语言大模型 / LLM - arXivDaily 专题

2506.17345 2025-06-24 cond-mat.mtrl-sci cs.LG 83%

CLOUD: A Scalable and Physics-Informed Foundation Model for Crystal Representation Learning

Changwen Xu, Shang Zhu, Venkatasubramanian Viswanathan

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

Comments 36 pages, 11 pages of Supporting Information

2506.03984 2025-06-05 cs.CL 83%

Around the World in 24 Hours: Probing LLM Knowledge of Time and Place

Carolin Holtermann, Paul Röttger, Anne Lauscher

机构 * University of Hamburg（汉堡大学）； University of Bocconi（博科尼大学）

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

2502.16733 2025-06-05 cs.LG 83%

Coreset Selection via LLM-based Concept Bottlenecks

Akshay Mehra, Trisha Mittal, Subhadra Gopalakrishnan, Joshua Kimball

机构 * Dolby Laboratory（多利贝实验室）； Apple（苹果公司）

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

2506.01334 2025-06-03 cs.CL 83%

Enhancing Interpretable Image Classification Through LLM Agents and Conditional Concept Bottleneck Models

Yiwen Jiang, Deval Mehta, Wei Feng, Zongyuan Ge

机构 * Faculty of Engineering, Monash University（墨尔本大学工程学院）； AIM for Health Lab, Faculty of IT, Monash University（墨尔本大学信息科技学院健康人工智能实验室）

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

Comments Accepted at ACL 2025 (Main)

2506.01074 2025-06-03 cs.CL cs.PL cs.SE 83%

How Programming Concepts and Neurons Are Shared in Code Language Models

Amir Hossein Kargaran, Yihong Liu, François Yvon, Hinrich Schütze

机构 * LMU Munich & Munich Center for Machine Learning（慕尼黑大学及慕尼黑机器学习中心）； Sorbonne Université & CNRS, ISIR（索邦大学及国家科学研究中心，ISIR）

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 ACL Findings 2025

2505.20809 2025-05-28 cs.CL 83%

Improved Representation Steering for Language Models

Zhengxuan Wu, Qinan Yu, Aryaman Arora, Christopher D. Manning, Christopher Potts

机构 * Stanford University（斯坦福大学）

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

Comments 46 pages, 23 figures, preprint

2504.13123 2025-05-20 cs.CV cs.AI 83%

Low-hallucination Synthetic Captions for Large-Scale Vision-Language Model Pre-training

Xinsong Zhang, Yarong Zeng, Xinting Huang, Hu Hu, Runquan Xie, Han Hu, Zhanhui Kang

机构 * Tencent（腾讯）

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

2505.06291 2025-05-13 eess.SP cs.CE cs.HC cs.LG 83%

ALFEE: Adaptive Large Foundation Model for EEG Representation

Wei Xiong, Junming Lin, Jiangtong Li, Jie Li, Changjun Jiang

机构 * Department of Computer Science and Technology, Tongji University（计算机科学与技术系，同济大学）

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

Comments 17pages, 17 figures

2505.01958 2025-05-06 cs.CV cs.CL 83%

A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models

Liqiang Jing, Guiming Hardy Chen, Ehsan Aghazadeh, Xin Eric Wang, Xinya Du

机构 * University of Texas at Dallas（德克萨斯大学达拉斯分校）； University of Massachusetts at Amherst（马萨诸塞大学阿姆赫斯特分校）； University of California, Santa Cruz（加州大学圣克鲁兹分校）

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

2504.19099 2025-04-29 cs.SE cs.AI cs.AR 83%

VeriDebug: A Unified LLM for Verilog Debugging via Contrastive Embedding and Guided Correction

Ning Wang, Bingkun Yao, Jie Zhou, Yuchen Hu, Xi Wang, Nan Guan, Zhe Jiang

机构 * City University of Hong Kong（香港城市大学）； Southeast University（东南大学）

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

2504.18639 2025-04-29 cs.CL 83%

Span-Level Hallucination Detection for LLM-Generated Answers

Passant Elchafei, Mervet Abu-Elkheir

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

2504.10504 2025-04-16 cs.CL cs.GR 83%

LayerFlow: Layer-wise Exploration of LLM Embeddings using Uncertainty-aware Interlinked Projections

Rita Sevastjanova, Robin Gerling, Thilo Spinner, Mennatallah El-Assady

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

2504.08808 2025-04-15 cs.CL 83%

Exploring the Effectiveness and Interpretability of Texts in LLM-based Time Series Models

Zhengke Sun, Hangwei Qian, Ivor Tsang

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

2502.18389 2025-04-10 cs.CL 83%

Monte Carlo Temperature: a robust sampling strategy for LLM's uncertainty quantification methods

Nicola Cecere, Andrea Bacciu, Ignacio Fernández Tobías, Amin Mantrach

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

2504.03440 2025-04-07 cs.CV cs.LG 83%

Know What You do Not Know: Verbalized Uncertainty Estimation Robustness on Corrupted Images in Vision-Language Models

Mirko Borszukovszki, Ivo Pascal de Jong, Matias Valdenegro-Toro

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

Comments 10 pages, 11 figures, TrustNLP Workshop @ NAACL 2025 Camera ready

2407.06581 2025-03-28 cs.AI cs.CV 83%

Vision language models are blind: Failing to translate detailed visual features into words

Pooyan Rahmanzadehgervi, Logan Bolton, Mohammad Reza Taesiri, Anh Totti Nguyen

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

2501.12206 2025-03-27 cs.CV cs.CL 83%

PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model

Kazi Hasan Ibn Arif, Sajib Acharjee Dip, Khizar Hussain, Lang Zhang, Chris Thomas

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

Comments 6 pages, 4 tables, 3 figures

2503.18854 2025-03-26 cs.CV cs.AI 83%

MC-LLaVA: Multi-Concept Personalized Vision-Language Model

Ruichuan An, Sihan Yang, Ming Lu, Renrui Zhang, Kai Zeng, Yulin Luo, Jiajun Cao, Hao Liang, Ying Chen, Qi She, Shanghang Zhang, Wentao Zhang

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

Comments I sincerely apologize for any inconvenience caused. We actually uploaded this paper to arXiv in November 2024, as arXiv:2411.11706. During this update, we did not consider the replacement operation of arXiv, which led to duplicate submissions. We have made modifications at the original address arXiv:2411.11706

2503.15886 2025-03-24 cs.CV cs.LG 83%

Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance

Hui Liu, Wenya Wang, Kecheng Chen, Jie Liu, Yibing Liu, Tiexin Qin, Peisong He, Xinghao Jiang, Haoliang Li

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

Comments 21 pages, 7 figures 7 tables

2503.14530 2025-03-21 cs.CV cs.AI 83%

SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders

Qing Li, Jiahui Geng, Derui Zhu, Fengyu Cai, Chenyang Lyu, Fakhri Karray

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

Comments More comparative experiments are needed

2503.04457 2025-03-07 cs.CV cs.AI 83%

TPC: Cross-Temporal Prediction Connection for Vision-Language Model Hallucination Reduction

Chao Wang, Weiwei Fu, Yang Zhou

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

2502.10038 2025-03-05 cs.AI 83%

POI-Enhancer: An LLM-based Semantic Enhancement Framework for POI Representation Learning

Jiawei Cheng, Jingyuan Wang, Yichuan Zhang, Jiahao Ji, Yuanshao Zhu, Zhibo Zhang, Xiangyu Zhao

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

Comments AAAI 25

2503.00309 2025-03-04 cs.IR cs.AI 83%

Pseudo-Knowledge Graph: Meta-Path Guided Retrieval and In-Graph Text for RAG-Equipped LLM

Yuxin Yang, Haoyang Wu, Tao Wang, Jia Yang, Hao Ma, Guojie Luo

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

2502.20750 2025-03-03 cs.CL 83%

Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow

Jiaqi Bai, Hongcheng Guo, Zhongyuan Peng, Jian Yang, Zhoujun Li, Mohan Li, Zhihong Tian

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

Comments Accepted to AAAI 2025. Camera ready version

2410.22071 2025-02-19 cs.CL 83%

Distinguishing Ignorance from Error in LLM Hallucinations

Adi Simhi, Jonathan Herzig, Idan Szpektor, Yonatan Belinkov

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

2411.12701 2025-02-18 cs.CR cs.AI 83%

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations

Huaizhi Ge, Yiming Li, Qifan Wang, Yongfeng Zhang, Ruixiang Tang

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

2411.11543 2025-01-14 cs.CV cs.AI 83%

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment

Zhendong Liu, Yuanbi Nie, Yingshui Tan, Jiaheng Liu, Xiangyu Yue, Qiushi Cui, Chongjun Wang, Xiaoyong Zhu, Bo Zheng

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

Comments arXiv admin note: substantial text overlap with arXiv:2405.13581

2501.05981 2025-01-13 cs.CL 83%

Hermit Kingdom Through the Lens of Multiple Perspectives: A Case Study of LLM Hallucination on North Korea

Eunjung Cho, Won Ik Cho, Soomin Seo

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

Comments Accepted at COLING 2025

2402.16315 2025-01-08 cs.CV cs.CL 83%

Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models

Jeonghwan Kim, Heng Ji

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 EMNLP 2024; Main Conference

2412.07386 2024-12-11 cs.CL 83%

Algorithmic Phase Transitions in Language Models: A Mechanistic Case Study of Arithmetic

Alan Sun, Ethan Sun, Warren Shepard

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 10 pages, 5 figures

1. 知识编辑与模型理解 7539 篇

CLOUD: A Scalable and Physics-Informed Foundation Model for Crystal Representation Learning

Around the World in 24 Hours: Probing LLM Knowledge of Time and Place

Coreset Selection via LLM-based Concept Bottlenecks

Enhancing Interpretable Image Classification Through LLM Agents and Conditional Concept Bottleneck Models

How Programming Concepts and Neurons Are Shared in Code Language Models

Improved Representation Steering for Language Models

Low-hallucination Synthetic Captions for Large-Scale Vision-Language Model Pre-training

ALFEE: Adaptive Large Foundation Model for EEG Representation

A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models

VeriDebug: A Unified LLM for Verilog Debugging via Contrastive Embedding and Guided Correction

Span-Level Hallucination Detection for LLM-Generated Answers

LayerFlow: Layer-wise Exploration of LLM Embeddings using Uncertainty-aware Interlinked Projections

Exploring the Effectiveness and Interpretability of Texts in LLM-based Time Series Models

Monte Carlo Temperature: a robust sampling strategy for LLM's uncertainty quantification methods

Know What You do Not Know: Verbalized Uncertainty Estimation Robustness on Corrupted Images in Vision-Language Models

Vision language models are blind: Failing to translate detailed visual features into words

PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model

MC-LLaVA: Multi-Concept Personalized Vision-Language Model

Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance

SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders

TPC: Cross-Temporal Prediction Connection for Vision-Language Model Hallucination Reduction

POI-Enhancer: An LLM-based Semantic Enhancement Framework for POI Representation Learning

Pseudo-Knowledge Graph: Meta-Path Guided Retrieval and In-Graph Text for RAG-Equipped LLM

Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow

Distinguishing Ignorance from Error in LLM Hallucinations

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment

Hermit Kingdom Through the Lens of Multiple Perspectives: A Case Study of LLM Hallucination on North Korea

Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models

Algorithmic Phase Transitions in Language Models: A Mechanistic Case Study of Arithmetic