Beyond Token-Local Imitation: Reward-Compatible Temporal Credit Assignment for On-Policy Distillation
On-policy distillation (OPD) has emerged as an effective approach for large language model post-training, yet existing objectives face a trade-off between objective fidelity and optimization stability. Token-level OPD provides stable but local supervision, whereas sequence-level OPD captures future credit at the cost of horizon-dependent variance. We establish a unified temporal-credit view of these formulations, showing that practical token-level OPD can be interpreted as a temporal approximation to the sequence-level reverse-KL gradient. Building on this connection, we propose $γ$OPD (GammaOPD), which uses discounted temporal credit assignment to balance long-horizon supervision and opt...
| Authors | Shiqi Liu, Zeyu He, Letian Tao et al. |
|---|---|
| Primary category | cs.LG |
| Published | 15 September 2026 |
| Last updated at source | 19 September 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.