Crosslingual On-Policy Self-Distillation for Multilingual Reasoning
Large language models (LLMs) have achieved remarkable progress in mathematical reasoning, but this ability is not equally accessible across languages. Especially low-resource languages exhibit much lower reasoning performance. To address this, we propose Crosslingual On-Policy Self-Distillation (COPSD), which transfers a model's own high-resource reasoning behavior to low-resource languages. COPSD uses the same model as student and teacher: the student sees only the low-resource problem, while the teacher receives privileged crosslingual context, including the problem translation and reference solution in English. Training minimizes full-distribution token-level divergence on the student'...
| Authors | Yihong Liu, Raoyuan Zhao, Michael A. Hedderich et al. |
|---|---|
| Primary category | cs.CL |
| Published | 10 May 2026 |
| Last updated at source | 10 May 2026 |
Popularity, last 2 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- yihongLiu/COPSD-AfriMGSM-TrainDatasetDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.