxi AI Lab（网易伏羲人工智能实验室） 纠错

Comments Accepted to ACL 2025 (Main conference)

ClozeMath: Improving Mathematical Reasoning in Language Models by Learning to Fill Equations

Quang Hieu Pham, Thuy Duong Nguyen, Tung Pham, Anh Tuan Luu, Dat Quoc Nguyen

机构 * Qualcomm AI Research（高通人工智能研究） 纠错

Comments Accepted to ACL 2025 Findings

Generating Pedagogically Meaningful Visuals for Math Word Problems: A New Benchmark and Analysis of Text-to-Image Models

Junling Wang, Anna Rutkiewicz, April Yi Wang, Mrinmaya Sachan

Comments Findings of the Association for Computational Linguistics: ACL 2025

Reason from Future: Reverse Thought Chain Enhances LLM Reasoning

Yinlong Xu, Yanzhao Zheng, Shuoshuo Sun, Shuaihan Huang, Baohua Dong, Hangcheng Zhu, Ruohui Huang, Gang Yu, Hongxia Xu, Jian Wu

机构 * College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院） ； Alibaba Group（阿里巴巴集团） ； State Key Laboratory of Transvascular Implantation Devices and TIDRI（血管植入设备国家重点实验室） ； Liangzhu Laboratory and WeDoctor Cloud（良渚实验室和WeDoctor云） ； Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence（浙江医学影像人工智能重点实验室） 纠错

Comments Accepted by ACL 2025 findings

Is linguistically-motivated data augmentation worth it?

Ray Groshan, Michael Ginn, Alexis Palmer

机构 * University of Colorado（科罗拉多大学） 纠错

Comments Accepted to ACL 2025 Main. First two authors contributed equally

Automatically Suggesting Diverse Example Sentences for L2 Japanese Learners Using Pre-Trained Language Models

Enrico Benedetti, Akiko Aizawa, Florian Boudin

机构 * National Institute of Informatics, Japan（日本信息处理研究所） ； JFLI, CNRS, Nantes University, France（JFLI、法国国家科学研究中心、法国南特大学） 纠错

Comments Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)

Debate, Reflect, and Distill: Multi-Agent Feedback with Tree-Structured Preference Optimization for Efficient Language Model Enhancement

Xiaofeng Zhou, Heyan Huang, Lizi Liao

机构 * Beijing Institute of Technology（北京理工大学） ； Singapore Management University（新加坡国立大学） 纠错

Comments 16 pages, 10 figures. The camera-ready paper for Findings of ACL 2025

TokAlign: Efficient Vocabulary Adaptation via Token Alignment

Chong Li, Jiajun Zhang, Chengqing Zong

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS, Beijing, China（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院，北京） ； School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China（人工智能学院，中国科学院大学，北京） 纠错

Comments ACL 2025, our codes and models are available at https://github.com/ZNLP/TokAlign

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding

Mingxu Tao, Jie Hu, Mingchuan Yang, Yunhuai Liu, Dongyan Zhao, Yansong Feng

机构 * Wangxuan Institute of Computer Technology, Peking University（北京大学王轩计算机技术研究所） ； Research Institute of China Telecom（中国电信研究 institute） ； School of Computer Science, Peking University（北京大学计算机科学学院） ； Beijing Institute of Big Data Research（北京大数据研究院） ； National Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室，BIGAI） 纠错

Comments ACL 2025 Findings

APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training

Jun Rao, Zepeng Lin, Xuebo Liu, Xiaopeng Ke, Lian Lian, Dong Jin, Shengjun Cheng, Jun Yu, Min Zhang

机构 * Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China（计算与智能学院，哈尔滨工业大学，深圳，中国） ； Huawei Cloud Computing Technologies Co., Ltd.（华为云计算技术有限公司） ； School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, China（智能科学与工程学院，哈尔滨工业大学，深圳，中国） 纠错

Comments ACL2025 Findings

Culture Matters in Toxic Language Detection in Persian

Zahra Bokaei, Walid Magdy, Bonnie Webber

Comments Accepted to ACL 2025 (Main Track)

The Reader is the Metric: How Textual Features and Reader Profiles Explain Conflicting Evaluations of AI Creative Writing

Guillermo Marco, Julio Gonzalo, Víctor Fresno

机构 * UNED Research Group in NLP and IR（UNED自然语言处理与信息检索研究组） 纠错

Comments Camera-ready version, 14 pages, 3 figures. Accepted to Findings of the Association for Computational Linguistics (ACL) 2025. Code & data: https://github.com/grmarco/the-reader-is-the-metric