TOPSD limits teacher supervision to verified prefixes in distillation
It beats conventional on-policy self-distillation on math reasoning in ten languages, especially lower-resource ones.
1 stories, newest first · one card per story
It beats conventional on-policy self-distillation on math reasoning in ten languages, especially lower-resource ones.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views