Comment by saahir.vazirani on Machine Unlearning in Large Language Models: A Comprehensive Survey with Empirical Insights from the Qwen 1.5 1.8B Model · 2025-02-02T18:55:53.228Z · LW · GW

Typically, the information being unlearnt is from the initial training with mass amounts of data from the internet so it may be difficult to pinpoint what exactly to remove while training.