Tag
This paper introduces Decoupled Credit Self-Distillation (DCSD) to separate credit direction and magnitude for self-distillation, achieving improvements of 8.45 points in mathematical reasoning and 7.01 points in multimodal reasoning across 11 benchmarks.
Combining GRPO and OPSD, CriPO is a rubric-based reinforcement learning method from ByteDance and Zhejiang University that addresses unexplored and suppressed criteria via self-distillation, achieving better performance and compute efficiency.