Order-Only On-Policy Distillation
Order-Only On-Policy Distillation
Order-Only On-Policy Distillation (O^{3}PD) trains student models to match the token ordering of the teacher model rather than probabilities, averaging 2.9 points better than OPD on HMMT25, AIME24, and AIME25, with a 5.6 point improvement on AIME25. This technique requires no temperature tuning and is unaffected by the teacher model's temperature.
Published on Nov 1
Authors:
,
Abstract
Order-only on-policy distillation trains students to match teacher token rankings rather than probabilities, improving reasoning performance without temperature tuning.
On-policy distillation (OPD) trains a student on its own generations by matching the teacher's token probabilities. These probabilities entangle two kinds of information: which tokens the teacher prefers, and how confident it is. The latter reflects the teacher's own capacity and calibration, which a smaller student may be unable to reproduce. Because the teacher temperature changes these values without changing the ordering, OPD is also sensitive to the temperature choice. We ask whether the teacher's ordering of candidate tokens is enough, and propose Order-Only On-Policy Distillation (O^{3}PD). At each student-generated prefix, O^{3}PD trains the student to reproduce the order of the teacher's top-K tokens, without fitting their probability values. The objective is therefore invariant to the teacher temperature and needs no temperature tuning. Across six teacher--student pairs, O^{3}PD outperforms OPD on the average over HMMT25, AIME24, and AIME25 in every pair, by up to 2.9 points, with gains of up to 5.6 points on AIME25. Other ranking losses yield similar gains, so the benefit comes from ordinal supervision itself. Analysis shows that O^{3}PD departs further from the teacher's probabilities than OPD, yet reproduces its ranking more faithfully and yields a stronger student. The ranking, not the probability values, thus carries the knowledge that on-policy distillation needs to transfer.
View arXiv page View PDF Add to collection
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.02112 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.02112 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.02112 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
Source: Hugging Face Daily Papers · huggingface.co