arXiv (All)
open access
Rethinking On-Policy Distillation of Large Language Models II: One Training Example
On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision from a teacher. Existing work has mainly studied its algorithmic behavior, leaving the role of training data unclear. We examine this role at the data-minimal limit by training on a single query. One-
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Teacher Should Think Ahead: Adaptive Continuations for Reliable On-Policy Distillation#1036937
- Contrastive On-Policy Distillation#1143849
- 1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation#1050609
- Rethinking On-Policy Distillation of Large Language Models II: One Training Example#639704
- TV-Regulated OPD: Direction Matters in On-Policy Distillation#985701
Record · ID 927037
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive