arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

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。

2025-09-03 至 2025-09-03 共收录 21 信号源:cs.CL, cs.AI, cs.LG

1. 知识编辑与模型理解 21 篇

2508.08100 2025-09-03 cs.LG cs.AI 90%

Grid2Guide: A* Enabled Small Language Model for Indoor Navigation

Md. Wasiul Haque, Sagar Dasgupta, Mizanur Rahman

机构 * The University of Alabama(阿拉巴马大学)

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

Comments 17 pages, 9 figures, 6 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.10722 2025-09-03 cs.CL cs.AI 88%

MEGen: Generative Backdoor into Large Language Models via Model Editing

Jiyang Qiu, Xinbei Ma, Zhuosheng Zhang, Hai Zhao, Yun Li, Qianren Wang

机构 * School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机科学学院) Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University(上海交通大学智能交互与认知工程重点实验室) Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3(上海Web3可信数据流通与治理重点实验室) Cognitive AI Lab(认知人工智能实验室)

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、cs.AI

Comments ACL 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00918 2025-09-03 cs.CR 88%

PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement

Xubin Yue, Zhenhua Xu, Wenpeng Xing, Jiahui Yu, Mohan Li, Meng Han

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.17182 2025-09-03 cs.LG cs.AI cs.CL 87%

LLM Assertiveness can be Mechanistically Decomposed into Emotional and Logical Components

Hikaru Tsujimura, Arush Tagade

机构 * Department of Psychology, Cardiff University(心理学系,卡迪夫大学) Department of Computer Science, George Washington University(计算机科学系,乔治华盛顿大学)

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、cs.AI、cs.LG

Comments This preprint is under review

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00099 2025-09-03 cs.LG quant-ph 85%

LLM-QUBO: An End-to-End Framework for Automated QUBO Transformation from Natural Language Problem Descriptions

Huixiang Zhang, Mahzabeen Emu, Salimur Choudhury

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.12225 2025-09-03 cs.CL cs.CY cs.IR 85%

Interpretation Gaps in LLM-Assisted Comprehension of Privacy Documents

Rinku Dewri

机构 * Department of Computer Science, University of Denver, CO, 80208, USA(计算机科学系,丹佛大学)

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 Minor revision

Journal ref IEEE Computer, 58:9, pp. 70-79, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00673 2025-09-03 cs.CL cs.AI cs.IR 84%

Confident, Calibrated, or Complicit: Probing the Trade-offs between Safety Alignment and Ideological Bias in Language Models in Detecting Hate Speech

Sanjeeevan Selvaganapathy, Mehwish Nasim

机构 * School of Physics, Mathematics and Computing(物理、数学与计算学系) Network Analysis and Social Influence Modelling (NASIM) Lab(网络分析与社会影响建模实验室) The University of Western Australia(西澳大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00723 2025-09-03 cs.AI cs.MM 83%

OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination

Junzhe Chen, Tianshu Zhang, Shiyu Huang, Yuwei Niu, Chao Sun, Rongzhou Zhang, Guanyu Zhou, Lijie Wen, Xuming Hu

机构 * Tsinghua University(清华大学) The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) OpenRL Chongqing University(重庆大学)

专题命中 知识编辑与模型理解 :preference optimization(title);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
2508.14086 2025-09-03 cs.LG 81%

EEGDM: EEG Representation Learning via Generative Diffusion Model

Jia Hong Puah, Sim Kuan Goh, Ziwei Zhang, Zixuan Ye, Chow Khuen Chan, Kheng Seang Lim, Si Lei Fong, Kok Sin Woon, Cuntai Guan

机构 * School of Artificial Intelligence and Robotics, Xiamen University Malaysia(厦门大学马来西亚分校人工智能与机器人学院) School of Energy and Chemical Engineering, Xiamen University Malaysia(厦门大学马来西亚分校能源与化学工程学院) Department of Biomedical Engineering, Universiti Malaya(马来亚大学生物医学工程系) Department of Medicine, Universiti Malaya(马来亚大学医学系) Thrust of Carbon Neutrality and Climate Change, Hong Kong University of Science and Technology (Guangzhou)(香港科学与艺术大学(广州)碳中和与气候变化研究方向) College of Computing & Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院)

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

Comments EEGDM Preprint 10 Pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00132 2025-09-03 cs.SD cs.AI cs.MM eess.AS 79%

CoComposer: LLM Multi-agent Collaborative Music Composition

Peiwen Xing, Aske Plaat, Niki van Stein

机构 * LIACS, Leiden University, Netherlands(莱顿大学莱顿信息与计算科学研究中心)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.02075 2025-09-03 cs.CL cs.AI 79%

How Instruction-Tuning Imparts Length Control: A Cross-Lingual Mechanistic Analysis

Elisabetta Rocchetti, Alfio Ferrara

机构 * Università degli Studi di Milano, Department of Computer Science(米兰大学计算机科学系)

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.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00314 2025-09-03 eess.SP 78%

CoMET: A Contrastive-Masked Brain Foundation Model for Universal EEG Representation

Ang Li, Zikai Wang, Liuyin Yang, Zhenyu Wang, Tianheng Xu, Honglin Hu, Marc M. Van Hulle

专题命中 知识编辑与模型理解 :foundation model(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
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/

详情

展开后加载摘要…

URL PDF HTML 收藏
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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.08529 2025-09-03 cs.AI cs.CL 73%

A Multi-granularity Concept Sparse Activation and Hierarchical Knowledge Graph Fusion Framework for Rare Disease Diagnosis

Mingda Zhang, Na Zhao, Jianglong Qin, Guoyu Ye, Ruixiang Tang

机构 * School of Software, Yunnan University(云南大学软件学院) Yunnan Key Laboratory of Software Engineering(云南软件工程重点实验室) Yunnan Provincial Hospital of Traditional Chinese Medicine(云南中医药省人民医院)

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

Comments 12 pages,3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.21484 2025-09-03 q-bio.QM cs.LG stat.ML 70%

Data-driven Discovery of Digital Twins in Biomedical Research

Clémence Métayer, Annabelle Ballesta, Julien Martinelli

机构 * Inserm U1331, Institut Curie Saint-Cloud, France(法国国家医学研究院U1331,圣克鲁医院) Aalto University Espoo, Finland(芬兰艾尔托大学)

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
2509.02388 2025-09-03 q-fin.ST 67%

Bridging Human Cognition and AI: A Framework for Explainable Decision-Making Systems

N. Jean, G. Le Pera

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

Comments We introduce a practical framework for explainable AI that combines modern interpretability methods with Malle's five-category model of human behavior explanation, illustrated through real-world case studies in credit risk and regulatory analysis

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00371 2025-09-03 cs.CV 67%

Two Causes, Not One: Rethinking Omission and Fabrication Hallucinations in MLLMs

Guangzong Si, Hao Yin, Xianfei Li, Qing Ding, Wenlong Liao, Tao He, Pai Peng

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

Comments Preprint,Underreview

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.02033 2025-09-03 cs.CL 57%

StructCoh: Structured Contrastive Learning for Context-Aware Text Semantic Matching

Chao Xue, Ziyuan Gao

机构 * Beihang University, Beijing, China(北京航空航天大学) University College London, London, UK(伦敦大学学院)

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

Comments Accepted by PRICAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00503 2025-09-03 cs.CL eess.AS 57%

Entropy-based Coarse and Compressed Semantic Speech Representation Learning

Jialong Zuo, Guangyan Zhang, Minghui Fang, Shengpeng Ji, Xiaoqi Jiao, Jingyu Li, Yiwen Guo, Zhou Zhao

机构 * Zhejiang University(浙江大学) LIGHTSPEED Independent Researcher(独立研究者)

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

详情

展开后加载摘要…

URL PDF HTML 收藏