pith. sign in

On-policy distillation of language models: Learning from self- generated mistakes

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

roles

background 1

polarities

background 1

representative citing papers

Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning

cs.AI · 2026-05-12 · unverdicted · novelty 6.0

ATESD makes teacher exposure to reference reasoning a learnable control variable via a Beta-policy optimized on future student improvement, yielding gains of up to +2.33 points over fixed-exposure self-distillation on AIME and HMMT math benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning cs.AI · 2026-05-12 · unverdicted · none · ref 2

    ATESD makes teacher exposure to reference reasoning a learnable control variable via a Beta-policy optimized on future student improvement, yielding gains of up to +2.33 points over fixed-exposure self-distillation on AIME and HMMT math benchmarks.