LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
By Matteo Boglioni · Paper · cs.CL
LLMs memorize sensitive training data, including personally identifiable information (PII), creating a pressing need for reliable post hoc removal methods. Unlearning has emerged as a promising solution, with state-of-the-art(SOTA) methods often following a localize-first, unlear