1
LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs
大模型训练数据泄露风险新视角：引入倾向性评估，揭示记忆化并非模型本意
arXiv:2606.06286v1 Announce Type: cross Abstract: Large language models can reproduce training data, but existing memorization evaluations mostly meas…