语言大模型 / LLM

Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm

Baixiang Huang, Zhen Tan, Haoran Wang, Zijie Liu, Dawei Li, Ali Payani, Huan Liu, Tianlong Chen, Kai Shu

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

Comments AAAI 2026 Oral. 14 pages (including appendix), 11 figures. Code, data, results, and additional resources are available at: https://model-editing.github.io

On the Brittleness of LLMs: A Journey around Set Membership

Lea Hergert, Gábor Berend, Mario Szegedy, Gyorgy Turan, Márk Jelasity

机构 * University of Szeged（塞格德大学） ； Rutgers University（罗格斯大学） ； University of Illinois at Chicago（伊利诺伊大学香槟分校） ； HUN-REN–SZTE Research Group on AI（AI研究组） 纠错

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

Seeing is Believing: Rich-Context Hallucination Detection for MLLMs via Backward Visual Grounding

Pinxue Guo, Chongruo Wu, Xinyu Zhou, Lingyi Hong, Zhaoyu Chen, Jinglun Li, Kaixun Jiang, Sen-ching Samson Cheung, Wei Zhang, Wenqiang Zhang

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

Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG

Bo Li, Tian Tian, Zhenghua Xu, Hao Cheng, Shikun Zhang, Wei Ye

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

Comments AAAI'26, Oral Paper

Guess or Recall? Training CNNs to Classify and Localize Memorization in LLMs

Jérémie Dentan, Davide Buscaldi, Sonia Vanier

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

Comments This paper has been accepted for publication at AAAI-26

Libra-MIL: Multimodal Prototypes Stereoscopic Infused with Task-specific Language Priors for Few-shot Whole Slide Image Classification

Zhenfeng Zhuang, Fangyu Zhou, Liansheng Wang

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

KG-DF: A Black-box Defense Framework against Jailbreak Attacks Based on Knowledge Graphs

Shuyuan Liu, Jiawei Chen, Xiao Yang, Hang Su, Zhaoxia Yin

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

Biomedical Hypothesis Explainability with Graph-Based Context Retrieval

Ilya Tyagin, Saeideh Valipour, Aliaksandra Sikirzhytskaya, Michael Shtutman, Ilya Safro

机构 * Center for Bioinformatics and Computational Biology University of Delaware（生物信息学与计算生物学中心 大田纳西大学） ； Computer and Information Sciences University of Delaware（计算机与信息科学 大田纳西大学） ； Drug Discovery and Biomedical Sciences (DDBS) College of Pharmacy University of South Carolina（药物发现与生物医学科学（DDBS）药学院 美国南卡罗来纳大学） 纠错

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

Comments 30 pages, 10 figures,

Findings of the Fourth Shared Task on Multilingual Coreference Resolution: Can LLMs Dethrone Traditional Approaches?

Michal Novák, Miloslav Konopík, Anna Nedoluzhko, Martin Popel, Ondřej Pražák, Jakub Sido, Milan Straka, Zdeněk Žabokrtský, Daniel Zeman

机构 * Charles University（查理大学） ； University of West Bohemia（西波西米亚大学） 纠错

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

Comments Accepted to CODI-CRAC 2025

DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination

Xuan Gong, Tianshi Ming, Xinpeng Wang, Zhihua Wei

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

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

Comments Accepted by EMNLP2024 (Main Conference), add GitHub link

LGCA: Enhancing Semantic Representation via Progressive Expansion

Thanh Hieu Cao, Trung Khang Tran, Gia Thinh Pham, Tuong Nghiem Diep, Thanh Binh Nguyen

机构 * University of Science, Vietnam National University Ho Chi Minh City, Vietnam（越南胡志明市国家大学科学大学） ； National University of Singapore, Singapore（新加坡国立大学） ； AISIA Lab, Ho Chi Minh City, Vietnam（越南胡志明市AISIA实验室） 纠错

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

Comments 15 pages, 5 figures, to appear in SoICT 2025

Mathematics Isn't Culture-Free: Probing Cultural Gaps via Entity and Scenario Perturbations

Aditya Tomar, Nihar Ranjan Sahoo, Ashish Mittal, Rudra Murthy, Pushpak Bhattacharyya

机构 * IIT Bombay（印度班加罗尔理工学院） ； IBM Research（IBM研究院） 纠错

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

NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging

Weiming Zhang, Qingyao Li, Xinyi Dai, Jizheng Chen, Kounianhua Du, Weiwen Liu, Yasheng Wang, Ruiming Tang, Yong Yu, Weinan Zhang

机构 * Shanghai Jiao Tong University（上海交通大学） ； Huawei Noah’s Ark Lab Shanghai（华为诺亚实验室） 纠错

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

OpenFactCheck: Building, Benchmarking Customized Fact-Checking Systems and Evaluating the Factuality of Claims and LLMs

Yuxia Wang, Minghan Wang, Hasan Iqbal, Georgi Georgiev, Jiahui Geng, Preslav Nakov

机构 * MBZUAI ； Monash University（墨尔本大学） ； Sofia University（索菲亚大学） 纠错

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

Comments 23 pages, 8 tables, 11 figures, Published In Proceedings of the 31st International Conference on Computational Linguistics 2025

Journal ref In Proceedings of the 31st International Conference on Computational Linguistics 2025, pages 11399-11421, Abu Dhabi, UAE. Association for Computational Linguistics

Graph-Guided Concept Selection for Efficient Retrieval-Augmented Generation

Ziyu Liu, Yijing Liu, Jianfei Yuan, Minzhi Yan, Le Yue, Honghui Xiong, Yi Yang

机构 * Huawei Cloud Computing Technology Co., Ltd, China（华为云计算技术有限公司，中国） 纠错

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

AgentSense: LLMs Empower Generalizable and Explainable Web-Based Participatory Urban Sensing

Xusen Guo, Mingxing Peng, Xixuan Hao, Xingchen Zou, Qiongyan Wang, Sijie Ruan, Yuxuan Liang

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Beijing Institute of Technology（北京理工大学） 纠错

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

Comments 13 pages, 10 pages

RAG-Stack: Co-Optimizing RAG Quality and Performance From the Vector Database Perspective

Wenqi Jiang

机构 * Systems Group, ETH Zurich（苏黎世联邦理工学院系统组） 纠错

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

A Matter of Representation: Towards Graph-Based Abstract Code Generation

Nyx Iskandar, Hisham Bedri, Andy Tsen

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

Unveiling the Vulnerability of Graph-LLMs: An Interpretable Multi-Dimensional Adversarial Attack on TAGs

Bowen Fan, Zhilin Guo, Xunkai Li, Yihan Zhou, Bing Zhou, Zhenjun Li, Rong-Hua Li, Guoren Wang

机构 * Beijing Institute of Technology（北京理工大学） ； Shandong University（山东大学） ； Shenzhen Institute of Technology（深圳理工大学） 纠错

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

Comments 12 pages, 4 figures

Instruction-aware User Embedding via Synergistic Language and Representation Modeling

Ziyi Gao, Yike Xu, Jiahao Yuan, Baokun Wang, Jinyong Wen, Xiaotong Lin, Yun Liu, Xing Fu, Yu Cheng, Yongchao Liu, Weiqiang Wang, Zhongle Xie

机构 * Zhejiang University（浙江大学） 纠错

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

Revisiting Hallucination Detection with Effective Rank-based Uncertainty

Rui Wang, Zeming Wei, Guanzhang Yue, Meng Sun

机构 * Peking University（北京大学） 纠错

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

Cluster Paths: Navigating Interpretability in Neural Networks

Nicholas M. Kroeger, Vincent Bindschaedler

机构 * Department of Computer Science University of Florida（计算机科学系佛罗里达大学） 纠错

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

Evaluating Node-tree Interfaces for AI Explainability

Lifei Wang, Natalie Friedman, Chengchao Zhu, Zeshu Zhu, S. Joy Mountford

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

Comments 5 pages, 2 figures. Accepted to the 3rd Workshop on Explainability in Human-Robot Collaboration: Real-World Concerns (XHRI 2025), scheduled for March 3, 2025, Hybrid (Melbourne and online) as part of HRI 2025

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

Elisei Rykov, Kseniia Petrushina, Maksim Savkin, Valerii Olisov, Artem Vazhentsev, Kseniia Titova, Alexander Panchenko, Vasily Konovalov, Julia Belikova

机构 * Skoltech ； AIRI ； MWS AI ； Sber AI Lab ； Moscow Institute of Physics and Technology（莫斯科物理技术学院） 纠错

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

On the Role of Unobserved Sequences on Sample-based Uncertainty Quantification for LLMs

Lucie Kunitomo-Jacquin, Edison Marrese-Taylor, Ken Fukuda

机构 * National Institute of Advanced Industrial Science and Technology (AIST)（国家先进工业科学与技术研究院） 纠错

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

Comments Accepted to UncertaiNLP workshop of EMNLP 2025

Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT

Guy Bar-Shalom, Fabrizio Frasca, Yaniv Galron, Yftah Ziser, Haggai Maron

机构 * Technion（技术离子大学） ； University of Groningen（格罗宁根大学） ； Nvidia Research（英伟达研究） 纠错

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

Comments Published in NeurIPS 2025

UncertainGen: Uncertainty-Aware Representations of DNA Sequences for Metagenomic Binning

Abdulkadir Celikkanat, Andres R. Masegosa, Mads Albertsen, Thomas D. Nielsen

机构 * Aalborg University（奥尔堡大学） 纠错

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

Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown

Lifu Tu, Rui Meng, Shafiq Joty, Yingbo Zhou, Semih Yavuz

机构 * Salesforce AI Research（Salesforce人工智能研究） 纠错

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

LatentGuard: Controllable Latent Steering for Robust Refusal of Attacks and Reliable Response Generation

Huizhen Shu, Xuying Li, Zhuo Li

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

Comments 9-page NeurIPS 2025 preprint including 3 figures and 1 table, with additional appendix material. Prepared using the NeurIPS 2025 preprint template and compiled with pdfLaTeX. All references are included via the provided .bbl file. Figures are in PDF format. No external supplementary files. All necessary style files and images are included

PART: Progressive Alignment Representation Training for Multilingual Speech-To-Text with LLMs

Pei Zhang, Andong Chen, Xi Chen, Baosong Yang, Derek F. Wong, Fei Huang

机构 * Tongyi Lab, Alibaba Group（通义实验室，阿里巴巴集团） ； The Chinese University of Hong Kong（香港中文大学） ； NLP 2 CT Lab, University of Macau（自然语言处理2CT实验室，澳门大学） 纠错

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