policy optimization

Can We Trust the Teacher? Decoupled Credit Direction-Magnitude for Self-Distillationarxiv.org

Existing self-distillation methods couple credit direction and magnitude, making them vulnerable to teacher errors and preference variance. Decoupled Credit Self-Distillation (DCSD) addresses this by theoretically separating credit direction and magnitude into two reliable signals, using belief-margin probing and marginal information gain to calibrate teacher supervision.