arXiv (All)
open access
On Repulsive and Attractive Teachers: Separating Correctness from Behavior in Self-Distillation
On-policy self-distillation provides dense, token-level supervision by conditioning a model on privileged information and distilling the resulting teacher distribution back into the model. However, privileged information can change not only what the teacher knows, but also how it behaves, entangling
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
- On Repulsive and Attractive Teachers: Separating Correctness from Behavior in Self-Distillation#1006920
- Beam Search as Test-Time Self-Distillation via Counterfactual Contexts#1132242
- Know Thyself, Teach Thyself: Internal Information Flow for Selective Self-Distillation#1131896
- Beyond Token Alignment: Event Completion for Cross-Tokenizer On-Policy Distillation#1128996
- Self-Distilled Agentic Reinforcement Learning#187299
Record · ID 1035958
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