The paper presents UNDO, a method that enhances unlearning in LLMs through distillation, achieving robust capability removal with reduced compute and data requirements compared to traditional retraining methods.

https://arxiv.org/abs//2506.06278

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers