arXiv (All)
open access
How Much Do Teacher Bridges Matter in Interleaved On-Policy Distillation?
On-policy distillation (OPD) trains a student using teacher predictions on student-generated responses. Some methods insert teacher-written segments, or bridges, but disagree on how to train on those tokens. We compare no loss, forward KL and reverse KL on identical trajectories using Qwen3-1.7B as
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
- A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillation#1342593
- 1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation#1050609
- Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher#974116
- Rethinking On-Policy Distillation of Large Language Models II: One Training Example#927037
- When Top-K Misses the Decision: Tool-Call Drift in Multi-Teacher On-Policy Distillation#973255
Record · ID 1489175
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