语言大模型 / LLM - arXivDaily 专题

2505.15356 2025-10-30 cs.CL 77%

NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging

Weiming Zhang, Qingyao Li, Xinyi Dai, Jizheng Chen, Kounianhua Du, Weiwen Liu, Yasheng Wang, Ruiming Tang, Yong Yu, Weinan Zhang

机构 * Shanghai Jiao Tong University（上海交通大学）； Huawei Noah’s Ark Lab Shanghai（华为诺亚实验室）

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

2405.05583 2025-10-30 cs.CL 77%

OpenFactCheck: Building, Benchmarking Customized Fact-Checking Systems and Evaluating the Factuality of Claims and LLMs

Yuxia Wang, Minghan Wang, Hasan Iqbal, Georgi Georgiev, Jiahui Geng, Preslav Nakov

机构 * MBZUAI ； Monash University（墨尔本大学）； Sofia University（索菲亚大学）

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

Comments 23 pages, 8 tables, 11 figures, Published In Proceedings of the 31st International Conference on Computational Linguistics 2025

Journal ref In Proceedings of the 31st International Conference on Computational Linguistics 2025, pages 11399-11421, Abu Dhabi, UAE. Association for Computational Linguistics

2510.24120 2025-10-29 cs.LG 77%

Graph-Guided Concept Selection for Efficient Retrieval-Augmented Generation

Ziyu Liu, Yijing Liu, Jianfei Yuan, Minzhi Yan, Le Yue, Honghui Xiong, Yi Yang

机构 * Huawei Cloud Computing Technology Co., Ltd, China（华为云计算技术有限公司，中国）

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.LG

2510.19661 2025-10-27 cs.AI 77%

AgentSense: LLMs Empower Generalizable and Explainable Web-Based Participatory Urban Sensing

Xusen Guo, Mingxing Peng, Xixuan Hao, Xingchen Zou, Qiongyan Wang, Sijie Ruan, Yuxuan Liang

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； Beijing Institute of Technology（北京理工大学）

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.AI

Comments 13 pages, 10 pages

2510.20296 2025-10-24 cs.DB cs.AI 77%

RAG-Stack: Co-Optimizing RAG Quality and Performance From the Vector Database Perspective

Wenqi Jiang

机构 * Systems Group, ETH Zurich（苏黎世联邦理工学院系统组）

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.AI

2510.13163 2025-10-16 cs.CL 77%

A Matter of Representation: Towards Graph-Based Abstract Code Generation

Nyx Iskandar, Hisham Bedri, Andy Tsen

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

2510.12233 2025-10-15 cs.LG 77%

Unveiling the Vulnerability of Graph-LLMs: An Interpretable Multi-Dimensional Adversarial Attack on TAGs

Bowen Fan, Zhilin Guo, Xunkai Li, Yihan Zhou, Bing Zhou, Zhenjun Li, Rong-Hua Li, Guoren Wang

机构 * Beijing Institute of Technology（北京理工大学）； Shandong University（山东大学）； Shenzhen Institute of Technology（深圳理工大学）

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.LG

Comments 12 pages, 4 figures

2510.11016 2025-10-14 cs.LG 77%

Instruction-aware User Embedding via Synergistic Language and Representation Modeling

Ziyi Gao, Yike Xu, Jiahao Yuan, Baokun Wang, Jinyong Wen, Xiaotong Lin, Yun Liu, Xing Fu, Yu Cheng, Yongchao Liu, Weiqiang Wang, Zhongle Xie

机构 * Zhejiang University（浙江大学）

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

2510.08389 2025-10-10 cs.AI 77%

Revisiting Hallucination Detection with Effective Rank-based Uncertainty

Rui Wang, Zeming Wei, Guanzhang Yue, Meng Sun

机构 * Peking University（北京大学）

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.AI

2510.06541 2025-10-09 cs.CV cs.LG 77%

Cluster Paths: Navigating Interpretability in Neural Networks

Nicholas M. Kroeger, Vincent Bindschaedler

机构 * Department of Computer Science University of Florida（计算机科学系佛罗里达大学）

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

2510.06457 2025-10-09 cs.HC cs.AI 77%

Evaluating Node-tree Interfaces for AI Explainability

Lifei Wang, Natalie Friedman, Chengchao Zhu, Zeshu Zhu, S. Joy Mountford

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.AI

Comments 5 pages, 2 figures. Accepted to the 3rd Workshop on Explainability in Human-Robot Collaboration: Real-World Concerns (XHRI 2025), scheduled for March 3, 2025, Hybrid (Melbourne and online) as part of HRI 2025

2510.04849 2025-10-07 cs.CL 77%

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

Elisei Rykov, Kseniia Petrushina, Maksim Savkin, Valerii Olisov, Artem Vazhentsev, Kseniia Titova, Alexander Panchenko, Vasily Konovalov, Julia Belikova

机构 * Skoltech ； AIRI ； MWS AI ； Sber AI Lab ； Moscow Institute of Physics and Technology（莫斯科物理技术学院）

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

2510.04439 2025-10-07 cs.CL 77%

On the Role of Unobserved Sequences on Sample-based Uncertainty Quantification for LLMs

Lucie Kunitomo-Jacquin, Edison Marrese-Taylor, Ken Fukuda

机构 * National Institute of Advanced Industrial Science and Technology (AIST)（国家先进工业科学与技术研究院）

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

Comments Accepted to UncertaiNLP workshop of EMNLP 2025

2510.00296 2025-10-02 cs.LG 77%

Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT

Guy Bar-Shalom, Fabrizio Frasca, Yaniv Galron, Yftah Ziser, Haggai Maron

机构 * Technion（技术离子大学）； University of Groningen（格罗宁根大学）； Nvidia Research（英伟达研究）

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.LG

Comments Published in NeurIPS 2025

2509.26116 2025-10-01 cs.LG cs.CE 77%

UncertainGen: Uncertainty-Aware Representations of DNA Sequences for Metagenomic Binning

Abdulkadir Celikkanat, Andres R. Masegosa, Mads Albertsen, Thomas D. Nielsen

机构 * Aalborg University（奥尔堡大学）

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.LG

2411.15993 2025-09-26 cs.CL 77%

Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown

Lifu Tu, Rui Meng, Shafiq Joty, Yingbo Zhou, Semih Yavuz

机构 * Salesforce AI Research（Salesforce人工智能研究）

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

2509.19839 2025-09-25 cs.AI 77%

LatentGuard: Controllable Latent Steering for Robust Refusal of Attacks and Reliable Response Generation

Huizhen Shu, Xuying Li, Zhuo Li

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.AI

Comments 9-page NeurIPS 2025 preprint including 3 figures and 1 table, with additional appendix material. Prepared using the NeurIPS 2025 preprint template and compiled with pdfLaTeX. All references are included via the provided .bbl file. Figures are in PDF format. No external supplementary files. All necessary style files and images are included

2509.19745 2025-09-25 cs.CL cs.SD 77%

PART: Progressive Alignment Representation Training for Multilingual Speech-To-Text with LLMs

Pei Zhang, Andong Chen, Xi Chen, Baosong Yang, Derek F. Wong, Fei Huang

机构 * Tongyi Lab, Alibaba Group（通义实验室，阿里巴巴集团）； The Chinese University of Hong Kong（香港中文大学）； NLP 2 CT Lab, University of Macau（自然语言处理2CT实验室，澳门大学）

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

2509.15667 2025-09-22 cs.CL cs.SD eess.AS 77%

VOX-KRIKRI: Unifying Speech and Language through Continuous Fusion

Dimitrios Damianos, Leon Voukoutis, Georgios Paraskevopoulos, Vassilis Katsouros

机构 * Institute for Speech and Language Processing, Athena Research Center, Greece（语音与语言处理研究所，亚特兰蒂斯研究中心，希腊）

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

2509.12661 2025-09-17 cs.CL 77%

Mitigating Strategy Preference Bias in Emotional Support Conversation via Uncertainty Estimations

Yougen Zhou, Qin Chen, Ningning Zhou, Jie Zhou, Xingjiao Wu, Liang He

机构 * Shanghai Institute of Artificial Intelligence for Education（上海人工智能教育研究院）； School of Computer Science and Technology（计算机科学与技术学院）； School of Psychology and Cognitive Science（心理学与认知科学学院）； School of Pharmacy（药学院）

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

2509.11369 2025-09-16 cs.LG 77%

Decoding Musical Origins: Distinguishing Human and AI Composers

Cheng-Yang Tsai, Tzu-Wei Huang, Shao-Yu Wei, Guan-Wei Chen, Hung-Ying Chu, Yu-Cheng Lin

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.LG

2509.10875 2025-09-16 cs.AI cond-mat.soft 77%

Is the `Agent' Paradigm a Limiting Framework for Next-Generation Intelligent Systems?

Jesse Gardner, Vladimir A. Baulin

机构 * Active Inference Institute（主动推断研究所）

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.AI

2509.07190 2025-09-10 cs.CL cs.HC 77%

Rule-Based Moral Principles for Explaining Uncertainty in Natural Language Generation

Zahra Atf, Peter R Lewis

机构 * Faculty of Business and Information Technology（商业与信息技术学院）； Ontario Tech University（安大略技术大学）

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

Comments This paper was accepted for presentation at the 35th IEEE International Conference on Collaborative Advances in Software and Computing. Conference website:https://conf.researchr.org/home/cascon-2025

2509.00328 2025-09-03 cs.RO cs.LG 77%

Mechanistic interpretability for steering vision-language-action models

Bear Häon, Kaylene Stocking, Ian Chuang, Claire Tomlin

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

Comments CoRL 2025. Project website: https://vla-mech-interp.github.io/

2501.04648 2025-09-03 cs.GR cs.CL cs.CV 77%

FlairGPT: Repurposing LLMs for Interior Designs

Gabrielle Littlefair, Niladri Shekhar Dutt, Niloy J. Mitra

机构 * University College London（伦敦大学学院）； Adobe Research（Adobe研究院）

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

Comments EUROGRAPHICS 2025

2508.21238 2025-09-01 cs.AI 77%

Addressing accuracy and hallucination of LLMs in Alzheimer's disease research through knowledge graphs

Tingxuan Xu, Jiarui Feng, Justin Melendez, Kaleigh Roberts, Donghong Cai, Mingfang Zhu, Donald Elbert, Yixin Chen, Randall J. Bateman

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.AI

2508.20578 2025-08-29 cs.AI cs.CR 77%

Human-AI Collaborative Bot Detection in MMORPGs

Jaeman Son, Hyunsoo Kim

机构 * NCSOFT

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.AI

2502.12964 2025-08-26 cs.CL 77%

Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer

Adi Simhi, Itay Itzhak, Fazl Barez, Gabriel Stanovsky, Yonatan Belinkov

机构 * Technion – Israel Institute of Technology（技术ion-以色列理工学院）； University of Oxford and WhiteBox（牛津大学和WhiteBox）； School of Computer Science and Engineering, The Hebrew University of Jerusalem（耶路撒冷希伯来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：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2508.17735 2025-08-26 cs.CL 77%

SMITE: Enhancing Fairness in LLMs through Optimal In-Context Example Selection via Dynamic Validation

Garima Chhikara, Kripabandhu Ghosh, Abhijnan Chakraborty

机构 * Indian Institute of Technology Delhi, India（印度德里理工学院）； Delhi Technological University, India（德里技术大学）； Indian Institute of Science Education and Research Kolkata, India（印度科学教育与研究学院科希拉分校）； Indian Institute of Technology Kharagpur, India（印度理工学院哈里科格分校）

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

2411.16252 2025-08-19 cs.CL 77%

NormXLogit: The Head-on-Top Never Lies

Sina Abbasi, Mohammad Reza Modarres, Mohammad Taher Pilehvar

机构 * Tehran Institute for Advanced Studies, Khatam University, Iran（泰赫兰高级研究院，卡坦大学，伊朗）； Cardiff University（卡迪夫大学）

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

Comments Added comparisons on computational efficiency, included experiments on a new dataset with an additional evaluation metric for classification tasks, expanded explanations and discussions in the experiments, and presented a worked example for alignment metrics computation

1. 知识编辑与模型理解 7583 篇

NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging

OpenFactCheck: Building, Benchmarking Customized Fact-Checking Systems and Evaluating the Factuality of Claims and LLMs

Graph-Guided Concept Selection for Efficient Retrieval-Augmented Generation

AgentSense: LLMs Empower Generalizable and Explainable Web-Based Participatory Urban Sensing

RAG-Stack: Co-Optimizing RAG Quality and Performance From the Vector Database Perspective

A Matter of Representation: Towards Graph-Based Abstract Code Generation

Unveiling the Vulnerability of Graph-LLMs: An Interpretable Multi-Dimensional Adversarial Attack on TAGs

Instruction-aware User Embedding via Synergistic Language and Representation Modeling

Revisiting Hallucination Detection with Effective Rank-based Uncertainty

Cluster Paths: Navigating Interpretability in Neural Networks

Evaluating Node-tree Interfaces for AI Explainability

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

On the Role of Unobserved Sequences on Sample-based Uncertainty Quantification for LLMs

Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT

UncertainGen: Uncertainty-Aware Representations of DNA Sequences for Metagenomic Binning

Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown

LatentGuard: Controllable Latent Steering for Robust Refusal of Attacks and Reliable Response Generation

PART: Progressive Alignment Representation Training for Multilingual Speech-To-Text with LLMs

VOX-KRIKRI: Unifying Speech and Language through Continuous Fusion

Mitigating Strategy Preference Bias in Emotional Support Conversation via Uncertainty Estimations

Decoding Musical Origins: Distinguishing Human and AI Composers

Is the `Agent' Paradigm a Limiting Framework for Next-Generation Intelligent Systems?

Rule-Based Moral Principles for Explaining Uncertainty in Natural Language Generation

Mechanistic interpretability for steering vision-language-action models

FlairGPT: Repurposing LLMs for Interior Designs

Addressing accuracy and hallucination of LLMs in Alzheimer's disease research through knowledge graphs

Human-AI Collaborative Bot Detection in MMORPGs

Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer

SMITE: Enhancing Fairness in LLMs through Optimal In-Context Example Selection via Dynamic Validation

NormXLogit: The Head-on-Top Never Lies