From Unfamiliar to Familiar: Detecting Pre-training Data via Gradient Deviations in Large Language Models 文章

ArXiv CS.CL2026-06-02NEWSen作者: Ruiqi Zhang, Lingxiang Wang, Hainan Zhang, Zhiming Zheng, Yanyan Lan
查看原文 →
关系图谱

From Unfamiliar to Familiar: Detecting Pre-training Data via Gradient Deviations in Large Language Models · 相关人物

暂无数据