1
RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning
提出影响力驱动参数重加权方法，高效解决大模型遗忘小样本或不平衡数据的难题。
arXiv:2512.04457v2 Announce Type: replace Abstract: Removing specific data influence from large language models (LLMs) remains challenging, as retrain…