arXiv (All)
open access
Understanding Off- vs On-Policy Distillation: A Tale of Distinct Training Objectives
On-policy distillation (OPD) learns from teacher feedback on student-generated responses and has shown promise in reducing forgetting relative to supervised fine-tuning (SFT). However, its benefits and fragility remain incompletely understood. We study sequential distillation from multiple teachers,
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
- Data-free On-policy Distillation#1136554
- TV-Regulated OPD: Direction Matters in On-Policy Distillation#985701
- Rethinking On-Policy Distillation of Large Language Models II: One Training Example#927037
- Beam Search as Test-Time Self-Distillation via Counterfactual Contexts#1132242
Record · ID 1143267
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