语言大模型 / LLM - arXivDaily 专题

2511.09864 2025-11-14 cs.LG 88%

Uncertainty-Guided Checkpoint Selection for Reinforcement Finetuning of Large Language Models

Manh Nguyen, Dung Nguyen, Dai Do, Svetha Venkatesh, Hung Le

机构 * Applied Artificial Intelligence Initiative（应用人工智能计划）； Deakin University（德肯大学）

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.LG

2508.02087 2025-11-13 cs.CL 88%

When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models

Keyu Wang, Jin Li, Shu Yang, Zhuoran Zhang, Di Wang

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

2511.04179 2025-11-07 cs.SE cs.AI 88%

Explaining Software Vulnerabilities with Large Language Models

Oshando Johnson, Alexandra Fomina, Ranjith Krishnamurthy, Vaibhav Chaudhari, Rohith Kumar Shanmuganathan, Eric Bodden

机构 * Chapman University（查普曼大学）； Paderborn University（帕德博恩大学）； University of Oldenburg（奥尔登堡大学）； Paderborn University and Fraunhofer IEM（帕德博恩大学和弗劳恩霍夫IEM研究所）

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

2510.27328 2025-11-05 cs.CL 88%

A Unified Representation Underlying the Judgment of Large Language Models

Yi-Long Lu, Jiajun Song, Wei Wang

机构 * State Key Laboratory of General Artificial Intelligence（人工智能通用技术国家重点实验室）； BIGAI

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

2511.01363 2025-11-04 cs.AI 88%

Automatic Minds: Cognitive Parallels Between Hypnotic States and Large Language Model Processing

Giuseppe Riva, Brenda K. Wiederhold, Fabrizia Mantovani

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 4 Tables

2505.15702 2025-10-28 cs.CL 88%

LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing

Peng Wang, Biyu Zhou, Xuehai Tang, Jizhong Han, Songlin Hu

机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）； School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）

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

Comments EMNLP 2025 main

2510.20252 2025-10-24 cs.AI 88%

Individualized Cognitive Simulation in Large Language Models: Evaluating Different Cognitive Representation Methods

Tianyi Zhang, Xiaolin Zhou, Yunzhe Wang, Erik Cambria, David Traum, Rui Mao

机构 * Department of Computer Science, University of Southern California（计算机科学系，南加州大学）； College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学）； USC Institute for Creative Technologies（南加州大学创意技术研究所）

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

2504.14045 2025-10-14 cs.AI cs.HC 88%

Metacognition and Uncertainty Communication in Humans and Large Language Models

Mark Steyvers, Megan A. K. Peters

机构 * Department of Cognitive Sciences University of California, Irvine（认知科学系加州大学尔湾分校）

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

Journal ref Current Directions in Psychological Science, 2025

2510.06912 2025-10-09 cs.LG 88%

Utilizing Large Language Models for Machine Learning Explainability

Alexandros Vassiliades, Nikolaos Polatidis, Stamatios Samaras, Sotiris Diplaris, Ignacio Cabrera Martin, Yannis Manolopoulos, Stefanos Vrochidis, Ioannis Kompatsiaris

机构 * Centre for Research \& Technology, Hellas School of Architecture Technology ； Engineering, University of Brighton, BN2 4GJ, United Kingdom University of Nicosia, 2417 Cyprus

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.LG

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

2509.24338 2025-09-30 cs.CL 88%

AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment

Mengyu Bu, Shaolei Zhang, Zhongjun He, Hua Wu, Yang Feng

机构 * Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS)（智能信息处理重点实验室，计算技术研究所，中国科学院）； Key Laboratory of AI Safety, Chinese Academy of Sciences（人工智能安全重点实验室，中国科学院）； University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）； Baidu Inc.（百度公司）

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

Comments Accepted to EMNLP 2025 Main Conference. The code will be available at https://github.com/ictnlp/AlignX

2509.21534 2025-09-29 cs.LG 88%

A circuit for predicting hierarchical structure in-context in Large Language Models

Tankred Saanum, Can Demircan, Samuel J. Gershman, Eric Schulz

机构 * Harvard University（哈佛大学）； Institute for Human-Centered AI（以人为中心的人工智能研究所）； Helmholtz Computational Health Center（海德堡计算健康中心）

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.LG

2505.16538 2025-09-19 cs.CL 88%

Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models

Ercong Nie, Helmut Schmid, Hinrich Schütze

机构 * Center for Information and Language Processing (CIS)（信息与语言处理中心）； 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：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments Accepted to EMNLP 2025 Findings

2412.13341 2025-09-08 cs.LG cs.CR 88%

Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing

Keltin Grimes, Marco Christiani, David Shriver, Marissa Connor

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.LG

Comments Published at ICLR 2025

2509.00869 2025-09-03 cs.CL 88%

Exploring and Mitigating Fawning Hallucinations in Large Language Models

Zixuan Shangguan, Yanjie Dong, Lanjun Wang, Xiaoyi Fan, Victor C. M. Leung, Xiping Hu

机构 * School of Medical Technology, Beijing Institute of Technology（北京理工大学医学技术学院）； Artificial Intelligence Research Institute, Shenzhen MSU-BIT University（深圳MSU-BIT大学人工智能研究院）； Tianjin University（天津大学）； The Hong Kong University of Science（香港科学大学）

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

2508.16448 2025-08-25 cs.MM cs.LG eess.IV 88%

Beyond Interpretability: Exploring the Comprehensibility of Adaptive Video Streaming through Large Language Models

Lianchen Jia, Chaoyang Li, Ziqi Yuan, Jiahui Chen, Tianchi Huang, Jiangchuan Liu, Lifeng Sun

机构 * Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）； School of Computing Science, Simon Fraser University（西蒙弗雷泽大学计算机科学系）； Beijing National Research Center for Information Science and Technology（北京信息科学国家研究中心）

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.LG

Comments ACM Multimedia2025

2411.17110 2025-08-20 cs.DB cs.LG 88%

TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations

Arash Dargahi Nobari, Davood Rafiei

机构 * University of Alberta（阿尔伯塔大学）

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.LG

2508.12482 2025-08-19 cs.CL 88%

The Structural Sources of Verb Meaning Revisited: Large Language Models Display Syntactic Bootstrapping

Xiaomeng Zhu, R. Thomas McCoy, Robert Frank

机构 * Department of Linguistics, Yale University（语言学系，耶鲁大学）； Wu Tsai Institute, Yale University（吴 Tsai 院，耶鲁大学）

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

2508.03211 2025-08-12 cs.CL 88%

Probing Syntax in Large Language Models: Successes and Remaining Challenges

Pablo J. Diego-Simón, Emmanuel Chemla, Jean-Rémi King, Yair Lakretz

机构 * LSCP, ENS, PSL, EHESS, CNRS（劳动和社会保障部、巴黎高等师范学院、巴黎社会科学学院、法国国家科学研究中心）

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

2406.10099 2025-08-08 cs.CL 88%

Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuning

Jiaqi Li, Yixuan Tang, Yi Yang

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学）

专题命中知识编辑与模型理解：LLM(title)；instruction tuning(title)；large language model(abstract)；language model(abstract)

Comments Findings of The 63rd Annual Meeting of the Association for Computational Linguistics (ACL Findings 2025)

2409.11026 2025-08-07 cs.CR cs.LG 88%

Prompt Obfuscation for Large Language Models

David Pape, Sina Mavali, Thorsten Eisenhofer, Lea Schönherr

机构 * CISPA Helmholtz Center for Information Security（CISPA 德国信息安全中心）； Berlin Institute for the Foundations of Learning and Data (BIFOLD)（柏林学习与数据基础研究所）； Technische Universität Berlin（柏林技术大学）

专题命中知识编辑与模型理解：large language model(title)；language model(title)；LLM(abstract)；foundation model(abstract)

2503.02442 2025-08-04 cs.CL 88%

AILS-NTUA at SemEval-2025 Task 3: Leveraging Large Language Models and Translation Strategies for Multilingual Hallucination Detection

Dimitra Karkani, Maria Lymperaiou, Giorgos Filandrianos, Nikolaos Spanos, Athanasios Voulodimos, Giorgos Stamou

机构 * School of Electrical and Computer Engineering（电气与计算机工程学院）； AILS Laboratory（AILS实验室）； National Technical University of Athens（雅典国家技术大学）

专题命中知识编辑与模型理解：large language model(title)；language model(title)；LLM(abstract)；prompting(abstract)

Journal ref The 19th International Workshop on Semantic Evaluation (SemEval 2025)

2507.12950 2025-07-21 cs.LG 88%

Insights into a radiology-specialised multimodal large language model with sparse autoencoders

Kenza Bouzid, Shruthi Bannur, Felix Meissen, Daniel Coelho de Castro, Anton Schwaighofer, Javier Alvarez-Valle, Stephanie L. Hyland

机构 * Microsoft Research, Health Futures, Cambridge, United Kingdom（微软研究院，健康未来，剑桥，英国）

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.LG

Comments Actionable Interpretability Workshop at ICML 2025. 24 pages, 7 figures, 5 tables

2403.09567 2025-07-17 cs.RO cs.AI 88%

Enhancing Trust in Autonomous Agents: An Architecture for Accountability and Explainability through Blockchain and Large Language Models

Laura Fernández-Becerra, Miguel Ángel González-Santamarta, Ángel Manuel Guerrero-Higueras, Francisco Javier Rodríguez-Lera, Vicente Matellán Olivera

机构 * Robotics Group, University of León（莱昂大学机器人组）

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

2506.22359 2025-06-30 cs.NI cs.AI 88%

Concept-Level AI for Telecom: Moving Beyond Large Language Models

Viswanath Kumarskandpriya, Abdulhalim Dandoush, Abbas Bradai, Ali Belgacem

机构 * Esme Research Lab, SA ESME, Ivry-Sur-Seine, France（Esme研究实验室，SA ESME，法国伊维尔--sur-塞纳）； University of Doha for Science and Technology (UDST)（多哈科学技术大学）； Côte d'Azur University, LEAT, Sophia Antipolis, France（蔚蓝海岸大学，LEAT，法国索菲亚-安蒂波利斯）

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

2502.11707 2025-06-26 cs.CL 88%

Ad-hoc Concept Forming in the Game Codenames as a Means for Evaluating Large Language Models

Sherzod Hakimov, Lara Pfennigschmidt, David Schlangen

机构 * Computational Linguistics, Department of Linguistics University of Potsdam（波恩大学语言学系）； German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）

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

Comments Accepted at GemBench workshop co-located with ACL 2025

2506.16163 2025-06-23 cs.AI 88%

Large Language Models are Near-Optimal Decision-Makers with a Non-Human Learning Behavior

Hao Li, Gengrui Zhang, Petter Holme, Shuyue Hu, Zhen Wang

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

2502.02958 2025-06-18 cs.CL 88%

Position: Editing Large Language Models Poses Serious Safety Risks

Paul Youssef, Zhixue Zhao, Daniel Braun, Jörg Schlötterer, Christin Seifert

机构 * Marburg University（马尔堡大学）； University of Sheffield（谢菲尔德大学）； University of Mannheim（曼海姆大学）

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

Comments Accepted at ICML 2025

2410.07819 2025-06-18 cs.CL 88%

Uncovering Overfitting in Large Language Model Editing

Mengqi Zhang, Xiaotian Ye, Qiang Liu, Pengjie Ren, Shu Wu, Zhumin Chen

机构 * Shandong University（山东大学）； School of Computer Science, Beijing University of Posts and Telecommunications（北京邮电大学计算机学院）； New Laboratory of Pattern Recognition (NLPR) State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）

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

Comments ICLR 2025

2506.08422 2025-06-12 cs.AI 88%

Transforming Expert Knowledge into Scalable Ontology via Large Language Models

Ikkei Itoku, David Theil, Evelyn Eichelsdoerfer Uehara, Sreyoshi Bhaduri, Junnosuke Kuroda, Toshi Yumoto, Alex Gil, Natalie Perez, Rajesh Cherukuri, Naumaan Nayyar

机构 * Amazon New York, USA（亚马逊纽约分公司）； Amazon Arlington, USA（亚马逊阿灵顿分公司）； Amazon Seattle, USA（亚马逊西雅图分公司）； Amazon Honolulu, USA（亚马逊檀香山分公司）

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

1. 知识编辑与模型理解 7583 篇

Uncertainty-Guided Checkpoint Selection for Reinforcement Finetuning of Large Language Models

When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models

Explaining Software Vulnerabilities with Large Language Models

A Unified Representation Underlying the Judgment of Large Language Models

Automatic Minds: Cognitive Parallels Between Hypnotic States and Large Language Model Processing

LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing

Individualized Cognitive Simulation in Large Language Models: Evaluating Different Cognitive Representation Methods

Metacognition and Uncertainty Communication in Humans and Large Language Models

Utilizing Large Language Models for Machine Learning Explainability

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

AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment

A circuit for predicting hierarchical structure in-context in Large Language Models

Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models

Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing

Exploring and Mitigating Fawning Hallucinations in Large Language Models

Beyond Interpretability: Exploring the Comprehensibility of Adaptive Video Streaming through Large Language Models

TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations

The Structural Sources of Verb Meaning Revisited: Large Language Models Display Syntactic Bootstrapping

Probing Syntax in Large Language Models: Successes and Remaining Challenges

Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuning

Prompt Obfuscation for Large Language Models

AILS-NTUA at SemEval-2025 Task 3: Leveraging Large Language Models and Translation Strategies for Multilingual Hallucination Detection

Insights into a radiology-specialised multimodal large language model with sparse autoencoders

Enhancing Trust in Autonomous Agents: An Architecture for Accountability and Explainability through Blockchain and Large Language Models

Concept-Level AI for Telecom: Moving Beyond Large Language Models

Ad-hoc Concept Forming in the Game Codenames as a Means for Evaluating Large Language Models

Large Language Models are Near-Optimal Decision-Makers with a Non-Human Learning Behavior

Position: Editing Large Language Models Poses Serious Safety Risks

Uncovering Overfitting in Large Language Model Editing

Transforming Expert Knowledge into Scalable Ontology via Large Language Models