1
Combating Data Laundering in LLM Training
一篇针对LLM训练中“数据洗白”问题的检测方案，通过分析模型对专有样本的预测差异来识别数据是否被非法使用
arXiv:2604.01904v2 Announce Type: replace-cross Abstract: Data rights owners can detect unauthorized data use in large language model (LLM) training b…