Xiang Yue

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning

2024 · arXiv (Cornell University)

Large Language Models (LLMs) embed sensitive, human-generated data, prompting the need for unlearning methods. Although certified unlearning offers strong privacy guarantees, its restrictive assumptions make it unsuitable for LLMs, giving rise to various heuristic approaches …