arXivDaily arXiv每日学术速递 周一至周五更新

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。

2025-07-31 至 2025-07-31 共收录 5 信号源:cs.CL, cs.AI, cs.LG

1. 知识编辑与模型理解 5 篇

2505.08450 2025-07-31 cs.CL 77%

IterKey: Iterative Keyword Generation with LLMs for Enhanced Retrieval Augmented Generation

Kazuki Hayashi, Hidetaka Kamigaito, Shinya Kouda, Taro Watanabe

机构 * Nara Institute of Science and Technology(奈良科学技術研究所) TDSE Inc.(TDSE公司)

专题命中 知识编辑与模型理解 :LLM(abstract);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
2505.15038 2025-07-31 cs.CL cs.AI 76%

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering

Haiyan Zhao, Xuansheng Wu, Fan Yang, Bo Shen, Ninghao Liu, Mengnan Du

机构 * New Jersey Institute of Technology(新泽西理工学院) University of Georgia(佐治亚大学) Wake Forest University(威克森林大学)

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

Comments 12 pages, 4 figures, 4 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.22772 2025-07-31 cs.CR cs.AI cs.LG 73%

Empirical Evaluation of Concept Drift in ML-Based Android Malware Detection

Ahmed Sabbah, Radi Jarrar, Samer Zein, David Mohaisen

机构 * Department of Computer Science, Birzeit University(巴伊兹大学计算机科学系) Department of Computer Science, University of Central Florida(中央佛罗里达大学计算机科学系)

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

Comments 18 pages, 12 tables, 14 figures, paper under review

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.15347 2025-07-31 cs.CL cs.LG 73%

Probing Information Distribution in Transformer Architectures through Entropy Analysis

Amedeo Buonanno, Alessandro Rivetti, Francesco A. N. Palmieri, Giovanni Di Gennaro, Gianmarco Romano

机构 * Department of Energy Technologies and Renewable Sources, ENEA(能源技术与可再生能源部门,ENEA)

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.LG

Comments Presented to the Italian Workshop on Neural Networks (WIRN2025) and it will appear in a Springer Chapter

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.22744 2025-07-31 cs.CL cs.AI 62%

Reducing Hallucinations in Summarization via Reinforcement Learning with Entity Hallucination Index

Praveenkumar Katwe, Rakesh Chandra, Balabantaray Kali, Prasad Vittala

机构 * International Institute of Information Technology(国际信息研究所) Informatica Business Solutions(Informatica商务解决方案)

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

Comments 8

详情

展开后加载摘要…

URL PDF HTML 收藏