Amogh Gupta

SHARD: Safe and Helpful Alignment via Self-Reframing Distillation

SHARD is introduced, a self-reframing distillation method to improve safe-helpfulness in large language models that first rewrites sensitive prompts to surface benign intent using philosophical guidelines, then reframes its original responses into safe, more helpful ones, and finally fine-tunes the model on its self-re...