Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning 事件

Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning arXiv:2602.19612v5 Announce Type: replace Abstract: Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated information. However, existing work assumes that all facts are equally forgettable and largely ignores whether the forgotten knowledge originates from pretraining or supervised fine-tuning (SFT). In this paper, we introduce DUET (Dual Unlearning Evaluation across Training Stages