融合异常度与参考差异的软加权聚合预训练数据检测方法

白皓丞, 杜彦辉, 周杰, 段奕晨, 仵一铭, 张挺

Soft-weighted Aggregation for Pretraining Data Detection via Token Surprisal and Reference Gap

BAI Haocheng, DU Yanhui, ZHOU Jie, DUAN Yichen, WU Yiming, ZHANG Ting

计算机科学 . 2026, (10): 102 -112 . DOI: 10.11896/jsjkx.260400118