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.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found