arXiv (All)
open access
A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillation
On-policy distillation (OPD) supervises a student on its own trajectories with token-level signals from a frozen teacher, yet how a sampled loss allocates updates across tokens remains poorly understood. We analyze the gradient of the per-token K2 estimator of reverse KL with respect to the student
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
- 1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation#1050609
- Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation#798469
- Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation#797056
- Leaky Students: Membership Inference against On-Policy Distillation#1117848
- Spend Teacher Tokens Where They Matter: Success-Referenced On-Policy Distillation#1186992
Record · ID 1342593
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