arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

Conference on Empirical Methods in Natural Language Processing · 会议 · Natural Language Processing

共收录 7862
2510.13848 2025-10-17 cs.CL cs.AI cs.LG

On-device System of Compositional Multi-tasking in Large Language Models

Ondrej Bohdal, Konstantinos Theodosiadis, Asterios Mpatziakas, Dimitris Filippidis, Iro Spyrou, Christos Zonios, Anastasios Drosou, Dimosthenis Ioannidis, Kyeng-Hun Lee, Jijoong Moon, Hyeonmok Ko, Mete Ozay, Umberto Michieli

机构 * Samsung R&D Institute UK(三星英国研发中心) CERTH(希腊CERTH) Samsung Research(三星研究)

Comments Accepted at EMNLP 2025 (industry track)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.13836 2025-10-17 cs.CL cs.AI

SIMBA UQ: Similarity-Based Aggregation for Uncertainty Quantification in Large Language Models

Debarun Bhattacharjya, Balaji Ganesan, Junkyu Lee, Radu Marinescu, Katsiaryna Mirylenka, Michael Glass, Xiao Shou

机构 * IBM Research(IBM研究院) Zalando Baylor University(贝勒大学)

Comments 15 pages including appendix, Findings of EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.13750 2025-10-17 cs.CL

Confidence-Based Response Abstinence: Improving LLM Trustworthiness via Activation-Based Uncertainty Estimation

Zhiqi Huang, Vivek Datla, Chenyang Zhu, Alfy Samuel, Daben Liu, Anoop Kumar, Ritesh Soni

机构 * Capital One

Comments UncertaiNLP at EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.19557 2025-10-17 cs.CL cs.LG

Confidence Calibration in Large Language Model-Based Entity Matching

Iris Kamsteeg, Juan Cardenas-Cartagena, Floris van Beers, Gineke ten Holt, Tsegaye Misikir Tashu, Matias Valdenegro-Toro

机构 * Bernoulli Institute, University of Groningen(格罗宁根大学伯努利研究所)

Comments 9 pages, 2 figures. UncertaiNLP 2025 Workshop @ EMNLP Camera Ready

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.03867 2025-10-17 cs.CL

Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth

Yang Wang, Chenghao Xiao, Chia-Yi Hsiao, Zi Yan Chang, Chi-Li Chen, Tyler Loakman, Chenghua Lin

机构 * The University of Manchester(曼彻斯特大学) Durham University(杜伦大学) The University of Sheffield(谢菲尔德大学)

Comments Accepted for oral presentation at the EMNLP 2025 Main Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.24834 2025-10-17 cs.CL

Multilinguality Does not Make Sense: Investigating Factors Behind Zero-Shot Transfer in Sense-Aware Tasks

Roksana Goworek, Haim Dubossarsky

机构 * Queen Mary University of London(伦敦玛丽女王大学) The Alan Turing Institute(艾伦·图灵研究所) University of Cambridge(剑桥大学)

Comments accepted to EMNLP 2025 Main

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.16566 2025-10-17 cs.CL

ScholarBench: A Bilingual Benchmark for Abstraction, Comprehension, and Reasoning Evaluation in Academic Contexts

Dongwon Noh, Donghyeok Koh, Junghun Yuk, Gyuwan Kim, Jaeyong Lee, Kyungtae Lim, Cheoneum Park

Comments EMNLP 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.03479 2025-10-17 cs.CL

Women, Infamous, and Exotic Beings: A Comparative Study of Honorific Usages in Wikipedia and LLMs for Bengali and Hindi

Sourabrata Mukherjee, Atharva Mehta, Sougata Saha, Akhil Arora, Monojit Choudhury

Comments Accepted and published at EMNLP 2025 (Main)

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.17692 2025-10-17 cs.CL cs.AI cs.LG

MIO: A Foundation Model on Multimodal Tokens

Zekun Wang, King Zhu, Chunpu Xu, Wangchunshu Zhou, Jiaheng Liu, Yibo Zhang, Jiashuo Wang, Ning Shi, Siyu Li, Yizhi Li, Haoran Que, Zhaoxiang Zhang, Yuanxing Zhang, Ge Zhang, Ke Xu, Jie Fu, Wenhao Huang

机构 * Beihang University(北航) M-A-P The Hong Kong Polytechnic University(香港理工大学) AIWaves University of Alberta(阿尔伯塔大学) University of Waterloo(滑铁卢大学) University of Manchester(曼彻斯特大学) Chinese Academy of Sciences(中国科学院) Peking University(北京大学) Shanghai AI Lab(上海AI实验室) Nanjing University(南京大学) Kuaishou Technology(快手科技)

Comments EMNLP 2025 (Oral). Codes and models are available in https://github.com/MIO-Team/MIO

Journal ref EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.14845 2025-10-17 cs.CL

AAVENUE: Detecting LLM Biases on NLU Tasks in AAVE via a Novel Benchmark

Abhay Gupta, Philip Meng, Ece Yurtseven, Sean O'Brien, Kevin Zhu

机构 * Algoverse AI Research(Algoverse AI 研究所)

Comments Published at NLP4PI @ EMNLP 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.13681 2025-10-16 cs.CL

How Sampling Affects the Detectability of Machine-written texts: A Comprehensive Study

Matthieu Dubois, François Yvon, Pablo Piantanida

机构 * Sorbonne Université, CNRS, ISIR, Paris France(索邦大学、国家科学研究中心、ISIR、巴黎法国) CNRS, International Laboratory on Learning Systems, Montréal, Canada(国家科学研究中心、学习系统国际实验室、蒙特利尔加拿大) Mila - Québec AI Institute, Montréal, Canada(魁北克AI研究所、蒙特利尔加拿大) CentraleSupélec, Université Paris-Saclay, Gif-sur-Yvette, France(CentraleSupélec、巴黎萨克雷大学、吉夫-sur-伊夫特法国)

Comments EMNLP 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.13494 2025-10-16 cs.CL cs.AI

LiteraryQA: Towards Effective Evaluation of Long-document Narrative QA

Tommaso Bonomo, Luca Gioffré, Roberto Navigli

机构 * Sapienza NLP Group, Sapienza University of Rome(Sapienza 大学自然语言处理组,Sapienza 罗马大学) Babelscape, Italy(Babelscape 公司,意大利)

Comments Accepted to EMNLP 2025 Main Conference. 22 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.13183 2025-10-16 cs.CL

DSCD: Large Language Model Detoxification with Self-Constrained Decoding

Ming Dong, Jinkui Zhang, Bolong Zheng, Xinhui Tu, Po Hu, Tingting He

机构 * Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning(湖北人工智能与智能学习省级重点实验室) National Language Resources Monitoring and Research Center for Network Media(网络媒体语言资源监测与研究国家中心) Central China Normal University(中央财经大学) Wuhan University of Technology(武汉理工大学)

Comments Accepted at EMNLP 2025 MainConference

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.13157 2025-10-16 cs.CE cs.AI cs.CL

Program of Thoughts for Financial Reasoning: Leveraging Dynamic In-Context Examples and Generative Retrieval

Subhendu Khatuya, Shashwat Naidu, Pawan Goyal, Niloy Ganguly

机构 * Indian Institute of Technology Kharagpur(印度理工学院卡格鲁分校)

Comments This work has been accepted for publication in the Main Conference of the Empirical Methods in Natural Language Processing (EMNLP) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12825 2025-10-16 cs.CL cs.AI cs.DB cs.LG

Classifier-Augmented Generation for Structured Workflow Prediction

Thomas Gschwind, Shramona Chakraborty, Nitin Gupta, Sameep Mehta

机构 * IBM Research(IBM研究院)

Comments Accepted at EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.02340 2025-10-16 cs.CL cs.LG

Can Prompts Rewind Time for LLMs? Evaluating the Effectiveness of Prompted Knowledge Cutoffs

Xin Gao, Ruiyi Zhang, Daniel Du, Saurabh Mahindre, Sai Ashish Somayajula, Pengtao Xie

机构 * UC San Diego(UC圣迭戈大学) SUNY Buffalo(纽约州立大学布法罗分校)

Comments Published at EMNLP 2025; Code and data available at https://github.com/gxx27/time_unlearn

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.24101 2025-10-16 cs.CL

BTC-SAM: Leveraging LLMs for Generation of Bias Test Cases for Sentiment Analysis Models

Zsolt T. Kardkovacs, Lynda Djennane, Anna Field, Boualem Benatallah, Yacine Gaci, Fabio Casati, Walid Gaaloul

机构 * Insight SFI Research Center on Data Analytics, Dublin City University(数据分析洞察SFI研究中心,都柏林城市大学) Laboratoire LITAN, École supérieure en Sciences et Technologies de l’Informatique et du Numérique(LITAN实验室,信息与数字技术高等学院) School of Computing, Dublin City University(计算学院,都柏林城市大学) Plus Que Pro, Strasbourg, France(斯特拉斯堡法国Plus Que Pro公司) ServiceNow, Zurich, Switzerland(瑞士苏黎世ServiceNow公司) Department of Information Engineering and Computer Science, University of Trento(信息工程与计算机科学系,特伦托大学) Télécom SudParis, SAMOVAR, Institut Polytechnique de Paris(巴黎理工学院SAMOVAR,Telecom SudParis)

Comments Accepted at EMNLP 2025 main conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.01052 2025-10-16 cs.AI cs.CL cs.CV

FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games

Jaewoo Ahn, Junseo Kim, Heeseung Yun, Jaehyeon Son, Dongmin Park, Jaewoong Cho, Gunhee Kim

机构 * Seoul National University(首尔国立大学) KRAFTON Georgia Institute of Technology(佐治亚理工学院)

Comments EMNLP 2025 Main. Project page: https://ahnjaewoo.github.io/flashadventure

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.04329 2025-10-16 cs.CL

No Language Data Left Behind: A Comparative Study of CJK Language Datasets in the Hugging Face Ecosystem

Dasol Choi, Woomyoung Park, Youngsook Song

机构 * Yonsei University(延世大学) AIM Intelligence(AIM智能) MODULABS Sionic AI Lablup

Comments Accepted to EMNLP 2025 MRL Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.19847 2025-10-16 cs.LG cs.AI cs.CL cs.CV

Orthogonal Finetuning Made Scalable

Zeju Qiu, Weiyang Liu, Adrian Weller, Bernhard Schölkopf

机构 * Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所) The Chinese University of Hong Kong(香港中文大学) University of Cambridge(剑桥大学) The Alan Turing Institute(艾伦·图灵研究所)

Comments EMNLP 2025 Main (18 pages, 7 figures, project page: https://spherelab.ai/oftv2/)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.13886 2025-10-16 cs.CL cs.AI

Investigating the interaction of linguistic and mathematical reasoning in language models using multilingual number puzzles

Antara Raaghavi Bhattacharya, Isabel Papadimitriou, Kathryn Davidson, David Alvarez-Melis

机构 * School of Engineering and Applied Sciences, Harvard University(哈佛大学工程与应用科学学院) Department of Linguistics, Harvard University(哈佛大学语言学系) Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University(哈佛大学凯普纳自然与人工智能研究 institute)

Comments Accepted to EMNLP 2025 Main Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.13211 2025-10-16 cs.CV cs.AI

MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with Resistance

Subin Kim, Hoonrae Kim, Jihyun Lee, Yejin Jeon, Gary Geunbae Lee

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

Comments EMNLP 2025 Main

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12722 2025-10-15 cs.CL

Which Word Orders Facilitate Length Generalization in LMs? An Investigation with GCG-Based Artificial Languages

Nadine El-Naggar, Tatsuki Kuribayashi, Ted Briscoe

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

Comments EMNLP 2025 Main Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12721 2025-10-15 cs.LG

CARVQ: Corrective Adaptor with Group Residual Vector Quantization for LLM Embedding Compression

Dayin Gou, Sanghyun Byun, Nilesh Malpeddi, Gabrielle De Micheli, Prathamesh Vaste, Jacob Song, Woo Seong Chung

机构 * LG Electronics USA(LG电子美国公司)

Comments Accepted at EMNLP Findings 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03202 2025-10-15 cs.CL

Model-Based Ranking of Source Languages for Zero-Shot Cross-Lingual Transfer

Abteen Ebrahimi, Adam Wiemerslage, Katharina von der Wense

机构 * University of Colorado Boulder(科罗拉多大学波得罗分校) Kensho Technologies(Kensho技术公司) Johannes Gutenberg University Mainz(美因茨约翰内斯·古滕贝格大学)

Comments Accepted to EMNLP 2025 (Main)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12548 2025-10-15 cs.CL cs.CV

VISaGE: Understanding Visual Generics and Exceptions

Stella Frank, Emily Allaway

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

Comments EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12181 2025-10-15 cs.CL cs.AI

From Knowledge to Treatment: Large Language Model Assisted Biomedical Concept Representation for Drug Repurposing

Chengrui Xiang, Tengfei Ma, Xiangzheng Fu, Yiping Liu, Bosheng Song, Xiangxiang Zeng

机构 * College of Computer Science and Electronic Engineering, Hunan University(计算机科学与电子工程学院,湖南大学)

Comments 16 pages, 4 figures, 13 tables. Accepted by EMNLP 2025 (Findings)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12116 2025-10-15 cs.CL cs.AI

Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models

Bajian Xiang, Shuaijiang Zhao, Tingwei Guo, Wei Zou

机构 * Beike Inc.(贝克公司) Bairong Inc.(柏睿公司)

Comments Accepted to EMNLP 2025 (Main Conference)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.11928 2025-10-15 cs.CL cs.AI

Discrepancy Detection at the Data Level: Toward Consistent Multilingual Question Answering

Lorena Calvo-Bartolomé, Valérie Aldana, Karla Cantarero, Alonso Madroñal de Mesa, Jerónimo Arenas-García, Jordan Boyd-Graber

Comments Long paper accepted at EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.11835 2025-10-15 cs.CV cs.AI cs.CL cs.LG cs.MM

Data or Language Supervision: What Makes CLIP Better than DINO?

Yiming Liu, Yuhui Zhang, Dhruba Ghosh, Ludwig Schmidt, Serena Yeung-Levy

机构 * Stanford University(斯坦福大学) Tsinghua University(清华大学)

Comments EMNLP 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏