EMNLP - arXivDaily 期刊&会议

2505.15776 2025-09-16 cs.CL cs.IR

ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning

Changtai Zhu, Siyin Wang, Ruijun Feng, Kai Song, Xipeng Qiu

机构 * Fudan University（复旦大学）； ByteDance Inc（字节跳动公司）； University of New South Wales（新南威尔士大学）

Comments Accepted by EMNLP 2025 at the Main Conference

2504.21773 2025-09-16 cs.CL cs.AI

MAC-Tuning: LLM Multi-Compositional Problem Reasoning with Enhanced Knowledge Boundary Awareness

Junsheng Huang, Zhitao He, Yucheng Huang, Sandeep Polisetty, Qingyun Wang, Yi. R Fung

机构 * Hong Kong University of Science and Technology（香港科技大学）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； UMass Amherst（马萨诸塞大学阿姆赫斯特分校）； William & Mary（威廉与玛丽学院）

Comments We release our code and resource at https://github.com/no-touch-fish/Multi-QA-Tuning. The paper is accepted into EMNLP 2025 main

2504.21403 2025-09-16 cs.CV

Static or Dynamic: Towards Query-Adaptive Token Selection for Video Question Answering

Yumeng Shi, Quanyu Long, Wenya Wang

机构 * Nanyang Technological University（南洋理工大学）

Comments Accepted to EMNLP 2025 (main)

2504.15133 2025-09-16 cs.CL cs.AI cs.CV cs.HC cs.LG

EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models

Ziwen Xu, Shuxun Wang, Kewei Xu, Haoming Xu, Mengru Wang, Xinle Deng, Yunzhi Yao, Guozhou Zheng, Huajun Chen, Ningyu Zhang

机构 * Zhejiang University（浙江大学）； Ocean Research Center of Zhoushan, Zhejiang University（舟山海洋研究中心，浙江大学）

Comments EMNLP 2025 System Demonstrations. Demo: https://www.youtube.com/watch?v=AkfoiPfp5rQ; code: https://github.com/zjunlp/EasyEdit

2504.14089 2025-09-16 cs.CL cs.AI cs.LG

LogicTree: Structured Proof Exploration for Coherent and Rigorous Logical Reasoning with Large Language Models

Kang He, Kaushik Roy

机构 * Electrical and Computer Engineering, Purdue University（电子与计算机工程系，普渡大学）

Comments EMNLP 2025 Main Conference

2502.12455 2025-09-16 cs.CL

DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs

Minxuan Lv, Zhenpeng Su, Leiyu Pan, Yizhe Xiong, Zijia Lin, Hui Chen, Wei Zhou, Jungong Han, Guiguang Ding, Cheng Luo, Di Zhang, Kun Gai, Songlin Hu

机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）； University of Chinese Academy of Sciences（中国科学院大学）； Kuaishou Technology（快手科技）； Tianjin University（天津大学）； Tsinghua University（清华大学）

Comments Accepted by EMNLP main conference

2502.11451 2025-09-16 cs.CL

From Personas to Talks: Revisiting the Impact of Personas on LLM-Synthesized Emotional Support Conversations

Shenghan Wu, Yimo Zhu, Wynne Hsu, Mong-Li Lee, Yang Deng

机构 * National University of Singapore（国立新加坡大学）； Singapore Management University（新加坡管理大学）

Comments Accepted by EMNLP 2025 Main Conference

2412.07030 2025-09-16 cs.CL cs.AI cs.CV cs.IR cs.LG

FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering

Amirhossein Abaskohi, Spandana Gella, Giuseppe Carenini, Issam H. Laradji

机构 * Department of Computer Science（计算机科学系）； The University of British Columbia（不列颠哥伦比亚大学）； ServiceNow Research（ServiceNow研究）

Comments Findings of EMNLP 2025

2412.05479 2025-09-16 cs.CV

LATTE: Learning to Think with Vision Specialists

Zixian Ma, Jianguo Zhang, Zhiwei Liu, Jieyu Zhang, Juntao Tan, Manli Shu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Caiming Xiong, Ranjay Krishna, Silvio Savarese

机构 * University of Washington（华盛顿大学）； Salesforce Research（Salesforce研究）

Journal ref EMNLP 2025

2410.18444 2025-09-16 cs.CL cs.SD eess.AS

Evaluating Automatic Speech Recognition Systems for Korean Meteorological Experts

ChaeHun Park, Hojun Cho, Jaegul Choo

机构 * KAIST AI（韩国国立信息科学院人工智能研究所）

Comments EMNLP 2025 Findings

2410.02465 2025-09-16 cs.CL cs.AI

Revealing the Inherent Instructability of Pre-Trained Language Models

Seokhyun An, Minji Kim, Hyounghun Kim

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

Comments Findings of EMNLP 2025 (32 pages). Code available at https://github.com/seokhyunan/response-tuning

2406.09070 2025-09-16 cs.LG cs.AI cs.CV

FairCoT: Enhancing Fairness in Text-to-Image Generation via Chain of Thought Reasoning with Multimodal Large Language Models

Zahraa Al Sahili, Ioannis Patras, Matthew Purver

机构 * School of Electronic Engineering and Computer Science, Queen Mary University of London（伦敦女王学院电子工程与计算机科学学院）； Department of Knowledge Technologies, Jožef Stefan Institute（Jožef Stefan研究所知识技术系）

Comments Accepted at EMNLP 2025