Who is Harry Potter? Inside Microsoft Research’s Fine-Tuning Method for Unlearning Concepts in LLMs

Can fine-tuning allow LLMs to unlearn existing knowledge?

I recently started an AI-focused educational newsletter, that already has over 160,000 subscribers. TheSequence is a no-BS (meaning no hype, no news, etc) ML-oriented newsletter that takes 5 minutes to read. The goal is to keep you up to date with machine learning projects, research papers, and concepts. Please give it a try by subscribing below:

TheSequence | Jesus Rodriguez | Substack

Large language models(LLMs) are regularly trained in …

artificial intelligence concepts educational etc fine-tuning harry potter inside knowledge large language models llms machine learning meaning microsoft microsoft research newsletter research thesequence