ACL

Data-Constrained Synthesis of Training Data for De-Identification

Thomas Vakili, Aron Henriksson, Hercules Dalianis

机构 * Department of Computer and Systems Sciences（计算机与系统科学系） 纠错

Comments ACL 2025 Main: Long paper

Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information

Yein Park, Chanwoong Yoon, Jungwoo Park, Minbyul Jeong, Jaewoo Kang

机构 * Korea University（韩国大学） ； Upstage AI ； AIGEN Sciences（AIGEN科学） 纠错

Comments Accepted to the main conference at ACL 2025

Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above

Nishant Balepur, Rachel Rudinger, Jordan Lee Boyd-Graber

机构 * University of Maryland（马里兰大学） 纠错

Comments ACL 2025

TESS 2: A Large-Scale Generalist Diffusion Language Model

Jaesung Tae, Hamish Ivison, Sachin Kumar, Arman Cohan

机构 * Yale University（耶鲁大学） ； University of Washington（华盛顿大学） ； Allen Institute for AI（人工智能研究院） ； The Ohio State University（俄亥俄州立大学） 纠错

Comments ACL 2025 camera-ready

HPSS: Heuristic Prompting Strategy Search for LLM Evaluators

Bosi Wen, Pei Ke, Yufei Sun, Cunxiang Wang, Xiaotao Gu, Jinfeng Zhou, Jie Tang, Hongning Wang, Minlie Huang

机构 * The Conversational Artificial Intelligence (CoAI) Group, Tsinghua University（清华大学对话人工智能（CoAI）小组） ； University of Electronic Science and Technology of China（电子科技大学） ； Zhipu AI（智谱AI） ； The Knowledge Engineering Group (KEG), Tsinghua University（清华大学知识工程小组（KEG）） 纠错

Comments ACL 2025 Findings

Subword models struggle with word learning, but surprisal hides it

Bastian Bunzeck, Sina Zarrieß

机构 * Computational Linguistics, Department of Linguistics（计算语言学系，语言学系） ； Bielefeld University（比勒菲尔德大学） 纠错

Comments Accepted to ACL 2025 (Main)

From Selection to Generation: A Survey of LLM-based Active Learning

Yu Xia, Subhojyoti Mukherjee, Zhouhang Xie, Junda Wu, Xintong Li, Ryan Aponte, Hanjia Lyu, Joe Barrow, Hongjie Chen, Franck Dernoncourt, Branislav Kveton, Tong Yu, Ruiyi Zhang, Jiuxiang Gu, Nesreen K. Ahmed, Yu Wang, Xiang Chen, Hanieh Deilamsalehy, Sungchul Kim, Zhengmian Hu, Yue Zhao, Nedim Lipka, Seunghyun Yoon, Ting-Hao Kenneth Huang, Zichao Wang, Puneet Mathur, Soumyabrata Pal, Koyel Mukherjee, Zhehao Zhang, Namyong Park, Thien Huu Nguyen, Jiebo Luo, Ryan A. Rossi, Julian McAuley

机构 * University of California San Diego（加州大学圣地亚哥分校） ； University of Wisconsin Madison（威斯康星大学麦迪逊分校） ； Carnegie Mellon University（卡内基梅隆大学） ； University of Rochester（罗切斯特大学） ； Adobe Research（Adobe研究） ； Dolby Labs（杜比实验室） ； Cisco AI Research（思科人工智能研究） ； University of Oregon（俄勒冈大学） ； University of Southern California（南加州大学） ； Pennsylvania State University（宾夕法尼亚州立大学） ； Dartmouth College（达特茅斯学院） 纠错

Comments ACL 2025

Exploring Persona Sentiment Sensitivity in Personalized Dialogue Generation

Yonghyun Jun, Hwanhee Lee

机构 * Department of Artificial Intelligence, Chung-Ang University（人工智能系， Chung-Ang 大学） 纠错

Comments Accepted to ACL 2025 (Main)

LLMs can Perform Multi-Dimensional Analytic Writing Assessments: A Case Study of L2 Graduate-Level Academic English Writing

Zhengxiang Wang, Veronika Makarova, Zhi Li, Jordan Kodner, Owen Rambow

机构 * Department of Linguistics & Institute for Advanced Computational Science, Stony Brook University（语言学系与高级计算科学研究所，石溪大学） ； Department of Linguistics, University of Saskatchewan（语言学系，萨斯喀彻温大学） 纠错

Comments ACL 2025

How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training

Yixin Ou, Yunzhi Yao, Ningyu Zhang, Hui Jin, Jiacheng Sun, Shumin Deng, Zhenguo Li, Huajun Chen

机构 * Zhejiang University（浙江大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） ； National University of Singapore（新加坡国立大学） ； NUS-NCS Joint Lab（新加坡国立大学-南洋理工大学联合实验室） 纠错

Comments ACL 2025 Findings

The Mirage of Model Editing: Revisiting Evaluation in the Wild

Wanli Yang, Fei Sun, Jiajun Tan, Xinyu Ma, Qi Cao, Dawei Yin, Huawei Shen, Xueqi Cheng

Comments Accepted to ACL 2025 Main Conference (Camera Ready Version)

Investigating Language Preference of Multilingual RAG Systems

Jeonghyun Park, Hwanhee Lee

机构 * Department of Artificial Intelligence, Chung-Ang University, Seoul, Korea（人工智能系， Chung-Ang 大学） 纠错

Comments ACL 2025 Findings

Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation

Guofu Xie, Xiao Zhang, Ting Yao, Yunsheng Shi

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学首都人工智能学院） ； Tencent（腾讯） 纠错

Comments This paper is accepted by the ACL 2025 Main Conference

Can Uniform Meaning Representation Help GPT-4 Translate from Indigenous Languages?

Shira Wein

机构 * Amherst College（阿默斯特学院） 纠错

Comments ACL 2025

RoToR: Towards More Reliable Responses for Order-Invariant Inputs

Soyoung Yoon, Dongha Ahn, Youngwon Lee, Minkyu Jung, HyungJoo Jang, Seung-won Hwang

机构 * Seoul National University（首尔国立大学） ； Channel Corporation（Channel公司） 纠错

Comments Accepted at ACL 2025 main

Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition

Masato Mita, Ryo Yoshida, Yohei Oseki

机构 * The University of Tokyo（东京大学） 纠错

Comments Accepted to ACL2025 (main, long)

The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs

Sergey Berezin, Reza Farahbakhsh, Noel Crespi

机构 * SAMOVAR, Télécom SudParis Institut Polytechnique de Paris（SAMOVAR，电信南巴黎高等理工学院） 纠错

Comments Accepted to the Main Track of ACL 2025

WhiSPA: Semantically and Psychologically Aligned Whisper with Self-Supervised Contrastive and Student-Teacher Learning

Rajath Rao, Adithya Ganesan, Oscar Kjell, Jonah Luby, Akshay Raghavan, Scott Feltman, Whitney Ringwald, Ryan L. Boyd, Benjamin Luft, Camilo Ruggero, Neville Ryant, Roman Kotov, H. Andrew Schwartz

机构 * Stony Brook University（石溪大学） ； University of Minnesota（明尼苏达大学） ； University of Texas at Dallas（德克萨斯大学达拉斯分校） ； University of Pennsylvania（宾夕法尼亚大学） 纠错

Comments 16 pages, 8 figures, ACL 2025

Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas

Nishant Balepur, Vishakh Padmakumar, Fumeng Yang, Shi Feng, Rachel Rudinger, Jordan Lee Boyd-Graber

机构 * University of Maryland（马里兰大学） ； New York University（纽约大学） ； George Washington University（乔治华盛顿大学） 纠错

Comments ACL 2025

Curiosity-Driven Reinforcement Learning from Human Feedback

Haoran Sun, Yekun Chai, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang

机构 * Baidu Inc.（百度公司） 纠错

Comments ACL 2025

Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications

Zhe Chen, Yusheng Liao, Shuyang Jiang, Pingjie Wang, Yiqiu Guo, Yanfeng Wang, Yu Wang

机构 * Shanghai Jiao Tong University（上海交通大学） ； Fudan University（复旦大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） 纠错

Comments ACL 2025 Main Conference. Project website: https://github.com/Jack-ZC8/Omni-RAG-Medical

Automating Legal Interpretation with LLMs: Retrieval, Generation, and Evaluation

Kangcheng Luo, Quzhe Huang, Cong Jiang, 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） ； Institute for Artificial Intelligence, Peking University（北京大学人工智能研究所） ； Peking University Law School（北京大学法学院） 纠错

Comments ACL 2025 Main Conference

"My life is miserable, have to sign 500 autographs everyday": Exposing Humblebragging, the Brags in Disguise

Sharath Naganna, Saprativa Bhattacharjee, Biplab Banerjee, Pushpak Bhattacharyya

机构 * Indian Institute of Technology Bombay（印度理工学院孟买分校） 纠错

Comments Accepted to ACL 2025 Findings

RecLM: Recommendation Instruction Tuning

Yangqin Jiang, Yuhao Yang, Lianghao Xia, Da Luo, Kangyi Lin, Chao Huang

Comments This paper is accepted by ACL 2025 main conference

Towards Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)

Jiarui Liu, Iman Ouzzani, Wenkai Li, Lechen Zhang, Tianyue Ou, Houda Bouamor, Zhijing Jin, Mona Diab

机构 * Carnegie Mellon University（卡内基梅隆大学） ； University of Michigan（密歇根大学） ； University of Toronto（多伦多大学） ； Max Planck Institute for Intelligent Systems（智能系统马克斯·普朗克研究所） ； Vector Institute（向量研究所） 纠错

Comments ACL 2025 Findings

Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media

Zhen Sun, Zongmin Zhang, Xinyue Shen, Ziyi Zhang, Yule Liu, Michael Backes, Yang Zhang, Xinlei He

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） 纠错

Comments Accepted at ACL 2025 Main Conference. 29 pages, 21 figures, 12 tables

Do Language Models Understand the Cognitive Tasks Given to Them? Investigations with the N-Back Paradigm

Xiaoyang Hu, Richard L. Lewis

机构 * Brown University（布朗大学） ； University of Michigan（密歇根大学） 纠错

Comments ACL 2025 Findings

Neuron Empirical Gradient: Discovering and Quantifying Neurons Global Linear Controllability

Xin Zhao, Zehui Jiang, Naoki Yoshinaga

机构 * The University of Tokyo（东京大学） ； Institute of Industrial Science, The University of Tokyo（东京大学工业科学研究所） 纠错

Comments Accepted to ACL 2025 Main, 32 pages

Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation

Vera Neplenbroek, Arianna Bisazza, Raquel Fernández

机构 * Institute for Logic, Language and Computation, University of Amsterdam（逻辑、语言与计算研究所，阿姆斯特丹大学） ； Center for Language and Cognition, University of Groningen（语言与认知中心，格罗宁根大学） 纠错

Comments Accepted to the Findings of ACL 2025

Mind Your Theory: Theory of Mind Goes Deeper Than Reasoning

Eitan Wagner, Nitay Alon, Joseph M. Barnby, Omri Abend

机构 * Hebrew University of Jerusalem（海法大学） ； MPI for Biological Cybernetics（生物感知研究所） ； Centre for AI and Machine Learning, AU（人工智能与机器学习中心） ； IoPPN, King’s College London（国王学院伦敦人工智能与感知神经科学中心） 纠错

Comments 4 pages, 2 figures, accepted to ACL2025 Findings