Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications 文章

ArXiv CS.CL2026-05-27NEWSen作者: Ziyi Tong, Feifei Sun, Le Minh Nguyen
大语言模型
查看原文 →
关系图谱

Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications · 相关人物

暂无数据