arXiv (All)
open access
Why On-Policy Distillation Sometimes Fails: Vanishing Learning Signals
On-policy distillation (OPD) enables effective capability transfer between language models, yet the mechanisms underlying its failures are not fully understood. Across code generation and mathematical reasoning, OPD with larger-scale teachers exhibits early loss plateaus, with an average final loss
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
- Recursive Offline Distillation via Entropy Gain Sampling and Answer Mixing#1356250
- No Pain, More Gain: Iterative Merging for Effective Multi-Teacher On-Policy Distillation#1129003
- DIAL-OPD: Learning More from Fewer Tokens in On-Policy Distillation#1248939
- Trapped by Their Own Rollouts: Understanding Aggregation--Rollout Feedback in Federated On-Policy Distillation#1116904
- RISE: Recursive Improvement via Self-Extrapolating Policy Distillation#972231
Record · ID 1248174
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