语言大模型 / LLM - arXivDaily 专题

2511.05516 2025-11-11 cs.CL cs.AI cs.SD eess.AS 81%

Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation

Canxiang Yan, Chunxiang Jin, Dawei Huang, Haibing Yu, Han Peng, Hui Zhan, Jie Gao, Jing Peng, Jingdong Chen, Jun Zhou, Kaimeng Ren, Ming Yang, Mingxue Yang, Qiang Xu, Qin Zhao, Ruijie Xiong, Shaoxiong Lin, Xuezhi Wang, Yi Yuan, Yifei Wu, Yongjie Lyu, Zhengyu He, Zhihao Qiu, Zhiqiang Fang, Ziyuan Huang

机构 * Inclusion AI Ant Group（Inclusion AI Ant集团）

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

Comments 32 pages, 8 figures

2511.04527 2025-11-07 cs.CL cs.AI 81%

Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamics

Amir Zur, Atticus Geiger, Ekdeep Singh Lubana, Eric Bigelow

机构 * Department of Linguistics, Stanford University（斯坦福大学语言学系）； Department of Psychology, Harvard University（哈佛大学心理学系）； Center for Brain Science, Harvard University（哈佛大学脑科学中心）； Physics of Intelligence Group, NTT Research（NTT研究物理智能小组）

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

2511.03559 2025-11-06 cs.CL cs.AI 81%

AILA--First Experiments with Localist Language Models

Joachim Diederich

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

2511.00180 2025-11-04 cs.CL cs.LG 81%

ParaScopes: What do Language Models Activations Encode About Future Text?

Nicky Pochinkov, Yulia Volkova, Anna Vasileva, Sai V R Chereddy

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

Comments Main paper: 9 pages, 10 figures. Total 24 pages

2503.16724 2025-11-03 cs.AI cs.LG 81%

Towards Automated Semantic Interpretability in Reinforcement Learning via Vision-Language Models

Zhaoxin Li, Zhang Xi-Jia, Batuhan Altundas, Letian Chen, Rohan Paleja, Matthew Gombolay

机构 * Georgia Institute of Technology（佐治亚理工学院）； Purdue University（普渡大学）

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

2502.19207 2025-10-28 cs.CL cs.AI 81%

FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge

Nakyeong Yang, Minsung Kim, Seunghyun Yoon, Joongbo Shin, Kyomin Jung

机构 * Seoul National University（首尔国立大学）； Adobe Research（Adobe研究）； LG AI Research（LG人工智能研究）

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

Comments accepted to EMNLP 2025

2506.08966 2025-10-27 cs.CL cs.LG cs.NE 81%

Pre-trained Language Models Learn Remarkably Accurate Representations of Numbers

Marek Kadlčík, Michal Štefánik, Timothee Mickus, Michal Spiegel, Josef Kuchař

机构 * Faculty of Informatics, Masaryk University（马萨里克大学信息学院）； University of Helsinki（赫尔辛基大学）； Kempelen Institute of Intelligent Technologies（凯姆佩尔智能技术研究所）

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

2510.19694 2025-10-23 cs.CL cs.AI 81%

Do Prompts Reshape Representations? An Empirical Study of Prompting Effects on Embeddings

Cesar Gonzalez-Gutierrez, Dirk Hovy

机构 * Polytechnic University of Catalonia（加泰罗尼亚理工大学）； Bocconi University（博科尼大学）

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

2505.09160 2025-10-23 cs.LG cs.AI cs.IT cs.NI eess.SP math.IT 81%

A Multi-Task Foundation Model for Wireless Channel Representation Using Contrastive and Masked Autoencoder Learning

Berkay Guler, Giovanni Geraci, Hamid Jafarkhani

机构 * Center for Pervasive Communications and Computing, University of California, Irvine（普及通信与计算中心，加州大学伊维特分校）； Nokia Standards（诺基亚标准）； Universitat Pompeu Fabra（庞培法布拉大学）

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

Comments - 17 pages, 7 figures, 5 tables - Submitted to IEEE JSAC Large AI Models for Future Wireless Communication Systems - Some of the results will appear in NeurIPS 2025, AI4NextG Workshop - This version is an extensive improvement in all aspects over the previous version with the same title - Dataset and implementation: https://github.com/BerkIGuler/WirelessContrastiveMaskedLearning

2509.24262 2025-10-22 q-bio.QM cs.AI cs.LG 81%

LAMP-PRo: Label-aware Attention for Multi-label Prediction of DNA- and RNA-binding Proteins using Protein Language Models

Nimisha Ghosh, Dheeran Sankaran, Rahul Balakrishnan Adhi, Sharath S, Amrut Anand

机构 * Department of Computer Science and Engineering, Shiv Nadar University Chennai, Tamil Nadu, India（计算机科学与工程系，Shiv Nadar大学 Chennai，印度 Tamil Nadu）

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

2510.13290 2025-10-16 cs.LG cs.AI 81%

To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models

Anna Hedström, Salim I. Amoukou, Tom Bewley, Saumitra Mishra, Manuela Veloso

机构 * J.P. Morgan AI Research（摩根大通AI研究）

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

Comments ICML 2025, 22 pages, 16 figures, 5 tables

Journal ref International Machine Learning Conference (ICML) 2025

2407.02646 2025-10-14 cs.AI cs.CL 81%

A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models

Daking Rai, Yilun Zhou, Shi Feng, Abulhair Saparov, Ziyu Yao

机构 * George Mason University（乔治·马歇尔大学）； Datadog AI Research（Datadog人工智能研究）； George Washington University（乔治华盛顿大学）； Purdue University（普渡大学）

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

Comments 61 pages, 15 figures, Preprint

2412.10513 2025-10-08 cs.AI cs.LG 81%

Extracting PAC Decision Trees from Black Box Binary Classifiers: The Gender Bias Case Study on BERT-based Language Models

Ana Ozaki, Roberto Confalonieri, Ricardo Guimarães, Anders Imenes

机构 * Universitetet i Oslo, Norway（奥斯陆大学）； Universita degli Studi di Padova, Italy（帕多瓦大学）； Universitetet i Bergen, Norway（卑尔根大学）

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

Comments This is a revision of the version published at AAAI 2025. We fixed an issue in Theorem 8 and run again all the experiments. We also fixed small grammar mistakes found while producing this revised version

2501.12266 2025-10-07 cs.CV cs.AI cs.CL 81%

CBVLM: Training-free Explainable Concept-based Large Vision Language Models for Medical Image Classification

Cristiano Patrício, Isabel Rio-Torto, Jaime S. Cardoso, Luís F. Teixeira, João C. Neves

机构 * INESC TEC ； NOVA LINCS ； Universidade da Beira Interior（贝拉蒙特大学）； Universidade do Porto（波尔图大学）

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

Comments Accepted for publication in Computers in Biology and Medicine

2509.25568 2025-10-01 cs.CL cs.AI 81%

Probing the Limits of Stylistic Alignment in Vision-Language Models

Asma Farajidizaji, Akash Gupta, Vatsal Raina

机构 * Imperial College London（伦敦帝国学院）； Apta AI

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

Comments 5 pages, 1 figure, 3 tables

2509.20977 2025-09-26 cs.LG cs.CL 81%

CLUE: Conflict-guided Localization for LLM Unlearning Framework

Hang Chen, Jiaying Zhu, Xinyu Yang, Wenya Wang

机构 * Hang Chen School of Computer Science and Technology Xi’an Jiaotong University（陈hang 硕士生计算机科学与技术学院西安交通大学）； Jiaying Zhu School of Computer Science and Engineering The Chinese University of Hong Kong（朱纪莹计算机科学与工程学院香港中文大学）； Xinyu Yang School of Computer Science and Technology Xi’an Jiaotong University（杨新宇硕士生计算机科学与技术学院西安交通大学）； Wenya Wang School of Computer Science and Engineering Nanyang Technological University（王文亚计算机科学与工程学院新加坡国立大学）

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

Comments 10 pages

2509.19563 2025-09-25 cs.CL cs.LG 81%

Uncertainty in Semantic Language Modeling with PIXELS

Stefania Radu, Marco Zullich, Matias Valdenegro-Toro

机构 * Department of Artificial Intelligence, Bernoulli Institute, University of Groningen（人工智能系、伯努利研究所、 Groningen大学）

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

Comments 9 pages, 6 figures, UncertaiNLP 2025 Workshop @ EMNLP Camera Ready

2509.17481 2025-09-23 cs.CV cs.AI cs.CL 81%

ChartHal: A Fine-grained Framework Evaluating Hallucination of Large Vision Language Models in Chart Understanding

Xingqi Wang, Yiming Cui, Xin Yao, Shijin Wang, Guoping Hu, Xiaoyu Qin

机构 * Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）； State Key Laboratory of Cognitive Intelligence, iFLYTEK（认知智能国家重点实验室）

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

2509.12650 2025-09-17 cs.LG cs.AI 81%

Leveraging Intermediate Representations of Time Series Foundation Models for Anomaly Detection

Chan Sik Han, Keon Myung Lee

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

Comments 10 pages,8 figures

2411.09689 2025-09-17 cs.AI cs.CL 81%

Probing LLM Hallucination from Within: Perturbation-Driven Approach via Internal Knowledge

Seongmin Lee, Hsiang Hsu, Chun-Fu Chen, Duen Horng Chau

机构 * Georgia Institute of Technology（佐治亚理工学院）； JPMorganChase Global Technology Applied Research（摩根大通全球科技应用研究）

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

Comments 22 pages, 15 figures

2508.16969 2025-08-26 cs.CL cs.AI cs.DB 81%

Explaining Black-box Language Models with Knowledge Probing Systems: A Post-hoc Explanation Perspective

Yunxiao Zhao, Hao Xu, Zhiqiang Wang, Xiaoli Li, Jiye Liang, Ru Li

机构 * School of Computer and Information Technology, Shanxi University, China（山西大学计算机与信息学院）； Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, Shanxi University, China（教育部计算智能与中文信息处理重点实验室）； Institute for Infocomm Research, A*Star, Singapore（A*Star信息与通信研究所）

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

Comments 16 pages, 8 figures. This paper has been accepted by DASFAA 2025: The 30th International Conference on Database Systems for Advanced Applications

2504.07402 2025-08-19 cs.LG cs.AI 81%

LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Models

Beilong Tang, Bang Zeng, Ming Li

机构 * Duke Kunshan University（杜克昆山大学）

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

Comments 8 pages, 5 figure, accepted by 2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

2508.00881 2025-08-05 cs.LG cs.CL 81%

Hallucination Detection and Mitigation with Diffusion in Multi-Variate Time-Series Foundation Models

Vijja Wichitwechkarn, Charles Fox, Ruchi Choudhary

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

2507.07505 2025-07-16 cs.CL cs.AI 81%

Hallucination Stations: On Some Basic Limitations of Transformer-Based Language Models

Varin Sikka, Vishal Sikka

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

Comments 6 pages; to be submitted to AAAI-26 after reviews

2507.10000 2025-07-15 cs.AI cs.CL 81%

On The Role of Intentionality in Knowledge Representation: Analyzing Scene Context for Cognitive Agents with a Tiny Language Model

Mark Burgess

机构 * Mark Burgess（独立研究者）

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

2408.05920 2025-07-04 cs.AI cs.LG 81%

Urban Region Pre-training and Prompting: A Graph-based Approach

Jiahui Jin, Yifan Song, Dong Kan, Haojia Zhu, Xiangguo Sun, Zhicheng Li, Xigang Sun, Jinghui Zhang

机构 * School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）

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

Comments Accepted at KDD 2025

2502.03628 2025-07-02 cs.CV cs.AI cs.LG 81%

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Zhuowei Li, Haizhou Shi, Yunhe Gao, Di Liu, Zhenting Wang, Yuxiao Chen, Ting Liu, Long Zhao, Hao Wang, Dimitris N. Metaxas

机构 * Rutgers University（罗格斯大学）； Stanford University（斯坦福大学）； Google DeepMind（谷歌DeepMind）

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

2411.06660 2025-07-01 cs.CL cs.LG 81%

Bridge: A Unified Framework to Knowledge Graph Completion via Language Models and Knowledge Representation

Qiao Qiao, Yuepei Li, Qing Wang, Kang Zhou, Qi Li

机构 * Iowa State University（爱荷华州立大学）

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

2506.17748 2025-06-24 cs.CL cs.AI 81%

HIDE and Seek: Detecting Hallucinations in Language Models via Decoupled Representations

Anwoy Chatterjee, Yash Goel, Tanmoy Chakraborty

机构 * Indian Institute of Technology Delhi, India（印度德里印度理工学院）

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

2410.01434 2025-06-24 cs.LG cs.CL 81%

Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models

Philipp Mondorf, Sondre Wold, Barbara Plank

机构 * MaiNLP, Center for Information and Language Processing, LMU Munich（MaiNLP、信息与语言处理中心、慕尼黑大学）； Munich Center for Machine Learning (MCML), Munich（慕尼黑机器学习中心）； Language Technology Group, University of Oslo（语言技术组、奥斯陆大学）

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

Comments ACL 2025 main, 22 pages, 21 figures

1. 知识编辑与模型理解 7550 篇

Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation

Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamics

AILA--First Experiments with Localist Language Models

ParaScopes: What do Language Models Activations Encode About Future Text?

Towards Automated Semantic Interpretability in Reinforcement Learning via Vision-Language Models

FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge

Pre-trained Language Models Learn Remarkably Accurate Representations of Numbers

Do Prompts Reshape Representations? An Empirical Study of Prompting Effects on Embeddings

A Multi-Task Foundation Model for Wireless Channel Representation Using Contrastive and Masked Autoencoder Learning

LAMP-PRo: Label-aware Attention for Multi-label Prediction of DNA- and RNA-binding Proteins using Protein Language Models

To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models

A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models

Extracting PAC Decision Trees from Black Box Binary Classifiers: The Gender Bias Case Study on BERT-based Language Models

CBVLM: Training-free Explainable Concept-based Large Vision Language Models for Medical Image Classification

Probing the Limits of Stylistic Alignment in Vision-Language Models

CLUE: Conflict-guided Localization for LLM Unlearning Framework

Uncertainty in Semantic Language Modeling with PIXELS

ChartHal: A Fine-grained Framework Evaluating Hallucination of Large Vision Language Models in Chart Understanding

Leveraging Intermediate Representations of Time Series Foundation Models for Anomaly Detection

Probing LLM Hallucination from Within: Perturbation-Driven Approach via Internal Knowledge

Explaining Black-box Language Models with Knowledge Probing Systems: A Post-hoc Explanation Perspective

LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Models

Hallucination Detection and Mitigation with Diffusion in Multi-Variate Time-Series Foundation Models

Hallucination Stations: On Some Basic Limitations of Transformer-Based Language Models

On The Role of Intentionality in Knowledge Representation: Analyzing Scene Context for Cognitive Agents with a Tiny Language Model

Urban Region Pre-training and Prompting: A Graph-based Approach

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Bridge: A Unified Framework to Knowledge Graph Completion via Language Models and Knowledge Representation

HIDE and Seek: Detecting Hallucinations in Language Models via Decoupled Representations

Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models