语言大模型 / LLM - arXivDaily 专题

2506.10946 2025-10-23 cs.LG cs.AI cs.CL 90%

GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models

Peizhi Niu, Evelyn Ma, Huiting Zhou, Duo Zhou, Huan Zhang, S. Rasoul Etesami, Olgica Milenkovic

机构 * Department of Electrical & Computer Engineering（电气与计算机工程系）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

2510.19484 2025-10-23 q-bio.BM cs.AI cs.LG 90%

KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge

Zaifei Yang, Hong Chang, Ruibing Hou, Shiguang Shan, Xilin Chen

机构 * State Key Laboratory of AI Safety, Institute of Computing Technology, CAS, China（人工智能安全国家重点实验室，计算技术研究所，中国科学院，中国）； University of Chinese Academy of Sciences (CAS), China（中国科学院大学（中国科学院））

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；pretraining(abstract)；分类 cs.AI、cs.LG

2503.01675 2025-10-23 cs.LG cs.CL 90%

Using (Not-so) Large Language Models to Generate Simulation Models in a Formal DSL: A Study on Reaction Networks

Justin N. Kreikemeyer, Miłosz Jankowski, Pia Wilsdorf, Adelinde M. Uhrmacher

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.LG

Comments 27 pages, 5 figures; supplemental material available at https://doi.org/10.1145/3733719

Journal ref ACM Trans. Model. Comput. Simul. 35, 4, Article 31 (October 2025), 27 pages

2510.19811 2025-10-23 cs.CL cs.LG 88%

Hubble: a Model Suite to Advance the Study of LLM Memorization

Johnny Tian-Zheng Wei, Ameya Godbole, Mohammad Aflah Khan, Ryan Wang, Xiaoyuan Zhu, James Flemings, Nitya Kashyap, Krishna P. Gummadi, Willie Neiswanger, Robin Jia

机构 * University of Southern California（南加州大学）； Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）

专题命中预训练与数据：LLM(title,abstract)；large language model(abstract)；language model(abstract)；pretraining(abstract)

2510.18932 2025-10-23 cs.CL cs.LG 87%

Evaluating LLM Story Generation through Large-scale Network Analysis of Social Structures

Hiroshi Nonaka, K. E. Perry

机构 * Soka University of America（索卡大学）

专题命中预训练与数据：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

Comments This paper has 14 pages and 8 figures. To be presented at the NeurIPS 2025 Workshop on Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling

2510.19488 2025-10-23 cs.CL cs.AI cs.LG 85%

VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos

Dunjie Lu, Yiheng Xu, Junli Wang, Haoyuan Wu, Xinyuan Wang, Zekun Wang, Junlin Yang, Hongjin Su, Jixuan Chen, Junda Chen, Yuchen Mao, Jingren Zhou, Junyang Lin, Binyuan Hui, Tao Yu

机构 * The University of Hong Kong（香港大学）； Qwen Team, Alibaba Group（阿里巴巴集团Qwen团队）

专题命中预训练与数据：pretraining(title,abstract)；SFT(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 8 pages, 6 figures

2510.18910 2025-10-23 cs.LG cs.AI 84%

Large Connectome Model: An fMRI Foundation Model of Brain Connectomes Empowered by Brain-Environment Interaction in Multitask Learning Landscape

Ziquan Wei, Tingting Dan, Guorong Wu

专题命中预训练与数据：foundation model(title,abstract)；pretraining(abstract)；分类 cs.AI、cs.LG

Comments 12 pages 6 figures

2510.19710 2025-10-23 cs.LG 83%

SEMPO: Lightweight Foundation Models for Time Series Forecasting

Hui He, Kun Yi, Yuanchi Ma, Qi Zhang, Zhendong Niu, Guansong Pang

机构 * Beijing Institute of Technology（北京理工大学）； Singapore Management University（新加坡管理大学）； State Information Center（国家信息中心）； Tongji University（同济大学）

专题命中预训练与数据：foundation model(title,abstract)；pretraining(abstract)；分类 cs.LG

Comments Accepted by NeurIPS 2025

2503.10620 2025-10-23 cs.CL 83%

From TOWER to SPIRE: Adding the Speech Modality to a Translation-Specialist LLM

Kshitij Ambilduke, Ben Peters, Sonal Sannigrahi, Anil Keshwani, Tsz Kin Lam, Bruno Martins, André F. T. Martins, Marcely Zanon Boito

机构 * ENS Paris-Saclay（巴黎-萨克雷大学）； INESC-ID ； Instituto de Telecomunicações（电信研究所）； Instituto Superior Técnico, Universidade de Lisboa（里斯本大学技术学院）； Sapienza University of Rome（罗马萨皮恩扎大学）； University of Edinburgh（爱丁堡大学）； TransPerfect ； NAVER LABS Europe（NAVER欧洲实验室）

专题命中预训练与数据：LLM(title)；language model(abstract)；pretraining(abstract)；分类 cs.CL

Comments EMNLP 2025 (Findings) camera ready

2510.19802 2025-10-23 cs.CV 82%

Class-Aware Prototype Learning with Negative Contrast for Test-Time Adaptation of Vision-Language Models

Xiaozhen Qiao, Jingkai Zhao, Yuqiu Jiang, Xianda Guo, Zhe Sun, Hongyuan Zhang, Xuelong Li

机构 * School of Information Science and Technology, University of Science and Technology of China（信息科学与技术学院，中国科学技术大学）； Institute of Artificial Intelligence (TeleAI), China Telecom, P. R. China（人工智能研究所（TeleAI），中国电信，中华人民共和国）； College of Computer Science, Wuhan University（计算机科学学院，武汉大学）； School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University（人工智能学院，光学与电子学（iOPEN），西北工业大学）

专题命中预训练与数据：language model(title,abstract)；pretraining(abstract)

2510.19264 2025-10-23 cs.CR cs.AI cs.NI 79%

LAPRAD: LLM-Assisted PRotocol Attack Discovery

R. Can Aygun, Yehuda Afek, Anat Bremler-Barr, Leonard Kleinrock

机构 * UCLA（加州大学洛杉矶分校）； Tel-Aviv University（特拉维夫大学）

专题命中预训练与数据：LLM(title,abstract)；分类 cs.AI

Comments IFIP Networking 2025 Proceedings (Accepted on 05.05.2025)

Journal ref Published in IFIP Networking 2025 Proceedings

2411.06565 2025-10-23 cs.CE cs.AI 79%

Foundation Model for Composite Microstructures: Reconstruction, Stiffness, and Nonlinear Behavior Prediction

Ting-Ju Wei, Chuin-Shan Chen

机构 * Department of Civil Engineering（土木工程系）； National Taiwan University（台湾大学）； Department of Materials Science and Engineering（材料科学与工程系）

专题命中预训练与数据：foundation model(title,abstract)；分类 cs.AI

2507.11540 2025-10-23 cs.CV 78%

Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation

Zhen Xu, Hongyu Zhou, Sida Peng, Haotong Lin, Haoyu Guo, Jiahao Shao, Peishan Yang, Qinglin Yang, Sheng Miao, Xingyi He, Yifan Wang, Yue Wang, Ruizhen Hu, Yiyi Liao, Xiaowei Zhou, Hujun Bao

专题命中预训练与数据：foundation model(title,abstract)

2510.19806 2025-10-23 cs.CL 77%

The Art of Asking: Multilingual Prompt Optimization for Synthetic Data

David Mora, Viraat Aryabumi, Wei-Yin Ko, Sara Hooker, Julia Kreutzer, Marzieh Fadaee

专题命中预训练与数据：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2510.19493 2025-10-23 cs.CL 70%

What is the Best Sequence Length for BABYLM?

Suchir Salhan, Richard Diehl Martinez, Zébulon Goriely, Paula Buttery

机构 * Department of Computer Science & Technology, University of Cambridge, U.K.（计算机科学与技术系，剑桥大学，英国）； ALTA Institute, University of Cambridge, U.K.（ALTA研究所，剑桥大学，英国）

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.CL

Comments Paper Accepted at the 2025 BabyLM Workshop @ EMNLP (Suzhou, China)

2506.21374 2025-10-23 cs.LG cs.AI 62%

Pay Attention to Small Weights

Chao Zhou, Tom Jacobs, Advait Gadhikar, Rebekka Burkholz

机构 * CISPA Helmholtz Center for Information Security（CISPA 情报安全研究中心）

专题命中预训练与数据：pretraining(abstract)；分类 cs.AI、cs.LG

2510.19367 2025-10-23 cs.CL 57%

Sign Language Translation with Sentence Embedding Supervision

Yasser Hamidullah, Josef van Genabith, Cristina España-Bonet

机构 * German Research Center for Artificial Intelligence (DFKI GmbH)（德国人工智能研究中心（DFKI GmbH））； Saarland Informatics Campus（萨尔兰州信息学校园）

专题命中预训练与数据：pretraining(abstract)；分类 cs.CL

Journal ref published at ACL2024

1. 预训练与数据 17 篇