Simple-OPD warms up a student on the teacher's chain-of-thought traces with a LoRA adapter before on-policy distillation, improving in-domain reasoning while preserving out-of-domain performance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Simple-OPD: Demystifying Warm-up for On-policy Distillation
Simple-OPD warms up a student on the teacher's chain-of-thought traces with a LoRA adapter before on-policy distillation, improving in-domain reasoning while preserving out-of-domain performance.