语言大模型 / LLM

JT-Safe: Intrinsically Enhancing the Safety and Trustworthiness of LLMs

Junlan Feng, Fanyu Meng, Chong Long, Pengyu Cong, Duqing Wang, Yan Zheng, Yuyao Zhang, Xuanchang Gao, Ye Yuan, Yunfei Ma, Zhijie Ren, Fan Yang, Na Wu, Di Jin, Chao Deng

机构 * China Mobile Jiutian Research（中国移动九天研究所） 纠错

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

Interpretability Framework for LLMs in Undergraduate Calculus

Sagnik Dakshit, Sushmita Sinha Roy

机构 * University of Texas at Tyler（德克萨斯理工大学） ； Florida Gulf Coast University（佛罗里达盖恩斯维尔大学） 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、cs.AI

Prediction hubs are context-informed frequent tokens in LLMs

Beatrix M. G. Nielsen, Iuri Macocco, Marco Baroni

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、cs.AI

Comments Published as a conference paper at ACL 2025

Journal ref Association for Computational Linguistics 2025

On Theoretical Interpretations of Concept-Based In-Context Learning

Huaze Tang, Tianren Peng, Shao-lun Huang

机构 * Institute of Data and Information Tsinghua Shenzhen International Graduate School（数据与信息研究所） 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、cs.AI

Scaling Language-Centric Omnimodal Representation Learning

Chenghao Xiao, Hou Pong Chan, Hao Zhang, Weiwen Xu, Mahani Aljunied, Yu Rong

机构 * DAMO Academy, Alibaba Group（达摩院，阿里巴巴集团） 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.CL、cs.AI

Comments NeurIPS 2025

On the Relationship Between the Choice of Representation and In-Context Learning

Ioana Marinescu, Kyunghyun Cho, Eric Karl Oermann

机构 * NYU（纽约大学） 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、cs.LG

Comments 25 pages, 6 figures, 10 tables

OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature

Alisha Srivastava, Emir Korukluoglu, Minh Nhat Le, Duyen Tran, Chau Minh Pham, Marzena Karpinska, Mohit Iyyer

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.CL、cs.AI

Comments Accepted to EMNLP 2025 Main

A novel hallucination classification framework

Maksym Zavhorodnii, Dmytro Dehtiarov, Anna Konovalenko

机构 * Instituto Superior Técnico, Universidade de Lisboa（里斯本大学技术学院） ； Molde University College（莫尔德大学学院） 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、cs.AI

Comments 15 pages, 3 figures

GRACE: Generative Representation Learning via Contrastive Policy Optimization

Jiashuo Sun, Shixuan Liu, Zhaochen Su, Xianrui Zhong, Pengcheng Jiang, Bowen Jin, Peiran Li, Weijia Shi, Jiawei Han

机构 * University of Illinois Urbana–Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Australian National University（澳大利亚国立大学） ； Hong Kong University of Science and Technology（香港科学与技术大学） ； University of Wisconsin–Madison（威斯康星大学麦迪逊分校） ； University of Washington（华盛顿大学） 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、cs.AI

Comments 23 pages, 7 figures, 7 tables

Ambiguity in LLMs is a concept missing problem

Zhibo Hu, Chen Wang, Yanfeng Shu, Hye-Young Paik, Liming Zhu

机构 * The University of New South Wales（新南威尔士大学） ； CSIRO Data61（澳大利亚联邦科学与工业研究组织数据61） 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、cs.LG

Comments 17 pages, 11 figures, title updated

Bridging the behavior-neural gap: A multimodal AI reveals the brain's geometry of emotion more accurately than human self-reports

Changde Du, Yizhuo Lu, Zhongyu Huang, Yi Sun, Zisen Zhou, Shaozheng Qin, Huiguang He

机构 * State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Institute of Automation, Chinese Academy of Sciences（脑认知与脑启发智能技术重点实验室，自动化研究所，中国科学院） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学） ； School of Future Technology, University of Chinese Academy of Sciences（未来技术学院，中国科学院大学） ； State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University（认知神经科学与学习国家重点实验室，北京师范大学） 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、cs.AI

Beyond Textual Context: Structural Graph Encoding with Adaptive Space Alignment to alleviate the hallucination of LLMs

Yifang Zhang, Pengfei Duan, Yiwen Yang, Shengwu Xiong

机构 * Wuhan University of Technology（武汉理工大学） 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.CL、cs.AI

Comments 11 pages, 5 figures

Black-Box Hallucination Detection via Consistency Under the Uncertain Expression

Seongho Joo, Kyungmin Min, Jahyun Koo, Kyomin Jung

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、cs.AI

Modeling Transformers as complex networks to analyze learning dynamics

Elisabetta Rocchetti

机构 * Università degli Studi di Milano, Department of Computer Science（米兰大学计算机科学系） 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、cs.LG

Hallucination Detection with the Internal Layers of LLMs

Martin Preiß

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、cs.AI

Comments Master's thesis

Unsupervised Hallucination Detection by Inspecting Reasoning Processes

Ponhvoan Srey, Xiaobao Wu, Anh Tuan Luu

机构 * Nanyang Technological University（南洋理工大学） 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.CL、cs.AI

Comments To appear in EMNLP 2025

Investigating Symbolic Triggers of Hallucination in Gemma Models Across HaluEval and TruthfulQA

Naveen Lamba, Sanju Tiwari, Manas Gaur

机构 * Center for Artificial Intelligence in Medicine, Imaging and Forensics, Sharda University, Greater Noida, India（人工智能医学与影像及法医学中心，沙达大学，印度Greater Noida） ； University of Maryland, Baltimore County, Baltimore, MD, USA（马里兰大学巴尔的摩县） 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、cs.AI

Cross-Layer Attention Probing for Fine-Grained Hallucination Detection

Malavika Suresh, Rahaf Aljundi, Ikechukwu Nkisi-Orji, Nirmalie Wiratunga

机构 * Robert Gordon University（罗伯特·戈登大学） 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、cs.AI

Comments To be published at the TRUST-AI workshop, ECAI 2025

MetaExplainer: A Framework to Generate Multi-Type User-Centered Explanations for AI Systems

Shruthi Chari, Oshani Seneviratne, Prithwish Chakraborty, Pablo Meyer, Deborah L. McGuinness

机构 * Rensselaer Polytechnic Institute（伦斯勒理工学院） ； Amazon Science（亚马逊科学） ； IBM Research（IBM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.AI、cs.LG

RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language

Subrata Biswas, Mohammad Nur Hossain Khan, Bashima Islam

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.CL、cs.LG

How Instruction-Tuning Imparts Length Control: A Cross-Lingual Mechanistic Analysis

Elisabetta Rocchetti, Alfio Ferrara

机构 * Università degli Studi di Milano, Department of Computer Science（米兰大学计算机科学系） 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.CL、cs.AI

Interpretable Mnemonic Generation for Kanji Learning via Expectation-Maximization

Jaewook Lee, Alexander Scarlatos, Andrew Lan

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校） 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、cs.AI

Comments The Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)

Multi-Ontology Integration with Dual-Axis Propagation for Medical Concept Representation

Mohsen Nayebi Kerdabadi, Arya Hadizadeh Moghaddam, Dongjie Wang, Zijun Yao

机构 * University of Kansas（堪萨斯大学） 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、cs.LG

Comments This work has been accepted as a full research paper at CIKM 2025

THEME: Enhancing Thematic Investing with Semantic Stock Representations and Temporal Dynamics

Hoyoung Lee, Wonbin Ahn, Suhwan Park, Jaehoon Lee, Minjae Kim, Sungdong Yoo, Taeyoon Lim, Woohyung Lim, Yongjae Lee

机构 * Ulsan National Institute of Science and Technology（乌山国立科学技术研究所） ； LG AI Research（LG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、cs.AI

Comments Accepted at ACM International Conference on Information and Knowledge Management (CIKM)

Guarding Your Conversations: Privacy Gatekeepers for Secure Interactions with Cloud-Based AI Models

GodsGift Uzor, Hasan Al-Qudah, Ynes Ineza, Abdul Serwadda

机构 * Department of Computer Science, Texas Tech University, Lubbock, Texas（计算机科学系，德克萨斯理工大学，德克萨斯州拉伯克） 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、cs.AI

Comments 2025 19th International Conference on Semantic Computing (ICSC)

Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection

Chengcan Wu, Zeming Wei, Huanran Chen, Yinpeng Dong, Meng Sun

机构 * Peking University（北京大学） ； Tsinghua University（清华大学） 纠错

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

Comments 10 pages, 9 figures, Under review as a full paper at AAAI 2026. A preliminary version is under review at the NeurIPS 2025 Workshop on Reliable ML from Unreliable Data

Conformal P-Value in Multiple-Choice Question Answering Tasks with Provable Risk Control

Yuanchang 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、cs.AI

A New Query Expansion Approach via Agent-Mediated Dialogic Inquiry

Wonduk Seo, Hyunjin An, Seunghyun Lee

机构 * Enhans Seoul, South Korea（首尔增强韩国） 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.CL、cs.LG

Comments Accepted by ACM SIGKDD 2025 Workshop on AI Agent for Information Retrieval (Agent4IR)

Improving ARDS Diagnosis Through Context-Aware Concept Bottleneck Models

Anish Narain, Ritam Majumdar, Nikita Narayanan, Dominic Marshall, Sonali Parbhoo

机构 * Imperial College London（帝国理工学院伦敦校区） 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、cs.LG

Comments 32 pages, 7 figures, accepted at Machine Learning for Healthcare Conference (MLHC) 2025

Towards Bridging Review Sparsity in Recommendation with Textual Edge Graph Representation

Leyao Wang, Xutao Mao, Xuhui Zhan, Yuying Zhao, Bo Ni, Ryan A. Rossi, Nesreen K. Ahmed, Tyler Derr

机构 * Yale University（耶鲁大学） ； Vanderbilt University（范德比大学） ； Adobe Research（Adobe研究） ； Cisco AI Research（思科人工智能研究） 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.AI、cs.LG

Comments 13 pages