arXiv (All)
open access
Correctness-Dependent Asymmetric Target Distributions for Self-Distillation Policy Optimization
Self-distillation policy optimization provides dense token-level supervision for LLM post-training through feedback-conditioned self-teachers. However, directly matching the self-teacher can disrupt successful behaviors on correct rollouts while providing insufficient correction on incorrect ones. W
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
- DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation#1200247
- Skill-Conditioned Gated Self-Distillation for LLM Reasoning#926054
- SimOPD: Relational Knowledge Transfer for On-Policy Distillation#1387584
- SimOPD: Relational Knowledge Transfer for On-Policy Distillation#1375094
- Teach Me After You Learn It: Lookahead Self-Distillation for RLVR#1343771
Record · ID 1401160
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