arXivDaily arXiv每日学术速递 周一至周五更新

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。

共收录 7565 信号源:cs.CL, cs.AI, cs.LG

1. 知识编辑与模型理解 7565 篇

2506.05439 2025-09-22 cs.CV cs.AI cs.CL 62%

LLMs Can Compensate for Deficiencies in Visual Representations

Sho Takishita, Jay Gala, Abdelrahman Mohamed, Kentaro Inui, Yova Kementchedjhieva

机构 * Fujitsu Limited(富士通有限公司) MBZUAI Tohoku University(东北大学) RIKEN(日本研究机构)

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

Comments EMNLP 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.17764 2025-09-22 cs.CL cs.AI math.ST stat.TH 62%

BBScoreV2: Learning Time-Evolution and Latent Alignment from Stochastic Representation

Tianhao Zhang, Zhecheng Sheng, Zhexiao Lin, Chen Jiang, Dongyeop Kang

机构 * University of Minnesota, Twin Cities(明尼苏达大学,双城分校) University of California, Berkeley(加州大学伯克利分校)

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

Journal ref The 2025 Conference on Empirical Methods in Natural Language Processing

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
2509.07475 2025-09-10 cs.CL cs.AI 62%

HALT-RAG: A Task-Adaptable Framework for Hallucination Detection with Calibrated NLI Ensembles and Abstention

Saumya Goswami, Siddharth Kurra

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.06509 2025-09-04 cs.CV cs.AI cs.LG 62%

Aligning Machine and Human Visual Representations across Abstraction Levels

Lukas Muttenthaler, Klaus Greff, Frieda Born, Bernhard Spitzer, Simon Kornblith, Michael C. Mozer, Klaus-Robert Müller, Thomas Unterthiner, Andrew K. Lampinen

机构 * Google DeepMind Machine Learning Group(谷歌DeepMind机器学习组) Technische Universität Berlin(技术大学柏林) BIFOLD Berlin Institute for the Foundations of Learning and Data(柏林学习与数据基础研究所) Max Planck Institute for Human Cognitive and Brain Sciences(人类认知与脑科学Max Planck研究所) Max Planck Institute for Human Development(人类发展Max Planck研究所) TUD Dresden University of Technology(德累斯顿技术大学) Anthropic Department of Artificial Intelligence, Korea University(人工智能系,韩国大学) Max Planck Institute for Informatics(信息Max Planck研究所)

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

Comments 91 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.18297 2025-08-27 cs.CV cs.AI cs.CL 62%

Can VLMs Recall Factual Associations From Visual References?

Dhananjay Ashok, Ashutosh Chaubey, Hirona J. Arai, Jonathan May, Jesse Thomason

机构 * University of Southern California(南加州大学) Information Sciences Institute, University of Southern California(信息科学研究所,南加州大学)

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

Comments To appear at EMNLP 2025 (Findings)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.14275 2025-08-21 cs.CL cs.AI 62%

Disentangling concept semantics via multilingual averaging in Sparse Autoencoders

Cliff O'Reilly, Ernesto Jimenez-Ruiz, Tillman Weyde

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.04770 2025-08-12 cs.LG cs.AI q-bio.MN 62%

Bidirectional Hierarchical Protein Multi-Modal Representation Learning

Xuefeng Liu, Songhao Jiang, Chih-chan Tien, Jinbo Xu, Rick Stevens

机构 * Argonne National Laboratory(阿贡国家实验室)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.18651 2025-08-08 cs.CV cs.CL cs.LG 62%

Verbalized Representation Learning for Interpretable Few-Shot Generalization

Cheng-Fu Yang, Da Yin, Wenbo Hu, Heng Ji, Nanyun Peng, Bolei Zhou, Kai-Wei Chang

机构 * University of California, Los Angeles(加州大学洛杉矶分校) University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

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

Comments Accepted to ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03164 2025-08-06 cs.CV cs.AI cs.CL 62%

ChartCap: Mitigating Hallucination of Dense Chart Captioning

Junyoung Lim, Jaewoo Ahn, Gunhee Kim

机构 * Seoul National University(首尔国立大学)

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

Comments ICCV 2025 (Highlight)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.00109 2025-08-04 cs.CL cs.AI 62%

FACTORY: A Challenging Human-Verified Prompt Set for Long-Form Factuality

Mingda Chen, Yang Li, Xilun Chen, Adina Williams, Gargi Ghosh, Scott Yih

机构 * FAIR at Meta(Meta 的 FAIR)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.01533 2025-08-04 cs.LG cs.AI q-bio.BM 62%

Transformers trained on proteins can learn to attend to Euclidean distance

Isaac Ellmen, Constantin Schneider, Matthew I. J. Raybould, Charlotte M. Deane

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

Journal ref Transactions on Machine Learning Research (2025) https://openreview.net/forum?id=mU59bDyqqv

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.22744 2025-07-31 cs.CL cs.AI 62%

Reducing Hallucinations in Summarization via Reinforcement Learning with Entity Hallucination Index

Praveenkumar Katwe, Rakesh Chandra, Balabantaray Kali, Prasad Vittala

机构 * International Institute of Information Technology(国际信息研究所) Informatica Business Solutions(Informatica商务解决方案)

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

Comments 8

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.10503 2025-07-29 cs.CV cs.CL cs.LG 62%

Everything is a Video: Unifying Modalities through Next-Frame Prediction

G. Thomas Hudson, Dean Slack, Thomas Winterbottom, Jamie Sterling, Chenghao Xiao, Junjie Shentu, Noura Al Moubayed

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

Comments 10 pages, 10 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.12769 2025-07-18 cs.CL cs.AI 62%

Synergy: End-to-end Concept Model

Keli Zheng, Zerong Xie

机构 * Institute of Software, Chinese Academy of Science(中国科学院软件研究所) The University of Hong Kong(香港大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.06816 2025-07-09 cs.LG cs.AI 62%

DeepCell: Self-Supervised Multiview Fusion for Circuit Representation Learning

Zhengyuan Shi, Chengyu Ma, Ziyang Zheng, Lingfeng Zhou, Hongyang Pan, Wentao Jiang, Fan Yang, Xiaoyan Yang, Zhufei Chu, Qiang Xu

机构 * Department of Computer Science and Engineering(计算机科学与工程系) The Chinese University of Hong Kong(香港中文大学) Faculty of Electrical Engineering and Computer Science(电气工程与计算机科学学院) Ningbo University(宁波大学) School of Computer Science(计算机科学学院) Hangzhou Dianzi University(杭州电子科技大学) School of Microelectronics(微电子学院) Fudan University(复旦大学) State Key Laboratory of Integrated Chips and System(集成电路与系统国家重点实验室) National Center of Technology Innovation for EDA(EDA技术创新国家中心)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.00579 2025-07-02 cs.CL cs.AI 62%

TUM-MiKaNi at SemEval-2025 Task 3: Towards Multilingual and Knowledge-Aware Non-factual Hallucination Identification

Miriam Anschütz, Ekaterina Gikalo, Niklas Herbster, Georg Groh

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

Comments 6 pages, 3 figures, SemEval-2025 Task 3, ACL

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.06230 2025-07-02 cs.CL cs.AI 62%

Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder

Yingji Zhang, Danilo S. Carvalho, André Freitas

机构 * Department of Computer Science, University of Manchester(曼彻斯特大学计算机科学系) Idiap Research Institute(Idiap研究机构) National Biomarker Centre, CRUK-MI, Univ. of Manchester(国家生物标记中心,CRUK-MI,曼彻斯特大学)

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

Comments CoNLL2025 (Best Paper nomination)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.23869 2025-07-01 cs.SD cs.AI cs.LG eess.AS 62%

Scaling Self-Supervised Representation Learning for Symbolic Piano Performance

Louis Bradshaw, Honglu Fan, Alexander Spangher, Stella Biderman, Simon Colton

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

Comments ISMIR (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.01644 2025-07-01 cs.CL cs.LG 62%

Multimodal Contrastive Representation Learning in Augmented Biomedical Knowledge Graphs

Tien Dang, Viet Thanh Duy Nguyen, Minh Tuan Le, Truong-Son Hy

机构 * University of Alabama at Birmingham(阿拉巴马大学伯明翰分校) Washington University in St. Louis(华盛顿大学圣路易斯分校)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.02648 2025-06-27 cs.LG cs.AI 62%

Representation Learning of Lab Values via Masked AutoEncoders

David Restrepo, Chenwei Wu, Yueran Jia, Jaden K. Sun, Jack Gallifant, Catherine G. Bielick, Yugang Jia, Leo A. Celi

机构 * Massachusetts Institute of Technology (MIT)(麻省理工学院) Université Paris-Saclay(巴黎-萨克雷大学) University of Michigan(密歇根大学) Northeastern University(东北大学) Harvard Medical School(哈佛医学院) Brigham and Women’s Hospital/Dana-Farber Cancer Institute(哈佛医学院-布里特医院/达纳-法伯癌症研究所) Beth Israel Deaconess Medical Center(贝斯以色列医疗中心)

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

Comments 14 pages of main text, 11 appendix

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.08160 2025-06-26 cs.CL cs.LG 62%

On the Role of Context in Reading Time Prediction

Andreas Opedal, Eleanor Chodroff, Ryan Cotterell, Ethan Gotlieb Wilcox

机构 * ETH Zürich(苏黎世联邦理工学院) Max Planck ETH Center for Learning Systems(马克斯·普朗克 ETH 学习系统中心) University of Zürich(苏黎世大学)

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

Comments EMNLP 2024; preprocessing was corrected to exclude variance due to word skipping and the conclusions remain unchanged

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.18259 2025-06-25 cs.CL cs.AI 62%

Detecting Machine-Generated Texts: Not Just "AI vs Humans" and Explainability is Complicated

Jiazhou Ji, Ruizhe Li, Shujun Li, Jie Guo, Weidong Qiu, Zheng Huang, Chiyu Chen, Xiaoyu Jiang, Xinru Lu

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

Comments 19 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.00253 2025-06-10 cs.CL cs.AI cs.CY 62%

Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race

Lihao Sun, Chengzhi Mao, Valentin Hofmann, Xuechunzi Bai

机构 * University of Chicago(芝加哥大学) Rutgers University(罗格斯大学) Allen Institute for AI(人工智能研究所) University of Washington(华盛顿大学)

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

Comments Accepted to ACL 2025 (Main)

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.09631 2025-06-05 cs.LG cs.CL cs.CY 62%

Representation Surgery: Theory and Practice of Affine Steering

Shashwat Singh, Shauli Ravfogel, Jonathan Herzig, Roee Aharoni, Ryan Cotterell, Ponnurangam Kumaraguru

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

Comments Accepted in ICML 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.06262 2025-06-04 cs.LG cs.AI 62%

Dialz: A Python Toolkit for Steering Vectors

Zara Siddique, Liam D. Turner, Luis Espinosa-Anke

机构 * School of Computer Science and Informatics, Cardiff University, United Kingdom(计算机科学与信息学学院,卡迪夫大学,英国) AMPLYFI, United Kingdom(AMPLYFI,英国)

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

Comments Accepted to ACL System Demo 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.19475 2025-06-04 cs.CV cs.AI cs.LG 62%

Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video

Sonia Joseph, Praneet Suresh, Lorenz Hufe, Edward Stevinson, Robert Graham, Yash Vadi, Danilo Bzdok, Sebastian Lapuschkin, Lee Sharkey, Blake Aaron Richards

机构 * Mila Quebec(蒙特利尔大学) McGill University(麦吉尔大学) Meta Université de Montréal(蒙特利尔大学) Imperial College London(伦敦帝国理工学院) Fraunhofer Heinrich Hertz Institute(弗劳恩霍夫 Heinrich Hertz 研究所) Technological University Dublin(都柏林技术大学) Apollo Research(Apollo 研究所)

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

Comments 4 pages, 3 figures, 9 tables. Oral and Tutorial at the CVPR Mechanistic Interpretability for Vision (MIV) Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.00930 2025-06-03 cs.AI cs.CL 62%

Aligning VLM Assistants with Personalized Situated Cognition

Yongqi Li, Shen Zhou, Xiaohu Li, Xin Miao, Jintao Wen, Mayi Xu, Jianhao Chen, Birong Pan, Hankun Kang, Yuanyuan Zhu, Ming Zhong, Tieyun Qian

机构 * School of Computer Science, Wuhan University(武汉大学计算机学院) Zhongguancun Academy(中关村学院)

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

Comments Accepted to ACL 2025 (main), camera-ready version

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.16344 2025-06-03 eess.AS cs.AI cs.CL cs.SD 62%

WhiSPA: Semantically and Psychologically Aligned Whisper with Self-Supervised Contrastive and Student-Teacher Learning

Rajath Rao, Adithya Ganesan, Oscar Kjell, Jonah Luby, Akshay Raghavan, Scott Feltman, Whitney Ringwald, Ryan L. Boyd, Benjamin Luft, Camilo Ruggero, Neville Ryant, Roman Kotov, H. Andrew Schwartz

机构 * Stony Brook University(石溪大学) University of Minnesota(明尼苏达大学) University of Texas at Dallas(德克萨斯大学达拉斯分校) University of Pennsylvania(宾夕法尼亚大学)

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

Comments 16 pages, 8 figures, ACL 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.18053 2025-06-03 cs.CL cs.AI 62%

Neuron Empirical Gradient: Discovering and Quantifying Neurons Global Linear Controllability

Xin Zhao, Zehui Jiang, Naoki Yoshinaga

机构 * The University of Tokyo(东京大学) Institute of Industrial Science, The University of Tokyo(东京大学工业科学研究所)

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

Comments Accepted to ACL 2025 Main, 32 pages

详情

展开后加载摘要…

URL PDF HTML 收藏