1
CAP: Controllable Alignment Prompting for Unlearning in LLMs
无需修改参数，用提示即可让大模型忘记敏感信息，高效又安全。
arXiv:2604.21251v5 Announce Type: replace-cross Abstract: Large language models (LLMs) trained on unfiltered corpora inherently risk retaining sensiti…