ACL

Unlocking Speech Instruction Data Potential with Query Rewriting

Yonghua Hei, Yibo Yan, Shuliang Liu, Huiyu Zhou, Linfeng Zhang, Xuming Hu

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Guangxi Zhuang Autonomous Region Big Data Research Institute（广西壮族自治区大数据研究院） ； The Hong Kong University of Science and Technology（香港科技大学） ； School of Artificial Intelligence, Shanghai Jiaotong University（上海交通大学人工智能学院） 纠错

Comments ACL 2025 Findings

ChainEdit: Propagating Ripple Effects in LLM Knowledge Editing through Logical Rule-Guided Chains

Zilu Dong, Xiangqing Shen, Zinong Yang, Rui Xia

机构 * School of Computer Science and Engineering, Nanjing University of Science and Technology, China（计算机科学与工程学院，南京理工大学） 纠错

Comments Accepted to ACL 2025 (main)

Beyond N-Grams: Rethinking Evaluation Metrics and Strategies for Multilingual Abstractive Summarization

Itai Mondshine, Tzuf Paz-Argaman, Reut Tsarfaty

机构 * Bar-Ilan University（巴伊兰大学） 纠错

Comments ACL 2025 Main

Improving MLLM's Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency

Yupu Liang, Yaping Zhang, Zhiyang Zhang, Zhiyuan Chen, Yang Zhao, Lu Xiang, Chengqing Zong, Yu Zhou

Comments Accepted by ACL 2025 Findings

Can LLMs Reliably Simulate Real Students' Abilities in Mathematics and Reading Comprehension?

KV Aditya Srivatsa, Kaushal Kumar Maurya, Ekaterina Kochmar

机构 * Mohamed bin Zayed University of Artificial Intelligence（莫莫德·本·扎耶德人工智能大学） 纠错

Comments Accepted to the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA), co-located with ACL 2025

UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations

Fengran Mo, Yifan Gao, Chuan Meng, Xin Liu, Zhuofeng Wu, Kelong Mao, Zhengyang Wang, Pei Chen, Zheng Li, Xian Li, Bing Yin, Meng Jiang

机构 * University of Montreal（蒙特利尔大学） ； University of Amsterdam（阿姆斯特丹大学） ； Renmin University（中国人民大学） ； University of Notre Dame（圣母大学） 纠错

Comments Accepted by ACL 2025 (main)

Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective

Yuchen Wen, Keping Bi, Wei Chen, Jiafeng Guo, Xueqi Cheng

机构 * State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences（中国科学院人工智能安全国家重点实验室，计算技术研究所） ； Key Laboratory of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences（中国科学院网络数据科学与技术重点实验室，计算技术研究所） ； University of Chinese Academy of Sciences（中国科学院大学） 纠错

Comments Accepted to ACL 2025 Findings

HeSum: a Novel Dataset for Abstractive Text Summarization in Hebrew

Tzuf Paz-Argaman, Itai Mondshine, Asaf Achi Mordechai, Reut Tsarfaty

机构 * Bar-Ilan University（巴伊兰大学） 纠错

Journal ref ACL 2024 Findings

Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation

Yupu Liang, Yaping Zhang, Zhiyang Zhang, Yang Zhao, Lu Xiang, Chengqing Zong, Yu Zhou

Comments Accepted by ACL 2025 Main

Hierarchical Bracketing Encodings for Dependency Parsing as Tagging

Ana Ezquerro, David Vilares, Anssi Yli-Jyrä, Carlos Gómez-Rodríguez

机构 * Universidade da Coruña, CITIC（乌拉圭科鲁纳大学，CITIC） ； Tampere University, Math. Res. Centre, Computing Sciences（塔尔基大学，数学研究中心，计算科学） ； University of Helsinki, Faculty of Arts, Digital Humanities（赫尔辛基大学，人文学院，数字人文） 纠错

Comments Accepted to ACL 2025. Camera-ready version

Enhancing Transformers for Generalizable First-Order Logical Entailment

Tianshi Zheng, Jiazheng Wang, Zihao Wang, Jiaxin Bai, Hang Yin, Zheye Deng, Yangqiu Song, Jianxin Li

机构 * Department of Computer Science and Engineering, HKUST, Hong Kong SAR, China（香港科技大学计算机科学与工程系） ； Department of Computer Science and Engineering, Beihang University, Beijing, China（北航计算机科学与工程系） ； Department of Mathematical Sciences, Tsinghua University, Beijing, China（清华大学数学科学系） 纠错

Comments ACL 2025 Main

Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style

Yuepei Li, Kang Zhou, Qiao Qiao, Bach Nguyen, Qing Wang, Qi Li

机构 * Department of Computer Science（计算机科学系） ； Iowa State University（爱荷华州立大学） 纠错

Comments This work is published at ACL 2025

Unsupervised Morphological Tree Tokenizer

Qingyang Zhu, Xiang Hu, Pengyu Ji, Wei Wu, Kewei Tu

机构 * New York University（纽约大学） ； Ant Group（蚂蚁集团） ； ShanghaiTech University（上海科技大学） 纠错

Comments ACL 2025 Findings

Shifting from Ranking to Set Selection for Retrieval Augmented Generation

Dahyun Lee, Yongrae Jo, Haeju Park, Moontae Lee

机构 * LG AI Research（LG人工智能研究） 纠错

Comments Accepted to ACL 2025 main (Oral Presentation)

CoAM: Corpus of All-Type Multiword Expressions

Yusuke Ide, Joshua Tanner, Adam Nohejl, Jacob Hoffman, Justin Vasselli, Hidetaka Kamigaito, Taro Watanabe

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

Comments ACL 2025 main

A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive

Sarath Sivaprasad, Pramod Kaushik, Sahar Abdelnabi, Mario Fritz

机构 * CISPA Helmholtz Center for Information Security（CISPA霍普夫中心信息安全研究所） ； TCS Research, Pune（TCS研究 Pune） ； Microsoft（微软） 纠错

Comments ACL 2025 (Oral)

Investigating the Robustness of Retrieval-Augmented Generation at the Query Level

Sezen Perçin, Xin Su, Qutub Sha Syed, Phillip Howard, Aleksei Kuvshinov, Leo Schwinn, Kay-Ulrich Scholl

机构 * Technical University of Munich（慕尼黑技术大学） ； Intel Labs（英特尔实验室） ； Thoughtworks 纠错

Comments Accepted to Generation, Evaluation & Metrics (GEM) Workshop at ACL 2025

MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection

Ziyan Liu, Chunxiao Fan, Haoran Lou, Yuexin Wu, Kaiwei Deng

Comments ACL 2025

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers

Zicong Tang, Shi Luohe, Zuchao Li, Baoyuan Qi, Guoming Liu, Lefei Zhang, Ping Wang

机构 * School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院） ； School of Computer Science, Wuhan University（武汉大学计算机学院） ； Xiaomi, Beijing, China（小米（北京，中国）） ； School of Information Management, Wuhan University（武汉大学信息管理学院） 纠错

Comments Accepted by ACL 2025 main

Knockout LLM Assessment: Using Large Language Models for Evaluations through Iterative Pairwise Comparisons

Isik Baran Sandan, Tu Anh Dinh, Jan Niehues

机构 * Karlsruhe Institute of Technology（卡尔斯鲁厄理工大学） 纠错

Comments Accepted to GEM @ ACL 2025

Substance over Style: Evaluating Proactive Conversational Coaching Agents

Vidya Srinivas, Xuhai Xu, Xin Liu, Kumar Ayush, Isaac Galatzer-Levy, Shwetak Patel, Daniel McDuff, Tim Althoff

机构 * University of Washington（华盛顿大学） ； Google Research（谷歌研究） 纠错

Comments Accepted to ACL 2025

Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts

Hongyu Chen, Seraphina Goldfarb-Tarrant

机构 * Cohere 纠错

Comments 9 pages, ACL 2025

CMQCIC-Bench: A Chinese Benchmark for Evaluating Large Language Models in Medical Quality Control Indicator Calculation

Guangya Yu, Yanhao Li, Zongying Jiang, Yuxiong Jin, Li Dai, Yupian Lin, Ruihui Hou, Weiyan Zhang, Yongqi Fan, Qi Ye, Jingping Liu, Tong Ruan

机构 * School of Information Science and Engineering, East China University of Science and Technology（信息科学与工程学院，东华大学） 纠错

Comments 2025 ACL Findings

Theme-Explanation Structure for Table Summarization using Large Language Models: A Case Study on Korean Tabular Data

TaeYoon Kwack, Jisoo Kim, Ki Yong Jung, DongGeon Lee, Heesun Park

机构 * Sungkyunkwan University（成均馆大学） ； Pohang University of Science and Technology（釜山科学技术大学） 纠错

Comments Accepted to TRL@ACL 2025

Can Input Attributions Explain Inductive Reasoning in In-Context Learning?

Mengyu Ye, Tatsuki Kuribayashi, Goro Kobayashi, Jun Suzuki

机构 * Tohoku University（东北大学） ； MBZUAI ； RIKEN（日本研究机构） 纠错

Comments Findings of ACL 2025

NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models

Abhinav Rao, Akhila Yerukola, Vishwa Shah, Katharina Reinecke, Maarten Sap

机构 * Language Technologies Institute, Carnegie Mellon University（卡内基梅隆大学语言技术研究所） ； Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院） 纠错

Comments Published at NAACL 2025, Albuquerque, New Mexico, USA

Journal ref Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) 2373-2403

Towards a Principled Evaluation of Knowledge Editors

Sebastian Pohl, Max Ploner, Alan Akbik

机构 * Humboldt Universität zu Berlin（洪堡德柏林大学） 纠错

Comments Accepted at L2M2 workshop at ACL 2025

Flipping Knowledge Distillation: Leveraging Small Models' Expertise to Enhance LLMs in Text Matching

Mingzhe Li, Jing Xiang, Qishen Zhang, Kaiyang Wan, Xiuying Chen

机构 * ByteDance, Beijing, China（字节跳动，北京，中国） ； Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（Mohamed bin Zayed人工智能大学） 纠错

Comments Accepted by ACL 2025 main

Mitigating Shortcut Learning with InterpoLated Learning

Michalis Korakakis, Andreas Vlachos, Adrian Weller

机构 * Department of Computer Science and Technology, University of Cambridge（计算机科学与技术系，剑桥大学） ； Department of Engineering, University of Cambridge（工程系，剑桥大学） ； The Alan Turing Institute（艾伦·图灵研究所） 纠错

Comments Accepted to ACL 2025 (Main)

A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models

Shuliang Liu, Hongyi Liu, Aiwei Liu, Bingchen Duan, Qi Zheng, Yibo Yan, He Geng, Peijie Jiang, Jia Liu, Xuming Hu

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； The Hong Kong University of Science and Technology（香港科技大学） ； Harbin Institute of Technology（哈尔滨工业大学） ； Ant Group, Alibaba（蚂蚁集团，阿里巴巴） ； Northeast Forest University（东北林业大学） 纠错

Comments Accepted by ACL 2025 Findings