语言大模型 / LLM

Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Models

Tomoya Yamashita, Akira Ito, Yuuki Yamanaka, Masanori Yamada, Takayuki Miura, Toshiki Shibahara

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

Concept Unlearning in Large Language Models via Self-Constructed Knowledge Triplets

Tomoya Yamashita, Yuuki Yamanaka, Masanori Yamada, Takayuki Miura, Toshiki Shibahara, Tomoharu Iwata

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

Quantifying Uncertainty in Natural Language Explanations of Large Language Models for Question Answering

Yangyi Li, Mengdi Huai

机构 * Department of Computer Science, Iowa State University（计算机科学系，爱荷华州立大学） 纠错

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

Calibrating LLM Confidence by Probing Perturbed Representation Stability

Reza Khanmohammadi, Erfan Miahi, Mehrsa Mardikoraem, Simerjot Kaur, Ivan Brugere, Charese H. Smiley, Kundan Thind, Mohammad M. Ghassemi

机构 * Michigan State University（密歇根州立大学） ； JPMorgan AI Research（摩根大通人工智能研究） ； Henry Ford Health（亨利福特健康） 纠错

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

Activation Space Interventions Can Be Transferred Between Large Language Models

Narmeen Oozeer, Dhruv Nathawani, Nirmalendu Prakash, Michael Lan, Abir Harrasse, Amirali Abdullah

机构 * Nvidia ； Singapore University of Technology and Design（新加坡技术与设计大学） 纠错

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

Comments 75 pages. Accepted to ICML 2025

Multi-Modal Interpretability for Enhanced Localization in Vision-Language Models

Muhammad Imran, Yugyung Lee

机构 * Computer Science, School of Science and Engineering, University of Missouri - Kansas City（计算机科学系，科学与工程学院，密苏里大学-堪萨斯城分校） 纠错

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

Comments 8 pages, 6 figures, 3 tables

Journal ref Non-Archival track - The First Workshop on Multimodal Knowledge and Language Modeling IJCAI 2025 Workshop, August 16, 2025 IJCAI 2025 Workshop, August 16, 2025 Room 516B, Palais des congrès, Montreal, Canada

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

NeuroRAD-FM: A Foundation Model for Neuro-Oncology with Distributionally Robust Training

Moinak Bhattacharya, Angelica P. Kurtz, Fabio M. Iwamoto, Prateek Prasanna, Gagandeep Singh

机构 * Department of Biomedical Informatics, Stony Brook University（生物医学信息学系，石溪大学） ； Department of Radiology, Columbia University Irving Medical Center（放射学系，哥伦比亚大学伊万杰琳医疗中心） ； Department of Neuro-Oncology, Columbia University Irving Medical Center（神经肿瘤学系，哥伦比亚大学伊万杰琳医疗中心） 纠错

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

VOX-KRIKRI: Unifying Speech and Language through Continuous Fusion

Dimitrios Damianos, Leon Voukoutis, Georgios Paraskevopoulos, Vassilis Katsouros

机构 * Institute for Speech and Language Processing, Athena Research Center, Greece（语音与语言处理研究所，亚特兰蒂斯研究中心，希腊） 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

SuPreME: A Supervised Pre-training Framework for Multimodal ECG Representation Learning

Mingsheng Cai, Jiuming Jiang, Wenhao Huang, Che Liu, Rossella Arcucci

机构 * The University of Edinburgh（爱丁堡大学） ； Imperial College London（帝国理工学院） ； Shenzhen Yinwang Intelligent Technology Co., Ltd（深圳英伟达智能技术有限公司） 纠错

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、cs.LG

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

RACap: Relation-Aware Prompting for Lightweight Retrieval-Augmented Image Captioning

Xiaosheng Long, Hanyu Wang, Zhentao Song, Kun Luo, Hongde Liu

机构 * School of biological science and medical engineering, Southeast University, China（生物科学与医学工程学院，东南大学，中国） ； Department of Neurosurgery, The second affiliated hospital of Xinjiang Medical University, China（神经外科部门，新疆医科大学第二附属医院，中国） 纠错

专题命中 知识编辑与模型理解 ：prompting(title)；分类 cs.AI

Two Facets of the Same Optimization Coin: Model Degradation and Representation Collapse in Graph Foundation Models

Xunkai Li, Daohan Su, Sicheng Liu, Ru Zhang, Zhenjun Li, Bing Zhou, Rong-Hua Li, Guoren Wang

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

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

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） 纠错

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

Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations

Linyang He, Qiaolin Wang, Xilin Jiang, Nima Mesgarani

机构 * Department of Electrical Engineering, Columbia University（哥伦比亚大学电气工程系） 纠错

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

Comments EMNLP 2025 Main Conference (Oral)

Discovering Semantic Subdimensions through Disentangled Conceptual Representations

Yunhao Zhang, Shaonan Wang, Nan Lin, Xinyi Dong, Chong Li, Chengqing Zong

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS（多模态人工智能系统国家重点实验室，自动化研究所） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； State Key Laboratory of Cognitive Science and Mental Health, Institute of Psychology, CAS（认知科学与心理健康国家重点实验室，心理研究所） ； Department of Psychology, University of Chinese Academy of Sciences（中国科学院大学心理学系） ； 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 ：large language model(abstract)；language model(abstract)；分类 cs.CL

LLMs Can Compensate for Deficiencies in Visual Representations

Sho Takishita, Jay Gala, Abdelrahman Mohamed, Kentaro Inui, Yova Kementchedjhieva

机构 * Fujitsu Limited（富士通有限公司） ； MBZUAI ； Tohoku University（东北大学） ； RIKEN（日本研究机构） 纠错

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

Comments EMNLP 2025 Findings

BBScoreV2: Learning Time-Evolution and Latent Alignment from Stochastic Representation

Tianhao Zhang, Zhecheng Sheng, Zhexiao Lin, Chen Jiang, Dongyeop Kang

机构 * University of Minnesota, Twin Cities（明尼苏达大学，双城分校） ； University of California, Berkeley（加州大学伯克利分校） 纠错

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

Journal ref The 2025 Conference on Empirical Methods in Natural Language Processing

VLA-Mark: A cross modal watermark for large vision-language alignment model

Shuliang Liu, Qi Zheng, Jesse Jiaxi Xu, Yibo Yan, Junyan Zhang, He Geng, Aiwei Liu, Peijie Jiang, Jia Liu, Yik-Cheung Tam, Xuming Hu

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； The Hong Kong University of Science and Technology（香港科技大学） ； University of Toronto（多伦多大学） ； Ant Group, Alibaba（蚂蚁集团，阿里巴巴） ； New York University Shanghai（纽约大学上海分校） 纠错

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

Comments Accepted by the main conference, EMNLP 2025

ViLU: Learning Vision-Language Uncertainties for Failure Prediction

Marc Lafon, Yannis Karmim, Julio Silva-Rodríguez, Paul Couairon, Clément Rambour, Raphaël Fournier-Sniehotta, Ismail Ben Ayed, Jose Dolz, Nicolas Thome

专题命中 知识编辑与模型理解 ：language model(abstract)

Journal ref International Conference on Computer Vision, ICCV 2025