arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

AI 大模型

语言大模型 / LLM

大语言模型、预训练、指令微调、后训练和语言模型应用。

2025-10-03 至 2025-10-03 共收录 13 信号源:cs.CL, cs.AI, cs.LG

1. 知识编辑与模型理解 13 篇

2510.01237 2025-10-03 cs.CL cs.AI 90%

Confidence-Aware Routing for Large Language Model Reliability Enhancement: A Multi-Signal Approach to Pre-Generation Hallucination Mitigation

Nandakishor M

机构 * AI Safety Research(人工智能安全研究) Convai Innovations(Convai创新)

专题命中 知识编辑与模型理解 :large language model(title,abstract);language model(title,abstract);LLM(abstract);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.01243 2025-10-03 cs.CL 89%

Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing

Yisong Xiao, Aishan Liu, Siyuan Liang, Zonghao Ying, Xianglong Liu, Dacheng Tao

机构 * SKLCCSE, Beihang University(北航智能计算与复杂系统研究院) National University of Singapore(新加坡国立大学) Zhongguancun Laboratory, Beijing(中关村实验室) Institute of Dataspace, Hefei(合肥数据空间研究院) Nanyang Technological University(南洋理工大学)

专题命中 知识编辑与模型理解 :large language model(title,abstract);language model(title,abstract);LLM(abstract);分类 cs.CL

Comments Accepted to NeurIPS 25

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.01274 2025-10-03 cs.CL cs.LG 88%

TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models

Shenxu Chang, Junchi Yu, Weixing Wang, Yongqiang Chen, Jialin Yu, Philip Torr, Jindong Gu

机构 * Department of Engineering Science, University of Oxford, UK(牛津大学工程科学系) Hasso Plattner Institute, University of Potsdam(波茨坦大学哈索普兰特纳研究所) Carnegie Mellon University(卡内基梅隆大学) Mohamed bin Zayed University of Artificial Intelligence(姆罕默德·本·拉希德智能大学)

专题命中 知识编辑与模型理解 :large language model(title,abstract);language model(title,abstract);分类 cs.CL、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.01231 2025-10-03 cs.CL cs.AI stat.ML 88%

Trustworthy Summarization via Uncertainty Quantification and Risk Awareness in Large Language Models

Shuaidong Pan, Di Wu

专题命中 知识编辑与模型理解 :large language model(title,abstract);language model(title,abstract);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.25252 2025-10-03 cs.AI 88%

Fact Grounded Attention: Eliminating Hallucination in Large Language Models Through Attention Level Knowledge Integration

Aayush Gupta

机构 * Aayush Gupta(独立研究者)

专题命中 知识编辑与模型理解 :large language model(title,abstract);language model(title,abstract);分类 cs.AI

Comments 15 pages, 3 figures, 4 tables. Code and dataset available at https://github.com/ayushgupta4897/FGA

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.01288 2025-10-03 cs.LG cs.AI 84%

Microsaccade-Inspired Probing: Positional Encoding Perturbations Reveal LLM Misbehaviours

Rui Melo, Rui Abreu, Corina S. Pasareanu

机构 * Carnegie Mellon University(卡内基梅隆大学) FEUP(费拉尔大学) INESC-ID(葡萄牙里斯本信息技术与创新研究中心)

专题命中 知识编辑与模型理解 :LLM(title);large language model(abstract);language model(abstract);分类 cs.AI、cs.LG

Comments 9 main pages, 13 appendix pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.02292 2025-10-03 cs.CL cs.CV 79%

From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens

Hala Sheta, Eric Huang, Shuyu Wu, Ilia Alenabi, Jiajun Hong, Ryker Lin, Ruoxi Ning, Daniel Wei, Jialin Yang, Jiawei Zhou, Ziqiao Ma, Freda Shi

专题命中 知识编辑与模型理解 :language model(title,abstract);分类 cs.CL

Comments EMNLP 2025 System Demonstration | Code: https://github.com/compling-wat/vlm-lens

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.01560 2025-10-03 stat.ML cs.LG 79%

AI Foundation Model for Time Series with Innovations Representation

Lang Tong, Xinyi Wang

机构 * Lang Tong Xinyi Wang

专题命中 知识编辑与模型理解 :foundation model(title,abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.00404 2025-10-03 cs.LG cs.AI cs.CL 75%

AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features

Xudong Zhu, Mohammad Mahdi Khalili, Zhihui Zhu

机构 * Department of Computer Science & Engineering, The Ohio State University(计算机科学与工程系,俄亥俄州立大学)

专题命中 知识编辑与模型理解 :large language model(abstract);language model(abstract);分类 cs.CL、cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.01652 2025-10-03 cs.CL 70%

Learning to Look at the Other Side: A Semantic Probing Study of Word Embeddings in LLMs with Enabled Bidirectional Attention

Zhaoxin Feng, Jianfei Ma, Emmanuele Chersoni, Xiaojing Zhao, Xiaoyi Bao

机构 * Language Science and Technology, The Hong Kong Polytechnic University(语言科学与技术,香港理工大学)

专题命中 知识编辑与模型理解 :large language model(abstract);language model(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.24858 2025-10-03 cs.CL cs.LG 62%

MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs

Gabrielle Kaili-May Liu, Gal Yona, Avi Caciularu, Idan Szpektor, Tim G. J. Rudner, Arman Cohan

机构 * Yale University(耶鲁大学) Google Research(谷歌研究) University of Toronto(多伦多大学)

专题命中 知识编辑与模型理解 :prompting(abstract);分类 cs.CL、cs.LG

Comments EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.18997 2025-10-03 cs.LG 57%

Theoretical Foundations of Representation Learning using Unlabeled Data: Statistics and Optimization

Pascal Esser, Maximilian Fleissner, Debarghya Ghoshdastidar

机构 * Ludwig-Maximilians-Universität München(慕尼黑路德维希-马克西米利安大学) Technical University of Munich(慕尼黑技术大学) TUM School of Computation, Information and Technology(慕尼黑技术大学计算、信息与技术学院) Munich Data Science Institute (MDSI)(慕尼黑数据科学研究所) Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心)

专题命中 知识编辑与模型理解 :foundation model(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.11627 2025-10-03 cs.LG 57%

Enhancing Electricity-System Resilience with Adaptive Robust Optimization and Conformal Uncertainty Characterization

Shuyi Chen, Shixiang Zhu, Ramteen Sioshansi

机构 * Heinz College of Information Systems and Public Policy, Carnegie Mellon University(信息系统与公共政策学院,卡内基梅隆大学) Carnegie Mellon Electricity Industry Center(卡内基梅隆电力产业中心) Wilton E. Scott Institute for Energy Innovation(威利特·E·斯科特能源创新研究所) Department of Engineering and Public Policy, Carnegie Mellon Electricity Industry Center(工程与公共政策系,卡内基梅隆电力产业中心) Department of Electrical and Computer Engineering, Heinz College of Information Systems and Public Policy(电气与计算机工程系,信息系统与公共政策学院) Department of Integrated Systems Engineering, The Ohio State University(整合系统工程系,俄亥俄州立大学)

专题命中 知识编辑与模型理解 :prompting(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏