Ask-to-Distill learns to write questions for on-policy distillation
A frozen student–teacher pair scores synthetic questions without reference answers, then those prompts feed standard on-policy distillation.
1 stories, newest first · one card per story
A frozen student–teacher pair scores synthetic questions without reference answers, then those prompts feed standard on-policy distillation.
Today 1.6K readers · 2.4K views · 774 reads · all time 189K views