ACL

Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs

Anshumann, Mohd Abbas Zaidi, Akhil Kedia, Jinwoo Ahn, Taehwak Kwon, Kangwook Lee, Haejun Lee, Joohyung Lee

Comments Accepted as Oral paper at ACL 2025. Source code is available at https://github.com/akhilkedia/RandomSamplingKD . Anshumann, Mohd Abbas Zaidi and Akhil Kedia have Equal Contribution

Effective Multi-Task Learning for Biomedical Named Entity Recognition

João Ruano, Gonçalo M. Correia, Leonor Barreiros, Afonso Mendes

机构 * Priberam Labs（Priberam实验室） 纠错

Comments Accepted at the 24th BioNLP workshop (ACL2025), 15 pages, 3 figures

Hybrid Annotation for Propaganda Detection: Integrating LLM Pre-Annotations with Human Intelligence

Ariana Sahitaj, Premtim Sahitaj, Veronika Solopova, Jiaao Li, Sebastian Möller, Vera Schmitt

机构 * Quality and Usability Lab, Technische Universität Berlin, Germany（柏林技术大学质量与可用性实验室） ； German Research Center for Artificial Intelligence (DFKI), Berlin, Germany（德国人工智能研究中心（DFKI）） 纠错

Comments NLP4PI at ACL

Locate-and-Focus: Enhancing Terminology Translation in Speech Language Models

Suhang Wu, Jialong Tang, Chengyi Yang, Pei Zhang, Baosong Yang, Junhui Li, Junfeng Yao, Min Zhang, Jinsong Su

机构 * Department of Digital Media Technology, Xiamen University（厦门大学数字媒体技术系） ； Tongyi Lab（通义实验室） ； Soochow University（苏州大学） ； Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism, China（福建省和台湾非物质文化遗产数字化保护与智能处理重点实验室（厦门大学），中华人民共和国文化和旅游部，中国） 纠错

Comments Accepted at ACL 2025

Exploring the Impact of Instruction-Tuning on LLM's Susceptibility to Misinformation

Kyubeen Han, Junseo Jang, Hongjin Kim, Geunyeong Jeong, Harksoo Kim

机构 * Konkuk University（韩国康 kuk 大学） ； ETRI（电子技术研究院） 纠错

Comments ACL 2025 Main Accepted

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection

San Kim, Jonghwi Kim, Yejin Jeon, Gary Geunbae Lee

机构 * Graduate School of Artificial Intelligence, POSTECH, Republic of Korea（人工智能研究生院，POSTECH，韩国） ； Department of Computer Science and Engineering, POSTECH, Republic of Korea（计算机科学与工程系，POSTECH，韩国） 纠错

Comments 18 pages, accepted to ACL Findings 2025

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models

Kexin Chen, Dongxia Wang, Yi Liu, Haonan Zhang, Wenhai Wang

Comments ACL 2025 main

Dynamic and Generalizable Process Reward Modeling

Zhangyue Yin, Qiushi Sun, Zhiyuan Zeng, Qinyuan Cheng, Xipeng Qiu, Xuanjing Huang

机构 * College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院） 纠错

Comments Accepted by ACL 2025 Main

Enhancing Transformation from Natural Language to Signal Temporal Logic Using LLMs with Diverse External Knowledge

Yue Fang, Zhi Jin, Jie An, Hongshen Chen, Xiaohong Chen, Naijun Zhan

机构 * School of Computer Science, Peking University（北京大学计算机学院） ； Key Laboratory of High Confidence Software Technologies (PKU), MOE（高可信软件技术重点实验室（PKU）） ； National Key Laboratory of Space Integrated Information System, Institute of Software, Chinese Academy of Sciences（空间一体化信息系统国家重点实验室，软件研究所，中国科学院） ； East China Normal University（华东师范大学） 纠错

Comments 11 pages, 5 figures, published to ACL 2025

Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs

Zixiao Wang, Duzhen Zhang, Ishita Agrawal, Shen Gao, Le Song, Xiuying Chen

机构 * Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） ； Shandong University（山东省大学） 纠错

Comments Accepted by ACL 2025 Findings

AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

Jianlyu Chen, Nan Wang, Chaofan Li, Bo Wang, Shitao Xiao, Han Xiao, Hao Liao, Defu Lian, Zheng Liu

机构 * University of Science and Technology of China（中国科学技术大学） ； Beijing Academy of Artificial Intelligence（北京人工智能研究院） ； Jina AI（极光科技） ； Beijing University of Posts and Telecommunications（北京邮电大学） ； Shenzhen University（深圳大学） ； State Key Laboratory of Cognitive Intelligence（认知智能国家重点实验室） ； Hong Kong Polytechnic University（香港理工大学） 纠错

Comments 32 pages, 6 figures; Accepted to ACL 2025 Main