AI RESEARCH
Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning
arXiv CS.CL
•
ArXi:2601.03190v3 Announce Type: replace Machine unlearning aims to forget sensitive knowledge from Large Language Models (LLMs) while maintaining general utility. However, existing approaches typically treat all tokens in a response indiscriminately and enforce uncertainty over the entire vocabulary. This global treatment results in unnecessary utility degradation and extends optimization to content-agnostic regions.