نسخة أولية وصول مفتوح
Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearning
Many localized large language model (LLM) unlearning methods select a small parameter subset from a localization signal and keep it fixed during optimization. The parameters most associated with a target, however, need not be the best ones to update, and candidate interventions can change value as optimization proceeds …