arXiv (All)
open access
1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation
Sparse on-policy distillation (OPD) allocates teacher supervision to a small subset of tokens in student-generated trajectories. However, useful teacher guidance can yield a noisy update when its gradient is estimated from a sampled next token. We study this estimation problem at a fixed prefix in i
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
- Contrastive On-Policy Distillation#1143849
- Teacher Should Think Ahead: Adaptive Continuations for Reliable On-Policy Distillation#1036937
- Rethinking On-Policy Distillation of Large Language Models II: One Training Example#927037
- Distillation as Probability Transport: Routed On-Policy Distillation#985698
- Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation#925371
Record · ID 1050609
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