Reasoning language models extract answers from sparse, order-shuffled chain-of-thought traces with little accuracy loss.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
OGLS-SD improves LLM reasoning by using verifiable outcome rewards to guide logit steering that calibrates teacher distributions in on-policy self-distillation, addressing reflection-induced mismatches.
citing papers explorer
-
OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning
OGLS-SD improves LLM reasoning by using verifiable outcome rewards to guide logit steering that calibrates teacher distributions in on-policy self-distillation, addressing reflection-induced mismatches.