语言大模型 / LLM - arXivDaily 专题

2510.03295 2025-10-07 cs.CV cs.CL cs.LG 73%

Multimodal Arabic Captioning with Interpretable Visual Concept Integration

Passant Elchafei, Amany Fashwan

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

2510.02571 2025-10-06 cs.CV cs.AI cs.CL 73%

How Confident are Video Models? Empowering Video Models to Express their Uncertainty

Zhiting Mei, Ola Shorinwa, Anirudha Majumdar

机构 * Princeton University（普林斯顿大学）

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

2509.25220 2025-10-01 cs.CL cs.LG 73%

Cyclic Ablation: Testing Concept Localization against Functional Regeneration in AI

Eduard Kapelko

机构 * Eduard Kapelko（独立研究者）

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 Code is available at: https://www.kaggle.com/code/kapedalex/cycleablationpublic/

2509.21357 2025-09-29 cs.CL cs.AI 73%

A Novel Differential Feature Learning for Effective Hallucination Detection and Classification

Wenkai Wang, Vincent Lee, Yizhen Zheng

机构 * Department of Data Science and AI（数据科学与人工智能系）； Monash University（墨尔本大学）

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

Comments 10 pages, 7 figures, 13 tables

2410.03090 2025-09-25 cs.CL cs.LG 73%

UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective

Jing Xiong, Jianghan Shen, Fanghua Ye, Chaofan Tao, Zhongwei Wan, Jianqiao Lu, Xun Wu, Chuanyang Zheng, Zhijiang Guo, Min Yang, Lingpeng Kong, Ngai Wong

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 at EMNLP 2025 (Main Conference)

2509.19143 2025-09-24 cs.CL cs.AI cs.CY 73%

Anecdoctoring: Automated Red-Teaming Across Language and Place

Alejandro Cuevas, Saloni Dash, Bharat Kumar Nayak, Dan Vann, Madeleine I. G. Daepp

机构 * Carnegie Mellon University（卡内基梅隆大学）； University of Washington（华盛顿大学）； Microsoft Research（微软研究院）； Independent Researcher（独立研究者）

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

Comments To be published in EMNLP 2025

2509.16598 2025-09-24 cs.CL cs.AI 73%

PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality

Byeongho Yu, Changhun Lee, Jungyu Jin, Eunhyeok Park

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

Comments accepted at EMNLP 2025 Main Conference

2509.17671 2025-09-23 cs.CL cs.AI 73%

Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

Selva Taş, Mahmut El Huseyni, Özay Ezerceli, Reyhan Bayraktar, Fatma Betül Terzioğlu

机构 * Hidden for Review（保密）

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

2508.08846 2025-09-23 cs.CL cs.AI 73%

Steering Towards Fairness: Mitigating Political Bias in LLMs

Afrozah Nadeem, Mark Dras, Usman Naseem

机构 * School of Computing, Macquarie University（计算机学院，麦考瑞大学）

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

Comments Accepted at CASE@RANLP2025

2503.05683 2025-09-23 cs.CL cs.LG 73%

WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs

Lukas Thede, Karsten Roth, Matthias Bethge, Zeynep Akata, Tom Hartvigsen

机构 * Tübingen AI Center, University of Tübingen（图宾根人工智能中心，图宾根大学）； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）； Technical University, Munich（慕尼黑技术大学）； University of Virginia（弗吉尼亚大学）

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

Comments published at ICML 2025

2509.16188 2025-09-22 cs.CL cs.AI 73%

CultureScope: A Dimensional Lens for Probing Cultural Understanding in LLMs

Jinghao Zhang, Sihang Jiang, Shiwei Guo, Shisong Chen, Yanghua Xiao, Hongwei Feng, Jiaqing Liang, Minggui HE, Shimin Tao, Hongxia Ma

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

2509.15926 2025-09-22 cs.CL cs.LG 73%

Beyond the Score: Uncertainty-Calibrated LLMs for Automated Essay Assessment

Ahmed Karim, Qiao Wang, Zheng Yuan

机构 * King’s College London（伦敦国王学院）； Hosei University（Hosei大学）； University of Sheffield（谢菲尔德大学）

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

Comments Accepted at EMNLP 2025 (Main Conference). Camera-ready version

2509.08380 2025-09-18 cs.AI cs.LG 73%

Co-Investigator AI: The Rise of Agentic AI for Smarter, Trustworthy AML Compliance Narratives

Prathamesh Vasudeo Naik, Naresh Kumar Dintakurthi, Zhanghao Hu, Yue Wang, Robby Qiu

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

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)

2505.02884 2025-09-10 cs.LG cs.AI 73%

Unlearning vs. Obfuscation: Are We Truly Removing Knowledge?

Guangzhi Sun, Potsawee Manakul, Xiao Zhan, Mark Gales

机构 * Department of Engineering, University of Cambridge（剑桥大学工程系）； Department of Informatics, King’s College London（伦敦大学国王学院信息学院）； SCB 10X, SCBX Group（SCB 10X，SCBX集团）

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

Comments To Appear in EMNLP 2025 main conference

2502.07322 2025-09-10 cs.CL cs.LG 73%

MEMIT-Merge: Addressing MEMIT's Key-Value Conflicts in Same-Subject Batch Editing for LLMs

Zilu Dong, Xiangqing Shen, Rui Xia

机构 * School of Computer Science and Engineering, Nanjing University of Science and Technology, China（计算机科学与工程学院，南京理工大学）

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

Comments Accepted by ACL2025 findings

2509.02499 2025-09-09 cs.CL cs.AI 73%

MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds

Junxi Wu, Jinpeng Wang, Zheng Liu, Bin Chen, Dongjian Hu, Hao Wu, Shu-Tao Xia

机构 * Nankai University（南开大学）； Tsinghua University（清华大学）； Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））； Peng Cheng Laboratory（鹏城实验室）； Shenzhen ShenNong Information Technology Co., Ltd.（深圳深农信息技术有限公司）

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

Comments EMNLP 2025

2410.14748 2025-09-09 cs.SE cs.AI cs.CL 73%

ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries

Kishan Maharaj, Vitobha Munigala, Srikanth G. Tamilselvam, Prince Kumar, Sayandeep Sen, Palani Kodeswaran, Abhijit Mishra, Pushpak Bhattacharyya

机构 * Indian Institute of Technology Bombay（印度理工学院班加罗尔分校）； IBM Research India（IBM印度研究院）； University of Texas at Austin（德克萨斯大学奥斯汀分校）

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

Comments Accepted in ACL 2025 Main, 14 pages, 3 Figures, 5 Tables

2509.04011 2025-09-05 cs.IR cs.AI cs.CL 73%

NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings

Or Shachar, Uri Katz, Yoav Goldberg, Oren Glickman

机构 * Computer Science Department, Bar-Ilan University（巴伊兰大学计算机科学系）

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

Comments Findings of EMNLP 2025

2509.02170 2025-09-04 cs.CL cs.AI 73%

Avoidance Decoding for Diverse Multi-Branch Story Generation

Kyeongman Park, Nakyeong Yang, Kyomin Jung

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

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

2507.08529 2025-09-03 cs.AI cs.CL 73%

A Multi-granularity Concept Sparse Activation and Hierarchical Knowledge Graph Fusion Framework for Rare Disease Diagnosis

Mingda Zhang, Na Zhao, Jianglong Qin, Guoyu Ye, Ruixiang Tang

机构 * School of Software, Yunnan University（云南大学软件学院）； Yunnan Key Laboratory of Software Engineering（云南软件工程重点实验室）； Yunnan Provincial Hospital of Traditional Chinese Medicine（云南中医药省人民医院）

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

Comments 12 pages,3 figures

2508.21186 2025-09-01 cs.LG cs.AI math.DS 73%

Manifold Trajectories in Next-Token Prediction: From Replicator Dynamics to Softmax Equilibrium

Christopher R. Lee-Jenkins

机构 * Centralia College（中央学院）

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

2508.20195 2025-08-29 cs.AI cs.CL cs.MA 73%

AI-AI Esthetic Collaboration with Explicit Semiotic Awareness and Emergent Grammar Development

Nicanor I. Moldovan

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

Comments 13 pages

2508.19321 2025-08-28 cs.CR cs.AI cs.CL 73%

An Investigation on Group Query Hallucination Attacks

Kehao Miao, Xiaolong Jin

机构 * University of Science and Technology of China（中国科学技术大学）； Purdue University（帕克大学）

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

2508.15882 2025-08-25 cs.SD cs.CL cs.LG eess.AS 73%

Beyond Transcription: Mechanistic Interpretability in ASR

Neta Glazer, Yael Segal-Feldman, Hilit Segev, Aviv Shamsian, Asaf Buchnick, Gill Hetz, Ethan Fetaya, Joseph Keshet, Aviv Navon

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

2508.15719 2025-08-22 cs.LG cs.AI 73%

Tutorial on the Probabilistic Unification of Estimation Theory, Machine Learning, and Generative AI

Mohammed Elmusrati

机构 * School of Technology and Innovations, University of Vaasa（技术与创新学院，瓦萨大学）

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

2508.10404 2025-08-15 cs.CL cs.AI 73%

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation

Huizhen Shu, Xuying Li, Qirui Wang, Yuji Kosuga, Mengqiu Tian, Zhuo Li

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

2508.09085 2025-08-13 cs.NI cs.AI cs.LG 73%

Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoring

Zihan Fang, Zheng Lin, Senkang Hu, Yihang Tao, Yiqin Deng, Xianhao Chen, Yuguang Fang

机构 * Hong Kong JC STEM Lab of Smart City and Department of Computer Science, City University of Hong Kong（香港JC STEM实验室及城市大学计算机科学系）

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

Comments 14 pages, 10 figures

2508.08795 2025-08-13 cs.AI cs.CL 73%

A Dual-Axis Taxonomy of Knowledge Editing for LLMs: From Mechanisms to Functions

Amir Mohammad Salehoof, Ali Ramezani, Yadollah Yaghoobzadeh, Majid Nili Ahmadabadi

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系）

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

Comments 13 pages, 1 figure

2502.19110 2025-08-13 cs.CL cs.LG 73%

Conformal Linguistic Calibration: Trading-off between Factuality and Specificity

Zhengping Jiang, Anqi Liu, Benjamin Van Durme

机构 * Johns Hopkins University（约翰霍普金斯大学）

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

1. 知识编辑与模型理解 7552 篇

Multimodal Arabic Captioning with Interpretable Visual Concept Integration

How Confident are Video Models? Empowering Video Models to Express their Uncertainty

Cyclic Ablation: Testing Concept Localization against Functional Regeneration in AI

A Novel Differential Feature Learning for Effective Hallucination Detection and Classification

UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective

Anecdoctoring: Automated Red-Teaming Across Language and Place

PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality

Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

Steering Towards Fairness: Mitigating Political Bias in LLMs

WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs

CultureScope: A Dimensional Lens for Probing Cultural Understanding in LLMs

Beyond the Score: Uncertainty-Calibrated LLMs for Automated Essay Assessment

Co-Investigator AI: The Rise of Agentic AI for Smarter, Trustworthy AML Compliance Narratives

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

Unlearning vs. Obfuscation: Are We Truly Removing Knowledge?

MEMIT-Merge: Addressing MEMIT's Key-Value Conflicts in Same-Subject Batch Editing for LLMs

MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds

ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries

NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings

Avoidance Decoding for Diverse Multi-Branch Story Generation

A Multi-granularity Concept Sparse Activation and Hierarchical Knowledge Graph Fusion Framework for Rare Disease Diagnosis

Manifold Trajectories in Next-Token Prediction: From Replicator Dynamics to Softmax Equilibrium

AI-AI Esthetic Collaboration with Explicit Semiotic Awareness and Emergent Grammar Development

An Investigation on Group Query Hallucination Attacks

Beyond Transcription: Mechanistic Interpretability in ASR

Tutorial on the Probabilistic Unification of Estimation Theory, Machine Learning, and Generative AI

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation

Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoring

A Dual-Axis Taxonomy of Knowledge Editing for LLMs: From Mechanisms to Functions

Conformal Linguistic Calibration: Trading-off between Factuality and Specificity