Distillation Robustifies Unlearning

NeurIPSSpotlight2025

Authors: Bruce W. Lee, Addie Foote, Alex Infanger, Leni Shor, Harish K Kamath, Jacob Goldman-Wetzler, Bryce Woodworth, Alex Cloud, Alexander Matt Turner
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Current LLM unlearning methods are not robust…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

distillation llm

← All NeurIPS 2025 Spotlight papers · Browse the whole archive