Provable Training Data Identification for Large Language Models
大语言模型训练数据的可证明识别
Zhenlong Liu, Hao Zeng, Weiran Huang, Hongxin Wei
机构
*
Department of Statistics and Data Science, Southern University of Science and Technology(统计与数据科学系,南方科技大学)
;
Shanghai Innovation Institute(上海创新研究院)
;
School of Computer Science, Shanghai Jiao Tong University(计算机科学学院,上海交通大学)
专题命中
预训练与数据
:large language model(title);language model(title);分类 cs.AI、cs.LG
Is Self-Pretraining really useful to improve diagnosis in medical Time Series?
自预训练(SPT)真的有助于改进医疗时间序列的诊断吗?
Omar Coser, Antonio Orvieto, Paolo Soda, Loredana Zollo
机构
*
Università Campus Bio-Medico di Roma(罗马生物医学大学校园大学)
;
Umeå University(于默奥大学)
;
Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)
;
ELLIS Institute Tübingen(埃利斯研究所蒂宾根分所)
机构
*
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
;
Beihang University(北京航空航天大学)
;
Huawei Foundation Model Department(华为基础模型部门)
Nikolaos Kougioulis, Nikolaos Gkorgkolis, MingXue Wang, Bora Caglayan, Dario Simionato, Andrea Tonon, Ioannis Tsamardinos
机构
*
Institute of Applied & Computational Mathematics, FORTH(应用与计算数学研究所,希腊国家科研院)
;
Computer Science Department, University of Crete(克里特大学计算机科学系)
;
Huawei Ireland Research Centre(华为爱尔兰研究中心)
CommentsAccepted at European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD) 2026. 33 pages (including Appendix), 11 Figures
Comments16 pages, 9 figures. v2: updated author list (added Yang Liu and Yuxin Li; marked core contributors and project lead) and added a release-date note on the first page
机构
*
University of Oklahoma(俄克拉荷马大学)
;
Imperial College London(伦敦帝国学院)
;
University of Michigan(密歇根大学)
;
Tencent(腾讯)
;
University of Edinburgh(爱丁堡大学)
;
University of Southern California(南加州大学)
;
Beijing Normal University(北京师范大学)
;
Beijing Normal-Hong Kong Baptist University(北京师范大学-香港浸会大学联合国际学院)
Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP
Grad-ECLIP: 基于梯度的CLIP视觉与文本解释
Chenyang Zhao, Kun Wang, Janet H. Hsiao, Antoni B. Chan
机构
*
Department of Computer Science, City University of Hong Kong(香港城市大学计算机科学系)
;
Division of Social Science and Department of Computer Science & Engineering, Hong Kong University of Science & Technology(香港科学与技术大学社会科学学院及计算机科学与工程系)
;
SenseTime Group Ltd(时光集团有限公司)
Journal refZhao C, Wang K, Hsiao J H, et al. Grad-eclip: Gradient-based visual and textual explanations for clip[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026
PolyFact: Comparing Consistency-Driven Post-training Methods for Cross-Lingual Factual Recall
通过一致性驱动的强化学习改进跨语言事实回忆
Jonathan von Rad, Louis Arts, George Burgess, Eleftheria Kolokytha, Harry O'Donnell, Ektor Oikonomidis Doumpas, Eduardo Sanchez, Yao Lu, Pontus Stenetorp
机构
*
University College London(伦敦大学学院)
;
Centre for Artificial Intelligence(人工智能中心)
专题命中
后训练与偏好优化
:post-training(title,abstract);SFT(abstract,abstract_cn);large language model(abstract);language model(abstract)
How Long Reasoning Chains Influence LLMs' Judgment of Answer Factuality
推理链长度如何影响LLM对答案事实性的判断
Minzhu Tu, Shiyu Ni, Keping Bi
机构
*
State Key Laboratory of AI Safety(人工智能安全国家重点实验室)
;
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)
;
University of Chinese Academy of Sciences(中国科学院大学)
;
Beijing University of Post and Telecommunications(北京邮电大学)
专题命中
推理与问题求解
:LLM(title_cn,summary_cn);large language model(abstract);language model(abstract);分类 cs.CL
机构
*
University of Southern California(南加州大学)
;
Carnegie Mellon University(卡内基梅隆大学)
;
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
;
Stanford University(斯坦福大学)
专题命中
推理与问题求解
:LLM(abstract,abstract_cn);large language model(abstract);language model(abstract);分类 cs.AI