EMNLP - arXivDaily 期刊&会议

2504.20484 2025-09-22 cs.CL

Enhancing LLM Language Adaption through Cross-lingual In-Context Pre-training

Linjuan Wu, Haoran Wei, Huan Lin, Tianhao Li, Baosong Yang, Fei Huang, Weiming Lu

机构 * Zhejiang University（浙江大学）； Tongyi Lab, Alibaba Group（阿里巴巴集团 Tongyi 实验室）

Comments 12 pages, 6 figures, EMNLP 2025

2503.18008 2025-09-22 cs.CL cs.NE

Personalized Language Models via Privacy-Preserving Evolutionary Model Merging

Kyuyoung Kim, Jinwoo Shin, Jaehyung Kim

机构 * KAIST AI（韩国科学技术院人工智能研究所）； Yonsei University（延世大学）

Comments EMNLP 2025 Oral

2503.12123 2025-09-22 cs.CL cs.AI

MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modeling

Zhaopeng Feng, Jiahan Ren, Jiayuan Su, Jiamei Zheng, Hongwei Wang, Zuozhu Liu

机构 * Zhejiang University（浙江大学）

Comments EMNLP 2025 Findings. Project page:https://sabijun.github.io/MT_RewardTreePage

2502.20587 2025-09-22 cs.LG

Cache-of-Thought: Master-Apprentice Framework for Cost-Effective Vision Language Model Reasoning

Mingyuan Wu, Jize Jiang, Haozhen Zheng, Meitang Li, Zhaoheng Li, Beitong Tian, Bo Chen, Yongjoo Park, Minjia Zhang, Chengxiang Zhai, Klara Nahrstedt

机构 * University of Illinois Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）； University of Michigan Ann Arbor（密歇根大学安娜堡分校）

Comments EMNLP 2025 Main Conference. Mingyuan, Jize, and Haozhen contributed equally, while Minjia, Chengxiang, and Klara advised equally

2502.19668 2025-09-22 eess.SP cs.AI cs.CL cs.LG

SuPreME: A Supervised Pre-training Framework for Multimodal ECG Representation Learning

Mingsheng Cai, Jiuming Jiang, Wenhao Huang, Che Liu, Rossella Arcucci

机构 * The University of Edinburgh（爱丁堡大学）； Imperial College London（帝国理工学院）； Shenzhen Yinwang Intelligent Technology Co., Ltd（深圳英伟达智能技术有限公司）

Comments Findings of The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)

2502.15178 2025-09-22 eess.AS cs.SD

Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders

Weiqiao Shan, Yuang Li, Yuhao Zhang, Yingfeng Luo, Chen Xu, Xiaofeng Zhao, Long Meng, Yunfei Lu, Min Zhang, Hao Yang, Tong Xiao, Jingbo Zhu

机构 * School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）； Huawei Translation Services Center（华为翻译服务中心）； The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））； College of Computer Science and Technology, Harbin Engineering University（哈尔滨工程大学计算机科学与技术学院）； NiuTrans Research（NiuTrans研究院）

Comments 16 pages,5 figures, 13 tables, to be published in EMNLP 2025 main conference

2501.07824 2025-09-22 cs.CL cs.AI cs.LG

Efficient Real-time Refinement of Language Model Text Generation

Joonho Ko, Jinheon Baek, Sung Ju Hwang

机构 * KAIST（韩国科学技术院）

Comments EMNLP 2025

2410.11900 2025-09-22 cs.AI cs.CL cs.LG cs.LO

FLARE: Faithful Logic-Aided Reasoning and Exploration

Erik Arakelyan, Pasquale Minervini, Pat Verga, Patrick Lewis, Isabelle Augenstein

机构 * University of Copenhagen（哥本哈根大学）； University of Edinburgh（爱丁堡大学）； Cohere ； NVIDIA

Comments Published at EMNLP 2025

2408.04675 2025-09-22 cs.CL cs.AI cs.IR

ConfReady: A RAG based Assistant and Dataset for Conference Checklist Responses

Michael Galarnyk, Rutwik Routu, Vidhyakshaya Kannan, Kosha Bheda, Prasun Banerjee, Agam Shah, Sudheer Chava

机构 * Georgia Institute of Technology（佐治亚理工学院）； Duke University（杜克大学）； Sai University（赛大学）

Comments Accepted at EMNLP 2025 Demo

2406.16013 2025-09-22 cs.CL cs.AI cs.IR

Database-Augmented Query Representation for Information Retrieval

Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, Jong C. Park

机构 * KAIST（韩国科学技术院）

Comments EMNLP 2025

2405.17764 2025-09-22 cs.CL cs.AI math.ST stat.TH

BBScoreV2: Learning Time-Evolution and Latent Alignment from Stochastic Representation

Tianhao Zhang, Zhecheng Sheng, Zhexiao Lin, Chen Jiang, Dongyeop Kang

机构 * University of Minnesota, Twin Cities（明尼苏达大学，双城分校）； University of California, Berkeley（加州大学伯克利分校）

Journal ref The 2025 Conference on Empirical Methods in Natural Language Processing

2509.15361 2025-09-22 cs.CL cs.AI cs.MM

Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing

Zichen Wu, Hsiu-Yuan Huang, Yunfang Wu

机构 * School of Computer Science, Peking University（北京大学计算机科学学院）； MOE Key Laboratory of Computational Linguistics, Peking University（北京大学教育部计算语言学重点实验室）； National Key Laboratory for Multimedia Information Processing, Peking University（北京大学国家多媒体信息处理重点实验室）

Comments Accepted by EMNLP 2025 Findings

2509.15356 2025-09-22 cs.LG

Predicting Language Models' Success at Zero-Shot Probabilistic Prediction

Kevin Ren, Santiago Cortes-Gomez, Carlos Miguel Patiño, Ananya Joshi, Ruiqi Lyu, Jingjing Tang, Alistair Turcan, Khurram Yamin, Steven Wu, Bryan Wilder

机构 * Cornell Tech（康奈尔科技）； Carnegie Mellon University（卡内基梅隆大学）

Comments EMNLP Findings 2025. We release our code at: camera-ready" target="_blank" rel="noopener">https://github.com/kkr36/llm-eval/tree/camera-ready

2509.15350 2025-09-22 cs.CL

Real, Fake, or Manipulated? Detecting Machine-Influenced Text

Yitong Wang, Zhongping Zhang, Margherita Piana, Zheng Zhou, Peter Gerstoft, Bryan A. Plummer

机构 * Boston University（波士顿大学）； University of California, San Diego（加州大学圣地亚哥分校）

Comments Accepted to EMNLP 2025 Findings

2508.15474 2025-09-22 cs.CL cs.AI

Subjective Behaviors and Preferences in LLM: Language of Browsing

Sai Sundaresan, Harshita Chopra, Atanu R. Sinha, Koustava Goswami, Nagasai Saketh Naidu, Raghav Karan, N Anushka

机构 * Adobe Research（Adobe研究院）； University of Washington, Seattle（华盛顿大学）

Comments Accepted at EMNLP 2025

2503.11751 2025-09-22 cs.CL

reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs

Zhaofeng Wu, Michihiro Yasunaga, Andrew Cohen, Yoon Kim, Asli Celikyilmaz, Marjan Ghazvininejad

机构 * FAIR at Meta（Meta 的 FAIR 部门）； MIT（麻省理工学院）

Comments EMNLP 2025