Training LLM Judges from Language Feedback via Position-Selective Self-Distillation
A position-masking self-distillation method trains LLM judges from language feedback and beats outcome-only RL on subjective tasks.
1 stories, newest first · one card per story
A position-masking self-distillation method trains LLM judges from language feedback and beats outcome-only RL on subjective tasks.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views