Карта знаний

Rubric-Conditioned Self-Distillation

1 статья затрагивает эту идею.

Статьи

ИИКлючевая идея

Teaching an AI to grade its own reasoning with a checklist beats giving it one right answer

Смежные понятия

Идеи, которые идут в паре с понятием «Rubric-Conditioned Self-Distillation».

Chain-Of-Thought Credit Assignment Knowledge Distillation Reasoning Language Models Reinforcement Learning With Verifiable Rewards Science Reasoning Benchmarks Self-Distillation