Skip to content
Sagan

Paper

Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning

Unreadunread

AI summary

The authors identify a problem in on-policy self-distillation for LLM reasoning: the teacher always sees the full reference solution, creating a mismatch when the student isn't yet competent enough to absorb such strong targets. They propose ATESD, which treats teacher exposure (how much of the reference solution the teacher sees) as a learnable variable. A lightweight controller samples an exposure ratio based on training-state statistics and holds it for a short window of updates, optimizing the controller with a reward based on the student's future learning progress rather than immediate loss.

Main takeaways:

  • Standard self-distillation methods have the teacher condition on the full reference reasoning, but this can be too strong when the student is far behind.
  • Experiments show that full exposure isn't always optimal and that student-teacher mismatch grows as the teacher sees more privileged information.
  • ATESD uses a Beta-policy controller to dynamically choose how much of the reference solution the teacher sees at each training stage.
  • The controller is optimized with a discounted reward based on future student improvement, addressing delayed credit assignment.
  • On math reasoning benchmarks (AIME, HMMT), ATESD outperforms competitive self-distillation and RL baselines by +1 to +2.3 points.