SafeLoRA:theSilverLiningofReducingSafety RiskswhenFine-tuningLargeLanguageModels
–Neural Information Processing Systems
It is worth noting thatSafe LoRAis a training-free and data-free approach, as it only requires the knowledge of the weights from the base and aligned LLMs.
Neural Information Processing Systems
Feb-15-2026, 23:04:21 GMT