The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning
arXiv:2603.11266v1 Announce Type: new Abstract: Unlearning in Large Language Models (LLMs) aims to enhance safety, mitigate biases, and comply with legal mandates, such as the …
Raj Sanjay Shah, Jing Huang, Keerthiram Murugesan, Nathalie Baracaldo, Diyi Yang
조회수 46회