OPPD Distillation Method Raises Single-Generation Reasoning Accuracy
The non-obvious result is that inference-time candidate scoring can be absorbed into the weights, so the sharpening gain survives a single forward pass at deployment. Teams doing RLHF-style training on math or code can stack OPPD on top of GRPO for up to 9.3 extra points, and unlike GRPO it needs no verified reference answers, which matters where reward data is scarce. The loss coefficient gives direct control over the absorbed sharpening exponent.