← Tuesday, October 13, 2026Models & trainingPaper

Offline student rollouts outperform on-policy distillation in 14 of 17 model pairs

huggingface.co by Siyan Zhao et al. Editor score 8/10

Semi-OPD beats on-policy distillation in 14 of 17 teacher-student pairs, with up to 13.6% higher accuracy and 11.4× faster training. The results challenge the assumption that on-policy sampling is always preferable and identify teacher-student alignment as a factor in choosing a recipe.

What

Semi-OPD distills teacher capabilities using offline rollouts generated by the initial student, as an alternative to on-policy distillation.

Method

Across 17 teacher-student pairs, Semi-OPD outperformed OPD in 14; the choice depends on the pair’s output-token overlap.

Why it matters

For model builders, student rollouts can offer more stable and efficient distillation when teacher and student are misaligned.

Read on huggingface.co →

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.