arXiv (All)
open access
What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection
On-Policy Distillation (OPD) has emerged as a widely adopted post-training paradigm for enhancing large language models in reasoning domains. However, the data-centric mechanisms in OPD remain relatively underexplored. This paper presents a empirical study of data efficiency and data selection in OP
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
- Rethinking On-Policy Distillation of Large Language Models II: One Training Example#927037
- TV-Regulated OPD: Direction Matters in On-Policy Distillation#985701
- Unbiased Top-$k$ Estimation for On-Policy Distillation#1128717
- No Pain, More Gain: Iterative Merging for Effective Multi-Teacher On-Policy Distillation#1129003
- Beyond Imitation: Reflective On-Policy Self-Distillation for LLM Reasoning#1129277
Record · ID 972142
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