语言大模型 / LLM - arXivDaily 专题

2503.21214 2025-12-03 cs.CV cs.CL 79%

VoxRep: Enhancing 3D Spatial Understanding in 2D Vision-Language Models via Voxel Representation

VoxRep：通过体素表示增强2D视觉-语言模型的3D空间理解

Alan Dao, Norapat Buppodom

机构 * Menlo Research（Menlo研究）

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

AI总结本文提出VoxRep方法，通过将体素空间切分为2D切片并输入预训练的视觉-语言模型，实现对3D环境的高效语义理解。

Journal ref Proc. APSIPA ASC 2025, pp. 1464-1469

2512.01405 2025-12-02 cs.LG 79%

Fantastic Features and Where to Find Them: A Probing Method to combine Features from Multiple Foundation Models

非凡特性及其获取方法：一种结合多个基础模型特征的探测方法

Benjamin Ramtoula, Pierre-Yves Lajoie, Paul Newman, Daniele De Martini

机构 * University of Oxford（牛津大学）； Polytechnique Montréal（蒙特利尔理工学院）

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

AI总结 ComBo是一种结合多个基础模型特征的探测方法，通过紧凑表示和轻量级transformer实现高效任务预测，优于现有探测方法并提升模型性能。

Comments Published at NeurIPS 2025

2511.12770 2025-12-01 cs.LG cs.CE 79%

MolEdit: Knowledge Editing for Multimodal Molecule Language Models

MolEdit: 多模态分子语言模型的知识编辑

Zhenyu Lei, Patrick Soga, Yaochen Zhu, Yinhan He, Yushun Dong, Jundong Li

机构 * University of Virginia（弗吉尼亚大学）； Florida State University（佛罗里达州立大学）

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

AI总结 MolEdit通过多专家知识适配器和专家意识编辑切换器，提升多模态分子语言模型的编辑可靠性与局部性，实现分子与描述词的高效互转。

2511.19641 2025-11-26 cs.CV cs.AI 79%

On the Utility of Foundation Models for Fast MRI: Vision-Language-Guided Image Reconstruction

在快速MRI中基础模型的效用：基于视觉-语言的图像重建

Ruimin Feng, Xingxin He, Ronald Mercer, Zachary Stewart, Fang Liu

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

AI总结本文提出利用视觉-语言基础模型通过语义空间优化提升欠采样MRI重建效果，实验表明其在保留解剖结构和提升感知质量方面优于传统方法。

2511.01836 2025-11-25 cs.LG 79%

Priors in Time: Missing Inductive Biases for Language Model Interpretability

时间中的先验：语言模型可解释性中缺失的归纳偏置

Ekdeep Singh Lubana, Can Rager, Sai Sumedh R. Hindupur, Valerie Costa, Greta Tuckute, Oam Patel, Sonia Krishna Murthy, Thomas Fel, Daniel Wurgaft, Eric J. Bigelow, Johnny Lin, Demba Ba, Martin Wattenberg, Fernanda Viegas, Melanie Weber, Aaron Mueller

机构 * Goodfire AI ； Independent（独立）； SEAS, Harvard University（哈佛大学SEAS学院）； EPFL（瑞士联邦理工学院）； Kempner Institute at Harvard University（哈佛大学凯普内研究所）； Department of Psychology, Stanford University（斯坦福大学心理学系）； Department of Psychology, Harvard University（哈佛大学心理学系）； Decode Research ； Boston University（波士顿大学）

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

AI总结本文提出时序特征分析方法，通过引入时序归纳偏置，改进语言模型表示的可解释性，有效区分抽象与新颖信息，克服现有方法的局限。

Comments Preprint

2511.15324 2025-11-20 cs.LG 79%

On the Internal Semantics of Time-Series Foundation Models

Atharva Pandey, Abhilash Neog, Gautam Jajoo

机构 * Kairosity

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

2511.12693 2025-11-18 cs.CV cs.AI 79%

HEDGE: Hallucination Estimation via Dense Geometric Entropy for VQA with Vision-Language Models

Sushant Gautam, Michael A. Riegler, Pål Halvorsen

机构 * Simula Metropolitan Center for Digital Engineering (SimulaMet)（Simula数字工程研究中心）； Oslo Metropolitan University (OsloMet)（奥斯陆 Metropolitan 大学）； Simula Research Laboratory（Simula研究实验室）

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

2501.17047 2025-11-13 cs.CL 79%

How Linguistics Learned to Stop Worrying and Love the Language Models

Richard Futrell, Kyle Mahowald

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

2511.06496 2025-11-11 cs.RO cs.AI cs.CV 79%

A Low-Rank Method for Vision Language Model Hallucination Mitigation in Autonomous Driving

Keke Long, Jiacheng Guo, Tianyun Zhang, Hongkai Yu, Xiaopeng Li

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

2503.11881 2025-11-11 cs.CL 79%

Evaluating Human-LLM Representation Alignment: A Case Study on Affective Sentence Generation for Augmentative and Alternative Communication

Shadab Choudhury, Asha Kumar, Lara J. Martin

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

Comments Published at IJCNLP-AACL 2025 Findings

2510.25807 2025-10-31 q-bio.GN cs.LG 79%

Discovering Interpretable Biological Concepts in Single-cell RNA-seq Foundation Models

Charlotte Claye, Pierre Marschall, Wassila Ouerdane, Céline Hudelot, Julien Duquesne

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

2510.22127 2025-10-28 cs.CV cs.LG 79%

Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions

Wenxuan Bao, Ruxi Deng, Jingrui He

机构 * 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(title,abstract)；分类 cs.LG

Comments Accepted by NeurIPS 2025

2412.09572 2025-10-22 cs.CL 79%

Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty

Yu Feng, Phu Mon Htut, Zheng Qi, Wei Xiao, Manuel Mager, Nikolaos Pappas, Kishaloy Halder, Yang Li, Yassine Benajiba, Dan Roth

机构 * University of Pennsylvania（宾夕法尼亚大学）； AWS AI Labs（AWS人工智能实验室）； Johannes Gutenberg University of Mainz（美因茨约翰内斯·古滕贝格大学）； Oracle AI（Oracle人工智能）

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

Comments EMNLP 2025 Findings

Journal ref EMNLP 2025 Findings

2510.17942 2025-10-22 cs.CY cs.AI 79%

Trust in foundation models and GenAI: A geographic perspective

Grant McKenzie, Krzysztof Janowicz, Carsten Kessler

机构 * McGill University, Canada（麦吉尔大学，加拿大）； University of Vienna, Austria（维也纳大学，奥地利）； Bochum University of Applied Sciences, Germany（波鸿应用科学大学，德国）； Aalborg University Copenhagen, Denmark（奥胡斯大学哥本哈根分校，丹麦）

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

2510.17833 2025-10-22 q-bio.NC cs.AI 79%

Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage

Ángela López-Cardona, Sebastián Idesis, Mireia Masias-Bruns, Sergi Abadal, Ioannis Arapakis

机构 * Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）

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

2510.15430 2025-10-21 cs.CV cs.AI 79%

Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models

Shuang Liang, Zhihao Xu, Jialing Tao, Hui Xue, Xiting Wang

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

Comments Withdrawn due to an accidental duplicate submission. This paper (arXiv:2510.15430) was unintentionally submitted as a new entry instead of a new version of our previous work (arXiv:2508.09201)

2510.14304 2025-10-17 cs.CV cs.AI 79%

Watermarking for Factuality: Guiding Vision-Language Models Toward Truth via Tri-layer Contrastive Decoding

Kyungryul Back, Seongbeom Park, Milim Kim, Mincheol Kwon, SangHyeok Lee, Hyunyoung Lee, Junhee Cho, Seunghyun Park, Jinkyu Kim

机构 * CSE, Korea University（韩国大学计算机科学与工程系）； KT Corporation（KT公司）； Soongsil University（顺成大学）

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

Comments EMNLP 2025 Findings; Project: https://github.com/KR-0822/TCD

2510.10719 2025-10-14 cs.SD cs.AI 79%

SS-DPPN: A self-supervised dual-path foundation model for the generalizable cardiac audio representation

Ummy Maria Muna, Md Mehedi Hasan Shawon, Md Jobayer, Sumaiya Akter, Md Rakibul Hasan, Md. Golam Rabiul Alam

机构 * Department of Computer Science and Engineering（计算机科学与工程系）； BRAC University（布拉克大学）； Department of Electricial and Electronic Engineering（电气与电子工程系）； Department of Biomedical Engineering（生物医学工程系）； Linköping University（林肯堡大学）； Department of Electrical and Computer Engineering（电气与计算机工程系）； University of Maryland（马里兰大学）； School of Electrical Engineering, Computing and Mathematical Sciences（电气工程、计算与数学科学学院）

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

2510.04819 2025-10-07 cs.CV cs.CL 79%

Visual Representations inside the Language Model

Benlin Liu, Amita Kamath, Madeleine Grunde-McLaughlin, Winson Han, Ranjay Krishna

机构 * University of Washington（华盛顿大学）； University of California Los Angeles（加州大学洛杉矶分校）； Allen Institute for AI（人工智能研究院）

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

Comments Accepted to COLM 2025

2510.03911 2025-10-07 cs.LG 79%

THEMIS: Unlocking Pretrained Knowledge with Foundation Model Embeddings for Anomaly Detection in Time Series

Yadav Mahesh Lorik, Kaushik Sarveswaran, Nagaraj Sundaramahalingam, Aravindakumar Venugopalan

机构 * Comcast India Engineering Center（Comcast印度工程中心）

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

Comments Oral Presentation. AI4TS Workshop, IJCAI'25

2405.14715 2025-10-07 cs.CV cs.AI 79%

Towards Cross-modal Backward-compatible Representation Learning for Vision-Language Models

Young Kyun Jang, Ser-nam Lim

机构 * Google DeepMind（谷歌DeepMind）； University of Central Florida（中央佛罗里达大学）

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

2510.02292 2025-10-03 cs.CL cs.CV 79%

From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens

Hala Sheta, Eric Huang, Shuyu Wu, Ilia Alenabi, Jiajun Hong, Ryker Lin, Ruoxi Ning, Daniel Wei, Jialin Yang, Jiawei Zhou, Ziqiao Ma, Freda Shi

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

Comments EMNLP 2025 System Demonstration | Code: https://github.com/compling-wat/vlm-lens

2510.01560 2025-10-03 stat.ML cs.LG 79%

AI Foundation Model for Time Series with Innovations Representation

Lang Tong, Xinyi Wang

机构 * Lang Tong ； Xinyi Wang

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

2507.12838 2025-10-02 cs.CL 79%

Are Knowledge and Reference in Multilingual Language Models Cross-Lingually Consistent?

Xi Ai, Mahardika Krisna Ihsani, Min-Yen Kan

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

Comments EMNLP'25 Findings Camera Ready

2509.25552 2025-10-01 cs.AI 79%

Evaluating Foundation Models with Pathological Concept Learning for Kidney Cancer

Shangqi Gao, Sihan Wang, Yibo Gao, Boming Wang, Xiahai Zhuang, Anne Warren, Grant Stewart, James Jones, Mireia Crispin-Ortuzar

机构 * University of Cambridge, Cambridge, UK（剑桥大学）； Fudan University, Shanghai, China（复旦大学）； Cambridge University Hospitals NHS Foundation Trust, Cambridge, UK（剑桥大学医院 NHS 基础信托）

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

Comments Best Paper Award at MICCAI AMAI 2025

2509.23002 2025-09-30 stat.ML cs.LG 79%

Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty

Lingyou Pang, Lei Huang, Jianyu Lin, Tianyu Wang, Akira Horiguchi, Alexander Aue, Carey E. Priebe

机构 * Department of Statistics, University of California, Davis（加州大学戴维斯分校统计系）； Department of Applied Mathematics and Statistics, Johns Hopkins University（约翰霍普金斯大学应用数学与统计学系）

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

Comments 26 pages including appendix; 3 figures and 5 tables. Under review for ICLR 2026

2402.12881 2025-09-29 cs.CL 79%

TEXT2AFFORD: Probing Object Affordance Prediction abilities of Language Models solely from Text

Sayantan Adak, Daivik Agrawal, Animesh Mukherjee, Somak Aditya

机构 * IIT, Kharagpur（印度Kharagpur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

Comments Accepted at Conference on Computational Natural Language Learning 2024

2505.10039 2025-09-26 cs.LG 79%

Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates

Hang Chen, Jiaying Zhu, Xinyu Yang, Wenya Wang

机构 * Hang Chen School of Computer Science and Technology Xi’an Jiaotong University（Hang Chen 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（Jiaying Zhu 计算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（Xinyu Yang 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（Wenya Wang 计算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：language model(title,abstract)；分类 cs.LG

Comments accepted by NeurIPS 2025 (poster)

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

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

1. 知识编辑与模型理解 7596 篇

VoxRep: Enhancing 3D Spatial Understanding in 2D Vision-Language Models via Voxel Representation

Fantastic Features and Where to Find Them: A Probing Method to combine Features from Multiple Foundation Models

MolEdit: Knowledge Editing for Multimodal Molecule Language Models

On the Utility of Foundation Models for Fast MRI: Vision-Language-Guided Image Reconstruction

Priors in Time: Missing Inductive Biases for Language Model Interpretability

On the Internal Semantics of Time-Series Foundation Models

HEDGE: Hallucination Estimation via Dense Geometric Entropy for VQA with Vision-Language Models

How Linguistics Learned to Stop Worrying and Love the Language Models

A Low-Rank Method for Vision Language Model Hallucination Mitigation in Autonomous Driving

Evaluating Human-LLM Representation Alignment: A Case Study on Affective Sentence Generation for Augmentative and Alternative Communication

Discovering Interpretable Biological Concepts in Single-cell RNA-seq Foundation Models

Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions

Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty

Trust in foundation models and GenAI: A geographic perspective

Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage

Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models

Watermarking for Factuality: Guiding Vision-Language Models Toward Truth via Tri-layer Contrastive Decoding

SS-DPPN: A self-supervised dual-path foundation model for the generalizable cardiac audio representation

Visual Representations inside the Language Model

THEMIS: Unlocking Pretrained Knowledge with Foundation Model Embeddings for Anomaly Detection in Time Series

Towards Cross-modal Backward-compatible Representation Learning for Vision-Language Models

From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens

AI Foundation Model for Time Series with Innovations Representation

Are Knowledge and Reference in Multilingual Language Models Cross-Lingually Consistent?

Evaluating Foundation Models with Pathological Concept Learning for Kidney Cancer

Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty

TEXT2AFFORD: Probing Object Affordance Prediction abilities of Language Models solely from Text

Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates

Lost in Embeddings: Information Loss in Vision-Language Models

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