GradDiff

A study by Łucki et al. found that machine unlearning methods are vulnerable to knowledge recovery, but experiments on six unlearned Llama-3-8B-Instruct checkpoints showed that ablating the refusal di…

Researchers propose RepSelect, a method for robust LLM unlearning that isolates forget-set-specific representations by collapsing top principal components of weight gradients, achieving 4-50x larger r…