语言大模型 / LLM - arXivDaily 专题

2508.10553 2025-08-15 cs.CL 85%

eDIF: A European Deep Inference Fabric for Remote Interpretability of LLM

Irma Heithoff. Marc Guggenberger, Sandra Kalogiannis, Susanne Mayer, Fabian Maag, Sigurd Schacht, Carsten Lanquillon

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

Comments 9 pages

2504.17130 2025-08-12 cs.CL cs.CR cs.CY 85%

Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control

Hannah Cyberey, David Evans

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

Comments Accepted to COLM 2025

2508.06846 2025-08-12 cs.HC cs.AI 85%

Highlight All the Phrases: Enhancing LLM Transparency through Visual Factuality Indicators

Hyo Jin Do, Rachel Ostrand, Werner Geyer, Keerthiram Murugesan, Dennis Wei, Justin Weisz

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

Comments 16 pages, 8 figures, To be published in Proceedings of the 8th AAAI/ACM Conference on AI, Ethics, and Society (AIES 2025)

2508.05622 2025-08-08 cs.AI 85%

Simulating Human-Like Learning Dynamics with LLM-Empowered Agents

Yu Yuan, Lili Zhao, Wei Chen, Guangting Zheng, Kai Zhang, Mengdi Zhang, Qi Liu

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

2503.19168 2025-08-08 cs.CL 85%

Language Model Uncertainty Quantification with Attention Chain

Yinghao Li, Rushi Qiang, Lama Moukheiber, Chao Zhang

机构 * Georgia Institute of Technology（佐治亚理工学院）

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

Comments 36 pages, 7 figures, 36 tables

2508.03275 2025-08-06 cs.CL 85%

LECTOR: LLM-Enhanced Concept-based Test-Oriented Repetition for Adaptive Spaced Learning

Jiahao Zhao

机构 * Xi’an University of Posts and Telecommunications（西安邮电大学）

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

Comments 15 pages, 4 figures, 1 table

2408.05456 2025-08-05 cs.CL 85%

Path-LLM: A Shortest-Path-based LLM Learning for Unified Graph Representation

Wenbo Shang, Xuliang Zhu, Xin Huang

机构 * Hong Kong Baptist University（香港 Baptist 大学）； Shanghai Jiao Tong University（上海交通大学）

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

Comments 15 pages, 12 figures

2507.15296 2025-07-22 cs.SE cs.AI 85%

Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems

Qian Xiong, Yuekai Huang, Ziyou Jiang, Zhiyuan Chang, Yujia Zheng, Tianhao Li, Mingyang Li

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

2507.13490 2025-07-21 cs.CL 85%

Revisiting LLM Value Probing Strategies: Are They Robust and Expressive?

Siqi Shen, Mehar Singh, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Rada Mihalcea

机构 * University of Michigan（密歇根大学）； LG AI Research（LG人工智能研究）； University of Illinois at Chicago（伊利诺伊大学香槟分校）

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

2507.10695 2025-07-16 cs.CY cs.AI cs.CR cs.ET cs.HC 85%

Exploring User Security and Privacy Attitudes and Concerns Toward the Use of General-Purpose LLM Chatbots for Mental Health

Jabari Kwesi, Jiaxun Cao, Riya Manchanda, Pardis Emami-Naeini

机构 * Duke University（杜克大学）

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

Comments Accepted to the 34th USENIX Security Symposium

2404.18865 2025-07-14 cs.CL 85%

Truth-value judgment in language models: 'truth directions' are context sensitive

Stefan F. Schouten, Peter Bloem, Ilia Markov, Piek Vossen

机构 * Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）

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

Comments COLM 2025

2507.04206 2025-07-08 cs.AI 85%

Mpemba Effect in Large-Language Model Training Dynamics: A Minimal Analysis of the Valley-River model

Sibei Liu, Zhijian Hu

机构 * University of Michigan（密歇根大学）

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

2507.01446 2025-07-03 cs.AI 85%

Using multi-agent architecture to mitigate the risk of LLM hallucinations

Abd Elrahman Amer, Magdi Amer

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

2507.01077 2025-07-03 cs.LG 85%

Good Enough to Learn: LLM-based Anomaly Detection in ECU Logs without Reliable Labels

Bogdan Bogdan, Arina Cazacu, Laura Vasilie

机构 * Dept. of AI, Big Data and Cloud（人工智能、大数据和云计算部门）

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

Comments 6 pages, 7 figures, 4 tables, accepted to IEEE Intelligent Vehicles Symposium (IV) 2025

2506.01048 2025-06-24 cs.AI 85%

IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory

Wei Song, Zhenya Huang, Cheng Cheng, Weibo Gao, Bihan Xu, GuanHao Zhao, Fei Wang, Runze Wu

机构 * State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China（认知智能国家重点实验室，中国科学技术大学）； Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（人工智能研究院，合肥综合性国家科学中心）； School of Computing, National University of Singapore（计算学院，新加坡国立大学）； NetEase Fuxi AI Lab（网易伏羲AI实验室）

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

Comments ACL 2025 Main

2506.07461 2025-06-10 cs.CL 85%

From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered

Siddartha Devic, Tejas Srinivasan, Jesse Thomason, Willie Neiswanger, Vatsal Sharan

机构 * University of Southern California（南加州大学）

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

2402.13184 2025-06-10 cs.CL 85%

What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents

Zhaoqian Xue, Beichen Wang, Suiyuan Zhu, Kai Mei, Hua Tang, Wenyue Hua, Mengnan Du, Yongfeng Zhang

机构 * Georgetown University（乔治城大学）； Rutgers University（罗格斯大学）； New York University（纽约大学）； New Jersey Institute of Technology（新泽西理工学院）

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

2411.10918 2025-06-03 cs.CR cs.AI 85%

INVARLLM: LLM-assisted Physical Invariant Extraction for Cyber-Physical Systems Anomaly Detection

Danial Abshari, Peiran Shi, Chenglong Fu, Meera Sridhar, Xiaojiang Du

机构 * University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）； Stevens Institute of Technology（史蒂文斯理工学院）

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

2505.20880 2025-05-28 cs.CL 85%

MSA at SemEval-2025 Task 3: High Quality Weak Labeling and LLM Ensemble Verification for Multilingual Hallucination Detection

Baraa Hikal, Ahmed Nasreldin, Ali Hamdi

机构 * Faculty of Computer Science, MSA University（计算机科学学院，MSA大学）

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

2505.19970 2025-05-27 cs.CL 85%

CP-Router: An Uncertainty-Aware Router Between LLM and LRM

Jiayuan Su, Fulin Lin, Zhaopeng Feng, Han Zheng, Teng Wang, Zhenyu Xiao, Xinlong Zhao, Zuozhu Liu, Lu Cheng, Hongwei Wang

机构 * Zhejiang University（浙江大学）； University of Hong Kong（香港大学）； Tsinghua University（清华大学）； Peking University（北京大学）； University of Illinois Chicago（伊利诺伊大学芝加哥分校）

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

2505.19670 2025-05-27 cs.CL cs.MM cs.SD eess.AS 85%

Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models

Hao Yang, Lizhen Qu, Ehsan Shareghi, Gholamreza Haffari

机构 * Department of Data Science & AI, Monash University（数据科学与人工智能系，莫纳什大学）

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

2505.16455 2025-05-23 cs.AI cs.CY 85%

Psychology-driven LLM Agents for Explainable Panic Prediction on Social Media during Sudden Disaster Events

Mengzhu Liu, Zhengqiu Zhu, Chuan Ai, Chen Gao, Xinghong Li, Lingnan He, Kaisheng Lai, Yingfeng Chen, Xin Lu, Yong Li, Quanjun Yin

机构 * National University of Defense Technology（国防科技大学）； Tsinghua University（清华大学）； Sun Yat-sen University（中山大学）； Jinan University（暨南大学）

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

2505.15793 2025-05-23 cs.RO cs.LG 85%

HCRMP: A LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving

Zhiwen Chen, Bo Leng, Zhuoren Li, Hanming Deng, Guizhe Jin, Ran Yu, Huanxi Wen

机构 * Tongji University（同济大学）； SenseTime Research（商汤科技研究院）

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

2503.21098 2025-05-14 cs.IR cs.AI 85%

Alleviating LLM-based Generative Retrieval Hallucination in Alipay Search

Yedan Shen, Kaixin Wu, Yuechen Ding, Jingyuan Wen, Hong Liu, Mingjie Zhong, Zhouhan Lin, Jia Xu, Linjian Mo

机构 * LUMIA Lab, Shanghai Jiao Tong University（LUMIA实验室，上海交通大学）

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

Comments Accepted by SIGIR 2025

Journal ref SIGIR 2025

2505.03030 2025-05-07 cs.CL 85%

UCSC at SemEval-2025 Task 3: Context, Models and Prompt Optimization for Automated Hallucination Detection in LLM Output

Sicong Huang, Jincheng He, Shiyuan Huang, Karthik Raja Anandan, Arkajyoti Chakraborty, Ian Lane

机构 * University of California, Santa Cruz（加州大学圣克ruz分校）

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

Comments 6 pages, 1 figure

2405.19456 2025-04-22 cs.AI 85%

SSFF: Investigating LLM Predictive Capabilities for Startup Success through a Multi-Agent Framework with Enhanced Explainability and Performance

Xisen Wang, Yigit Ihlamur, Fuat Alican

机构 * University of Oxford（牛津大学）； Vela Partners

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

Comments For relevant code: https://github.com/Xisen-Wang/Startup-Success-Forecasting-Framework

2504.02733 2025-04-04 cs.CL 85%

Enhancing LLM Robustness to Perturbed Instructions: An Empirical Study

Aryan Agrawal, Lisa Alazraki, Shahin Honarvar, Marek Rei

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

Comments Building Trust Workshop, ICLR 2025

2412.00493 2025-03-28 cs.CV cs.CL 85%

Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding

Duo Zheng, Shijia Huang, Liwei Wang

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

Comments Accepted by CVPR 2025

2503.15117 2025-03-20 cs.CL 85%

Exploring Model Editing for LLM-based Aspect-Based Sentiment Classification

Shichen Li, Zhongqing Wang, Zheyu Zhao, Yue Zhang, Peifeng Li

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

Comments AAAI2025

2411.15432 2025-03-17 cs.CL cs.CV 85%

Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts

Qizhou Chen, Chengyu Wang, Dakan Wang, Taolin Zhang, Wangyue Li, Xiaofeng He

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

Comments CVPR 2025 Accepted

1. 知识编辑与模型理解 7596 篇

eDIF: A European Deep Inference Fabric for Remote Interpretability of LLM

Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control

Highlight All the Phrases: Enhancing LLM Transparency through Visual Factuality Indicators

Simulating Human-Like Learning Dynamics with LLM-Empowered Agents

Language Model Uncertainty Quantification with Attention Chain

LECTOR: LLM-Enhanced Concept-based Test-Oriented Repetition for Adaptive Spaced Learning

Path-LLM: A Shortest-Path-based LLM Learning for Unified Graph Representation

Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems

Revisiting LLM Value Probing Strategies: Are They Robust and Expressive?

Exploring User Security and Privacy Attitudes and Concerns Toward the Use of General-Purpose LLM Chatbots for Mental Health

Truth-value judgment in language models: 'truth directions' are context sensitive

Mpemba Effect in Large-Language Model Training Dynamics: A Minimal Analysis of the Valley-River model

Using multi-agent architecture to mitigate the risk of LLM hallucinations

Good Enough to Learn: LLM-based Anomaly Detection in ECU Logs without Reliable Labels

IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory

From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered

What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents

INVARLLM: LLM-assisted Physical Invariant Extraction for Cyber-Physical Systems Anomaly Detection

MSA at SemEval-2025 Task 3: High Quality Weak Labeling and LLM Ensemble Verification for Multilingual Hallucination Detection

CP-Router: An Uncertainty-Aware Router Between LLM and LRM

Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models

Psychology-driven LLM Agents for Explainable Panic Prediction on Social Media during Sudden Disaster Events

HCRMP: A LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving

Alleviating LLM-based Generative Retrieval Hallucination in Alipay Search

UCSC at SemEval-2025 Task 3: Context, Models and Prompt Optimization for Automated Hallucination Detection in LLM Output

SSFF: Investigating LLM Predictive Capabilities for Startup Success through a Multi-Agent Framework with Enhanced Explainability and Performance

Enhancing LLM Robustness to Perturbed Instructions: An Empirical Study

Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding

Exploring Model Editing for LLM-based Aspect-Based Sentiment Classification

Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts