Structured problem-space guidance, rather than the full reference solution, yields the highest aggregate question-only accuracy in on-policy self-distillation across three math benchmarks and model scales.
Reasoning Scaffolding: Distilling the Flow of Thought from
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning
Structured problem-space guidance, rather than the full reference solution, yields the highest aggregate question-only accuracy in on-policy self-distillation across three math benchmarks and model scales.