EMNLP - arXivDaily 期刊&会议

2510.09822 2025-10-14 cs.CV cs.CL

Task-Aware Resolution Optimization for Visual Large Language Models

Weiqing Luo, Zhen Tan, Yifan Li, Xinyu Zhao, Kwonjoon Lee, Behzad Dariush, Tianlong Chen

机构 * University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）； Arizona State University（亚利桑那州立大学）； Michigan State University（密歇根州立大学）； Honda Research Institute USA（本田美国研究院）

Comments Accepted as a main conference paper at EMNLP 2025. 9 pages (main content), 7 figures

2510.09709 2025-10-14 cs.CL cs.AI

The Idola Tribus of AI: Large Language Models tend to perceive order where none exists

Shin-nosuke Ishikawa, Masato Todo, Taiki Ogihara, Hirotsugu Ohba

机构 * Graduate School of Artificial Intelligence and Science, Rikkyo University（人工智能与科学研究生院，立命馆大学）； Strategic Digital Business Unit, Mamezou Co., Ltd.（战略数字商务部，麦迈株式会社）

Comments 14 pages, 3 figures, accepted to Findings of EMNLP 2025

2510.09674 2025-10-14 cs.CY cs.AI

Leveraging LLMs to Streamline the Review of Public Funding Applications

Joao D. S. Marques, Andre V. Duarte, Andre Carvalho, Gil Rocha, Bruno Martins, Arlindo L. Oliveira

机构 * Instituto Superior Técnico（理工学院）； INESC-ID（里斯本创新科学与技术研究中心）； Carnegie Mellon University（卡内基梅隆大学）

Comments Paper Accepted at EMNLP 2025 Industry Track

2509.03937 2025-10-14 cs.CL cs.AI

SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning

Yuhao Zhang, Shaoming Duan, Jinhang Su, Chuanyi Liu, Peiyi Han

机构 * Harbin Institute of Technology（哈尔滨工业大学）； Pengcheng Laboratory（鹏城实验室）

Comments EMNLP 2025 Findings

2506.12963 2025-10-14 cs.AI cs.LG

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills

Changsheng Wang, Chongyu Fan, Yihua Zhang, Jinghan Jia, Dennis Wei, Parikshit Ram, Nathalie Baracaldo, Sijia Liu

机构 * Michigan State University（密歇根州立大学）； IBM Research（IBM研究院）

Comments Accepted by EMNLP 2025

2505.06538 2025-10-14 cs.CL

Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model

Xinyue Lou, You Li, Jinan Xu, Xiangyu Shi, Chi Chen, Kaiyu Huang

机构 * Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education（大数据与人工智能交通联合实验室（北京交通大学））； School of Computer Science and Technology, Beijing Jiaotong University（计算机科学与技术学院，北京交通大学）； Tsinghua University（清华大学）

Comments Accepted by EMNLP 2025 (main)

2502.19127 2025-10-14 cs.CL

Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization

Siyuan Zhang, Yichi Zhang, Yinpeng Dong, Hang Su

机构 * Dept. of Comp. Sci. and Tech.（计算机科学与技术系）； Institute for AI（人工智能研究院）； Tsinghua-Bosch Joint ML Center（清华大学-博世联合机器学习中心）； THBI Lab（THBI实验室）； BNRist Center（BNRist中心）； Tsinghua University（清华大学）

Comments 33 pages, 17 figures, 21 tables, accepted by EMNLP 2025 as findings paper