1
Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
LLM的机器遗忘并非真正删除，最新研究揭示了其可逆性，挑战现有安全假设。
arXiv:2505.16831v3 Announce Type: replace-cross Abstract: Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy i…