Want to create an interactive transcript for this episode?
Podcast: Arxiv Papers
Episode: [QA] Distillation Robustifies Unlearning
Description: 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//2506.06278YouTube: https://www.youtube.com/@ArxivPapersTikTok: https://www.tiktok.com/@arxiv_papersApple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers