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。

共收录 7552 信号源:cs.CL, cs.AI, cs.LG

1. 知识编辑与模型理解 7552 篇

2510.21121 2025-10-27 cs.RO cs.AI 70%

Generalizable Hierarchical Skill Learning via Object-Centric Representation

Haibo Zhao, Yu Qi, Boce Hu, Yizhe Zhu, Ziyan Chen, Heng Tian, Xupeng Zhu, Owen Howell, Haojie Huang, Robin Walters, Dian Wang, Robert Platt

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.13737 2025-10-27 cs.AI 70%

Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers

Andrew Nam, Henry Conklin, Yukang Yang, Thomas Griffiths, Jonathan Cohen, Sarah-Jane Leslie

机构 * Princeton Laboratory for AI Natural and Artificial Minds(普林斯顿人工智能实验室) Princeton University(普林斯顿大学) Department of Electrical and Computer Engineering(电气与计算机工程系) Department of Psychology(心理学系) Princeton Neuroscience Institute(普林斯顿神经科学研究所) Department of Philosophy(哲学系) Center for Statistics and Machine Learning(统计与机器学习中心)

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

Comments 10 pages, 5 figures, 2 tables. The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.20807 2025-10-24 cs.CV cs.LG 70%

Video Prediction of Dynamic Physical Simulations With Pixel-Space Spatiotemporal Transformers

Dean L Slack, G Thomas Hudson, Thomas Winterbottom, Noura Al Moubayed

机构 * Durham University(杜伦大学)

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

Comments 14 pages, 14 figures

Journal ref IEEE Transactions on Neural Networks and Learning Systems, 36, 19106-19118, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.20531 2025-10-24 cs.CV cs.AI 70%

Fake-in-Facext: Towards Fine-Grained Explainable DeepFake Analysis

Lixiong Qin, Yang Zhang, Mei Wang, Jiani Hu, Weihong Deng, Weiran Xu

机构 * Beijing University of Posts and Telecommunications(北京邮电大学) Beijing Normal University(北京师范大学)

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

Comments 25 pages, 9 figures, 17 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.13688 2025-10-24 cs.LG stat.ML 70%

What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers

Pulkit Gopalani, Wei Hu

机构 * University of Michigan(密歇根大学)

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

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.19792 2025-10-23 cs.CY cs.AI 70%

On Controlled Change: Generative AI's Impact on Professional Authority in Journalism

Tomás Dodds, Wang Ngai Yeung, Claudia Mellado, Mathias-Felipe de Lima-Santos

机构 * University of Wisconsin-Madison(威斯康星大学麦迪逊分校) Leiden University(莱顿大学) Northeastern University(东北大学) London University of Oxford(牛津大学伦敦分校) Pontificia Universidad Católica de Valparaiso(瓦尔帕莱索天主教大学) Macquarie University(麦考瑞大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.19678 2025-10-23 cs.CV cs.AI 70%

I Spy With My Model's Eye: Visual Search as a Behavioural Test for MLLMs

John Burden, Jonathan Prunty, Ben Slater, Matthieu Tehenan, Greg Davis, Lucy Cheke

机构 * Leverhulme Centre for the Future of Intelligence, University of Cambridge(未来智能研究中心、剑桥大学) Department of Engineering, University of Cambridge(工程系、剑桥大学) Department of Psychology, University of Cambridge(心理学系、剑桥大学) Department of Computer Science, University of Cambridge(计算机科学系、剑桥大学)

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

Comments Preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.19310 2025-10-23 cs.CL 70%

JointCQ: Improving Factual Hallucination Detection with Joint Claim and Query Generation

Fan Xu, Huixuan Zhang, Zhenliang Zhang, Jiahao Wang, Xiaojun Wan

机构 * Wangxuan Institute of Computer Technology, Peking University(王轩计算机技术研究所,北京大学) Trustworthy Technology and Engineering Laboratory, Huawei(可信技术与工程实验室,华为)

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
2510.15188 2025-10-21 cs.CR cs.LG 70%

OCR-APT: Reconstructing APT Stories from Audit Logs using Subgraph Anomaly Detection and LLMs

Ahmed Aly, Essam Mansour, Amr Youssef

机构 * Concordia University(康科德大学)

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

Comments This is the authors' extended version of the paper accepted for publication at the ACM SIGSAC Conference on Computer and Communications Security (CCS 2025). The final published version is available at https://doi.org/10.1145/3719027.3765219

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.13946 2025-10-21 cs.AI 70%

Visual Instruction Bottleneck Tuning

Changdae Oh, Jiatong Li, Shawn Im, Sharon Li

机构 * Department of Computer Sciences, University of Wisconsin–Madison(计算机科学系,威斯康星大学麦迪逊分校)

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

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12672 2025-10-20 cs.LG 70%

Keep Calm and Avoid Harmful Content: Concept Alignment and Latent Manipulation Towards Safer Answers

Ruben Belo, Marta Guimaraes, Claudia Soares

机构 * Neuraspace(Neuraspace公司)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.15094 2025-10-20 cs.LG 70%

Evaluating Sparse Autoencoders for Monosemantic Representation

Moghis Fereidouni, Muhammad Umair Haider, Peizhong Ju, A. B. Siddique

机构 * University of Kentucky(肯塔基大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12851 2025-10-16 cs.SD cs.LG eess.AS 70%

Adaptive vector steering: A training-free, layer-wise intervention for hallucination mitigation in large audio and multimodal models

Tsung-En Lin, Kuan-Yi Lee, Hung-Yi Lee

机构 * National Taiwan University(国立台湾大学) ASUS Open Cloud Infrastructure Software Center(ASUS开放云基础设施软件中心)

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

Comments Note: This preprint is a version of the paper submitted to ICASSP 2026. The author list here includes contributors who provided additional supervision and guidance. The official ICASSP submission may differ slightly in author composition

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.07457 2025-10-16 cs.LG stat.ML 70%

Estimating the Hallucination Rate of Generative AI

Andrew Jesson, Nicolas Beltran-Velez, Quentin Chu, Sweta Karlekar, Jannik Kossen, Yarin Gal, John P. Cunningham, David Blei

机构 * Department of Statistics, Columbia University(统计系,哥伦比亚大学) Department of Computer Science, Columbia University(计算机科学系,哥伦比亚大学) OATML, Department of Computer Science, University of Oxford(OATML,计算机科学系,牛津大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.10292 2025-10-14 cs.CV cs.AI 70%

From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries

Joy Hsu, Emily Jin, Jiajun Wu, Niloy J. Mitra

机构 * Department of Computer Science Stanford University(计算机科学系 斯坦福大学) Department of Computer Science University College London(计算机科学系 伦敦大学学院)

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

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.10280 2025-10-14 cs.CL 70%

On the Entity-Level Alignment in Crosslingual Consistency

Yihong Liu, Mingyang Wang, François Yvon, Hinrich Schütze

机构 * Center for Information and Language Processing, LMU Munich(信息与语言处理中心,慕尼黑大学) Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心(MCML)) Sorbonne Université, CNRS, ISIR, France(索邦大学,CNRS,ISIR,法国)

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

Comments preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.16922 2025-10-10 cs.CL 70%

UNCLE: Benchmarking Uncertainty Expressions in Long-Form Generation

Ruihan Yang, Caiqi Zhang, Zhisong Zhang, Xinting Huang, Dong Yu, Nigel Collier, Deqing Yang

机构 * Fudan University(复旦大学) University of Cambridge(剑桥大学) Tencent AI Lab(腾讯AI实验室) City University of Hong Kong(香港城市大学)

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

Comments EMNLP 2025 Main

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.10411 2025-10-10 cs.CL 70%

Resolving Lexical Bias in Model Editing

Hammad Rizwan, Domenic Rosati, Ga Wu, Hassan Sajjad

机构 * Department of Computer Science, Dalhousie University, Halifax, Canada(计算机科学系,达尔豪斯大学,哈利法克斯,加拿大)

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

Journal ref Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51747-51769, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.18234 2025-10-09 cs.HC cs.CL 70%

Can AI Have a Personality? Prompt Engineering for AI Personality Simulation: A Chatbot Case Study in Gender-Affirming Voice Therapy Training

Tailon D. Jackson, Byunggu Yu

机构 * University of the District of Columbia(哥伦比亚特区大学)

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
2508.17744 2025-10-08 cs.LG 70%

Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks

Sotaro Takeshita, Yurina Takeshita, Daniel Ruffinelli, Simone Paolo Ponzetto

机构 * Data and Web Science Group, University of Mannheim(曼海姆大学数据与网络科学组)

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

Comments Accepted to EMNLP 2025 Main Conference (Oral), camera-ready version

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.03645 2025-10-07 cs.AI 70%

Graph Generation Powered with LLMs for Boosting Multivariate Time-Series Representation Learning

Yucheng Wang, Min Wu, Ruibing Jin, Xiaoli Li, Lihua Xie, Zhenghua Chen

机构 * Institute for Infocomm Research, A ∗ STAR, Singapore(信息通信研究所,A*STAR,新加坡) School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore(电气电子工程学院,南洋理工大学,新加坡) College of Computing and Data Science, Nanyang Technological University, Singapore(计算与数据科学学院,南洋理工大学,新加坡)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.10612 2025-10-07 cs.CL 70%

Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs

Hanxing Ding, Liang Pang, Zihao Wei, Huawei Shen, Xueqi Cheng

机构 * State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences(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)

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

Comments Accepted at SIGIR-AP 2025

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
2510.00625 2025-10-02 cs.AI 70%

Is Model Editing Built on Sand? Revealing Its Illusory Success and Fragile Foundation

Wei Liu, Haomei Xu, Bingqing Liu, Zhiying Deng, Haozhao Wang, Jun Wang, Ruixuan Li, Yee Whye Teh, Wee Sun Lee

机构 * National University of Singapore(新加坡国立大学) Huazhong University of Science and Technology(华中科技大学) Central China Normal University(中国地质大学) iWudao Tech(iWudao科技) Oxford(牛津大学) Google Deepmind(谷歌DeepMind)

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

Comments This is a work in progress. Comments and suggestions are welcome

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.26461 2025-10-01 cs.CL 70%

CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Engine

Yuyang Cheng, Linyue Cai, Changwei Peng, Yumiao Xu, Rongfang Bie, Yong Zhao

机构 * Sichuan University(四川大学) Beijing Normal University(北京师范大学)

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
2507.04943 2025-10-01 cs.CV cs.CL 70%

ReLoop: "Seeing Twice and Thinking Backwards" via Closed-loop Training to Mitigate Hallucinations in Multimodal understanding

Jianjiang Yang, Yanshu li, Ziyan Huang

机构 * University of Bristol(布里斯托大学) Brown University(布朗大学) South China University of Technology(华南理工大学)

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

Comments Accepted by conference EMNLP2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.07309 2025-10-01 cs.CL 70%

ConfRAG: Confidence-Guided Retrieval-Augmenting Generation

Yin Huang, Yifan Ethan Xu, Kai Sun, Vera Yan, Alicia Sun, Haidar Khan, Jimmy Nguyen, Jingxiang Chen, Mohammad Kachuee, Zhaojiang Lin, Yue Liu, Aaron Colak, Anuj Kumar, Wen-tau Yih, Xin Luna Dong

机构 * Meta Reality Labs(Meta现实实验室) FAIR at Meta(Meta的FAIR)

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

Comments 10 pages main content, 7 pages appendix, 6 figures, 10 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.01872 2025-10-01 cs.CL 70%

Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions

Rachneet Sachdeva, Rima Hazra, Iryna Gurevych

机构 * Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science and Hessian Center for AI (hessian.AI), Technical University of Darmstadt(德累斯顿技术大学计算机科学系、海斯堡人工智能中心(hessian.AI)、通用知识处理实验室(UKP Lab))

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

Comments Accepted at EMNLP 2025 (Main)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.24171 2025-09-30 cs.LG 70%

Model Correlation Detection via Random Selection Probing

Ruibo Chen, Sheng Zhang, Yihan Wu, Tong Zheng, Peihua Mai, Heng Huang

机构 * University of Maryland, College Park(马里兰大学学院公园分校)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.23684 2025-09-30 cs.LG 70%

Hedonic Neurons: A Mechanistic Mapping of Latent Coalitions in Transformer MLPs

Tanya Chowdhury, Atharva Nijasure, Yair Zick, James Allan

机构 * Center for Intelligent Information Retrieval(智能信息检索中心) University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)

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

Comments Preprint

详情

展开后加载摘要…

URL PDF HTML 收藏