语言大模型 / LLM - arXivDaily 专题

2503.17349 2025-10-02 cs.CV 82%

Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models

Jianing Qi, Jiawei Liu, Hao Tang, Zhigang Zhu

机构 * CUNY Graduate Center（纽约大学研究生中心）； Borough of Manhattan Community College（曼哈顿社区学院）； The City College of New York（纽约城市学院）

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

2509.05230 2025-09-11 cs.CL cs.AI cs.LG 82%

CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language Models

Aysenur Kocak, Shuo Yang, Bardh Prenkaj, Gjergji Kasneci

机构 * Technical University of Munich（慕尼黑技术大学）

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

Comments Accepted at the Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)

2505.14729 2025-08-01 cs.CV 82%

Uncovering Cultural Representation Disparities in Vision-Language Models

Ram Mohan Rao Kadiyala, Siddhant Gupta, Jebish Purbey, Srishti Yadav, Suman Debnath, Alejandro Salamanca, Desmond Elliott

机构 * Cohere Labs Community ； IIT Roorkee（印度理工学院罗尔克hee分校）； University of Copenhagen（哥本哈根大学）； Cohere Labs ； Amazon Datasets（亚马逊数据集）

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

Comments 28 pages, 36 figures

2403.15836 2025-07-30 cs.CV 82%

VLM-CPL: Consensus Pseudo Labels from Vision-Language Models for Annotation-Free Pathological Image Classification

Lanfeng Zhong, Zongyao Huang, Yang Liu, Wenjun Liao, Shichuan Zhang, Guotai Wang, Shaoting Zhang

机构 * School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China（电子科技大学机械与电子工程学院）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； Department of Pathology, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Affiliated Cancer Hospital of University of Electronic Science and Technology of China（pathology department, 四川省癌症临床研究中心, 四川省肿瘤医院及研究所, 电子科技大学附属肿瘤医院）； Department of Radiation Oncology, Sichuan Cancer Hospital and Institute, University of Electronic Science and Technology of China（放射肿瘤科, 四川省肿瘤医院及研究所, 电子科技大学）

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

Comments Accepted at TMI

2507.18631 2025-07-28 cs.CR 82%

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment

Hao Li, Lijun Li, Zhenghao Lu, Xianyi Wei, Rui Li, Jing Shao, Lei Sha

专题命中知识编辑与模型理解：LLM(title,abstract)；post-training(abstract)

2507.09081 2025-07-15 cs.CV 82%

From Physics to Foundation Models: A Review of AI-Driven Quantitative Remote Sensing Inversion

Zhenyu Yu, Mohd Yamani Idna Idris, Hua Wang, Pei Wang, Junyi Chen, Kun Wang

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

2507.07486 2025-07-11 q-bio.OT 82%

Sparse Autoencoders Reveal Interpretable Structure in Small Gene Language Models

Haoxiang Guan, Jiyan He, Jie Zhang

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

Comments AI4X 2025 Oral

2507.01790 2025-07-03 cs.CL cs.AI cs.CV cs.LG 82%

How Do Vision-Language Models Process Conflicting Information Across Modalities?

Tianze Hua, Tian Yun, Ellie Pavlick

机构 * Brown University（布朗大学）

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

Comments All code and resources are available at: https://github.com/ethahtz/vlm_conflicting_info_processing

2506.20178 2025-06-26 cs.CL cs.AI cs.LG 82%

COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees

Zhiyuan Wang, Jinhao Duan, Qingni Wang, Xiaofeng Zhu, Tianlong Chen, Xiaoshuang Shi, Kaidi Xu

机构 * University of Electronic Science and Technology of China（电子科技大学）； Drexel University（德雷塞尔大学）； University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）

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

2403.01755 2025-06-18 cs.CY 82%

AI Language Models Could Both Help and Harm Equity in Marine Policymaking: The Case Study of the BBNJ Question-Answering Bot

Matt Ziegler, Sarah Lothian, Brian O'Neill, Richard Anderson, Yoshitaka Ota

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

Journal ref npj Ocean Sustainability | (2025)4:32

2402.08680 2025-06-13 cs.LG cs.AI cs.CL cs.CV 82%

Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance

Linxi Zhao, Yihe Deng, Weitong Zhang, Quanquan Gu

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

Comments 25 pages, 13 figures, 25 tables

Journal ref In Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada. PMLR 267, 2025

2503.01917 2025-05-23 cs.LG cs.AI cs.CL 82%

Steer LLM Latents for Hallucination Detection

Seongheon Park, Xuefeng Du, Min-Hsuan Yeh, Haobo Wang, Yixuan Li

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

Comments ICML 2025

2310.10378 2025-05-20 cs.CL cs.AI cs.HC cs.LG 82%

Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models

Jirui Qi, Raquel Fernández, Arianna Bisazza

机构 * Center for Language and Cognition, University of Groningen（格罗宁根大学语言与认知中心）； Institute for Logic, Language and Computation, University of Amsterdam（阿姆斯特丹大学逻辑、语言与计算研究所）

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

Comments EMNLP2023 Outstanding Paper (Multilinguality and Linguistic Diversity Track). All code and data are released at https://github.com/Betswish/Cross-Lingual-Consistency

2504.17671 2025-05-16 cs.CL cs.AI cs.LG 82%

Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Prediction

Yuanchang Ye, Weiyan Wen

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

Comments Accepted by ICIPCA 2025

2409.03757 2025-05-09 cs.CV cs.AI cs.CL cs.LG cs.RO 82%

Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding

Yunze Man, Shuhong Zheng, Zhipeng Bao, Martial Hebert, Liang-Yan Gui, Yu-Xiong Wang

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； Carnegie Mellon University（卡内基梅隆大学）

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

Comments NeurIPS 2024. Project page: https://yunzeman.github.io/lexicon3d Github: https://github.com/YunzeMan/Lexicon3D

2403.19647 2025-03-28 cs.LG cs.AI cs.CL 82%

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Samuel Marks, Can Rager, Eric J. Michaud, Yonatan Belinkov, David Bau, Aaron Mueller

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

Comments Code and data at https://github.com/saprmarks/feature-circuits. Demonstration at https://feature-circuits.xyz

Journal ref International Conference on Learning Representations, 2025

2411.13623 2025-03-25 cs.CV 82%

Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning

Tim Lenz, Peter Neidlinger, Marta Ligero, Georg Wölflein, Marko van Treeck, Jakob Nikolas Kather

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

Comments Got accepted at CVPR 2025

2412.09668 2025-03-21 cs.CV 82%

Vision-Language Models Generate More Homogeneous Stories for Phenotypically Black Individuals

Messi H. J. Lee, Soyeon Jeon

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

2312.08870 2025-03-04 cs.CV 82%

Vista-LLaMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens

Fan Ma, Xiaojie Jin, Heng Wang, Yuchen Xian, Jiashi Feng, Yi Yang

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

2502.00717 2025-02-04 cs.CV 82%

MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction

Chao Wang, Jianming Yang, Yang Zhou

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

Comments 8 pages, 5 figures, 4 tables

2412.02886 2024-12-17 cs.CV 82%

Patchfinder: Leveraging Visual Language Models for Accurate Information Retrieval using Model Uncertainty

Roman Colman, Minh Vu, Manish Bhattarai, Martin Ma, Hari Viswanathan, Daniel O'Malley, Javier E. Santos

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

Comments This paper has been accepted to IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025

2412.07802 2024-12-12 cs.CV 82%

Language Model as Visual Explainer

Xingyi Yang, Xinchao Wang

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

2411.09894 2024-11-18 cs.CV 82%

Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement

Yanyan Huang, Weiqin Zhao, Yihang Chen, Yu Fu, Lequan Yu

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

2407.15814 2024-11-08 cs.CL cs.AI cs.LG 82%

Perceptions of Linguistic Uncertainty by Language Models and Humans

Catarina G Belem, Markelle Kelly, Mark Steyvers, Sameer Singh, Padhraic Smyth

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

Comments Accepted at EMNLP 2024 (Main)

2408.00113 2024-10-31 cs.LG cs.AI cs.CL 82%

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models

Adam Karvonen, Benjamin Wright, Can Rager, Rico Angell, Jannik Brinkmann, Logan Smith, Claudio Mayrink Verdun, David Bau, Samuel Marks

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

Comments Accepted as an oral paper (top 5%) at the ICML 2024 Mechanistic Interpretability Workshop and to the NeurIPS 2024 Main Conference

2410.03964 2024-10-30 cs.LG cs.AI cs.CL stat.ML 82%

Variational Language Concepts for Interpreting Foundation Language Models

Hengyi Wang, Shiwei Tan, Zhiqing Hong, Desheng Zhang, Hao Wang

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

Comments Accepted at EMNLP 2024 Findings

2409.19283 2024-10-08 eess.AS cs.SD 82%

Analyzing and Mitigating Inconsistency in Discrete Audio Tokens for Neural Codec Language Models

Wenrui Liu, Zhifang Guo, Jin Xu, Yuanjun Lv, Yunfei Chu, Zhou Zhao, Junyang Lin

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

Comments e.g.: 15 pages, 4 figures

2409.15604 2024-09-25 cs.HC 82%

Persona-L has Entered the Chat: Leveraging LLM and Ability-based Framework for Personas of People with Complex Needs

Lipeipei Sun, Tianzi Qin, Anran Hu, Jiale Zhang, Shuojia Lin, Jianyan Chen, Mona Ali, Mirjana Prpa

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

2404.08263 2024-09-11 cs.CL cs.AI cs.LG cs.SI 82%

Relational Prompt-based Pre-trained Language Models for Social Event Detection

Pu Li, Xiaoyan Yu, Hao Peng, Yantuan Xian, Linqin Wang, Li Sun, Jingyun Zhang, Philip S. Yu

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

Comments ACM TOIS

2402.16998 2024-08-19 cs.CL cs.AI cs.LG cs.SD eess.AS 82%

What Do Language Models Hear? Probing for Auditory Representations in Language Models

Jerry Ngo, Yoon Kim

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

Journal ref 2024.acl-long.297

1. 知识编辑与模型理解 7550 篇

Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models

CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language Models

Uncovering Cultural Representation Disparities in Vision-Language Models

VLM-CPL: Consensus Pseudo Labels from Vision-Language Models for Annotation-Free Pathological Image Classification

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment

From Physics to Foundation Models: A Review of AI-Driven Quantitative Remote Sensing Inversion

Sparse Autoencoders Reveal Interpretable Structure in Small Gene Language Models

How Do Vision-Language Models Process Conflicting Information Across Modalities?

COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees

AI Language Models Could Both Help and Harm Equity in Marine Policymaking: The Case Study of the BBNJ Question-Answering Bot

Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance

Steer LLM Latents for Hallucination Detection

Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models

Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Prediction

Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning

Vision-Language Models Generate More Homogeneous Stories for Phenotypically Black Individuals

Vista-LLaMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens

MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction

Patchfinder: Leveraging Visual Language Models for Accurate Information Retrieval using Model Uncertainty

Language Model as Visual Explainer

Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement

Perceptions of Linguistic Uncertainty by Language Models and Humans

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models

Variational Language Concepts for Interpreting Foundation Language Models

Analyzing and Mitigating Inconsistency in Discrete Audio Tokens for Neural Codec Language Models

Persona-L has Entered the Chat: Leveraging LLM and Ability-based Framework for Personas of People with Complex Needs

Relational Prompt-based Pre-trained Language Models for Social Event Detection

What Do Language Models Hear? Probing for Auditory Representations in Language Models