1
Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning
最新研究揭示大模型“遗忘”机制：事实显著性与微调如何双重影响模型知识删除的效果。
arXiv:2602.19612v5 Announce Type: replace Abstract: Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated informat…