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。

2025-09-16 至 2025-09-16 共收录 17 信号源:cs.CL, cs.AI, cs.LG

1. 知识编辑与模型理解 17 篇

2505.23657 2025-09-16 cs.CL cs.AI cs.LG 89%

Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation

Hongxiang Zhang, Hao Chen, Muhao Chen, Tianyi Zhang

机构 * Purdue University(普渡大学) University of California, Davis(加州大学戴维斯分校)

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.CL、cs.AI、cs.LG

Comments 19 pages, 3 figures, EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.11952 2025-09-16 cs.CV 88%

CLAIRE: A Dual Encoder Network with RIFT Loss and Phi-3 Small Language Model Based Interpretability for Cross-Modality Synthetic Aperture Radar and Optical Land Cover Segmentation

Debopom Sutradhar, Arefin Ittesafun Abian, Mohaimenul Azam Khan Raiaan, Reem E. Mohamed, Sheikh Izzal Azid, Sami Azam

机构 * Department of Computer Science and Engineering, United International University(计算机科学与工程系,国际大学) Faculty of Science and Information Technology, Charles Darwin University(科学与信息技术学院,查尔斯·达尔文大学) School of Engineering and Energy , Murdoch University(工程与能源学院,默多尼大学) Faculty of Science and Technology, Charles Darwin University(科学与技术学院,查尔斯·达尔文大学)

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

Comments 23 pages, 6 figures, 10 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.09931 2025-09-16 cs.LG cs.AI 86%

Mechanistic Interpretability of LoRA-Adapted Language Models for Nuclear Reactor Safety Applications

Yoon Pyo Lee

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、cs.LG

Comments Accepted for publication in Nuclear Technology. 24 pages, 2 tables, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.12065 2025-09-16 cs.CL 83%

Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect

Alina Klerings, Jannik Brinkmann, Daniel Ruffinelli, Simone Ponzetto

机构 * University of Mannheim(曼海姆大学) Technical University Clausthal(克劳斯泰尔大学)

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

Comments to be published in The 2025 Conference on Empirical Methods in Natural Language Processing

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.11986 2025-09-16 cs.CV cs.CL 79%

Lost in Embeddings: Information Loss in Vision-Language Models

Wenyan Li, Raphael Tang, Chengzu Li, Caiqi Zhang, Ivan Vulić, Anders Søgaard

机构 * University of Copenhagen(哥本哈根大学) Microsoft(微软) University of Cambridge(剑桥大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.11287 2025-09-16 cs.CV cs.CL 79%

Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations

Yifan Lu, Ziqi Zhang, Chunfeng Yuan, Jun Gao, Congxuan Zhang, Xiaojuan Qi, Bing Li, Weiming Hu

机构 * Beijing Key Laboratory of Super Intelligent Security of Multi-Modal Information, CASIA(北京多模态信息超级智能安全重点实验室,中国科学院自动化所) State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA(多模态人工智能系统国家重点实验室,中国科学院自动化所) School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院) Hello Group(Hello集团) Nanchang Hangkong University(南昌航空大学) The University of Hong Kong(香港大学) School of Information Science and Technology, ShanghaiTech University(上海科技大学信息科学与技术学院)

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

Comments emnlp 2025 accepted

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.07233 2025-09-16 eess.AS cs.CL 79%

Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding

Tzu-wen Hsu, Ke-Han Lu, Cheng-Han Chiang, Hung-yi Lee

机构 * Purdue University(普渡大学) National Taiwan University(国立台湾大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
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

详情

展开后加载摘要…

URL PDF HTML 收藏
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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.04335 2025-09-16 cs.CL cs.AI cs.LG 75%

Hallucinated Span Detection with Multi-View Attention Features

Yuya Ogasa, Yuki Arase

机构 * Grad. Sch. of Information Science and Tech.(信息科学与技术研究生院) The University of Osaka(大阪大学) School of Computing(计算学部) Institute of Science(科学研究所) LY Corporation(LY公司)

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、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.03106 2025-09-16 cs.CL cs.LG 73%

Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation

Yurui Chang, Bochuan Cao, Lu Lin

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.LG

Comments Accepted to ACL 2025 (Findings)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.11915 2025-09-16 cs.CL 70%

Uncertainty in Authorship: Why Perfect AI Detection Is Mathematically Impossible

Aadil Gani Ganie

机构 * UNIVERSITAT POLITECNICA DE VALENCIA(瓦伦西亚理工大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.11569 2025-09-16 cs.CL 70%

D$^2$HScore: Reasoning-Aware Hallucination Detection via Semantic Breadth and Depth Analysis in LLMs

Yue Ding, Xiaofang Zhu, Tianze Xia, Junfei Wu, Xinlong Chen, Qiang Liu, Liang Wang

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

Comments under review

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.16146 2025-09-16 cs.CV cs.AI cs.CL cs.LG 67%

Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation

Zhenglin Hua, Jinghan He, Zijun Yao, Tianxu Han, Haiyun Guo, Yuheng Jia, Junfeng Fang

机构 * School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院) Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University)(东南大学新一代人工智能技术及其交叉应用关键实验室) Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所基础模型研究中心) School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院) Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系) Wuhan University of Technology(武汉理工大学) National University of Singapore(新加坡国立大学)

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

Comments Accepted to Findings of EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.07082 2025-09-16 cs.CV cs.AI cs.LG 62%

On the Generalization of Representation Uncertainty in Earth Observation

Spyros Kondylatos, Nikolaos Ioannis Bountos, Dimitrios Michail, Xiao Xiang Zhu, Gustau Camps-Valls, Ioannis Papoutsis

机构 * National Observatory of Athens(雅典国家天文台) National Technical University of Athens(雅典技术大学) University of Valencia(瓦伦西亚大学) Harokopio University of Athens(雅典惠克罗波利斯大学) Technical University of Munich(慕尼黑技术大学) Munich Center for Machine Learning(慕尼黑机器学习中心) Archimedes/Athena RC(阿基米德/雅典RC)

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

Comments Accepted to ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.12039 2025-09-16 cs.CV 50%

RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration

Zilong Zhang, Chujie Qin, Chunle Guo, Yong Zhang, Chao Xue, Ming-Ming Cheng, Chongyi Li

机构 * VCIP, CS, Nankai University(VCIP、计算机科学系、南开大学) Chongqing Chang’an Wangjiang Industrial Group Co., Ltd(重庆长安王江工业集团有限公司) Tiandy Technologies(天鼎科技)

专题命中 知识编辑与模型理解 :pretraining(abstract)

Comments 18 pages, 22 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.22104 2025-09-16 eess.AS 50%

M2D-CLAP: Exploring General-purpose Audio-Language Representations Beyond CLAP

Daisuke Niizumi, Daiki Takeuchi, Masahiro Yasuda, Binh Thien Nguyen, Yasunori Ohishi, Noboru Harada

专题命中 知识编辑与模型理解 :LLM(abstract)

Comments Formerly M2D2, reverted to M2D-CLAP. 15 pages, 7 figures, 13 tables. Accepted by IEEE Access

详情

展开后加载摘要…

URL PDF HTML 收藏