arXiv (All)
open access
iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs
On-policy self-distillation fine-tuning (SDFT) learns new skills from demonstrations while reducing forgetting, but it always distils toward the full demonstration-conditioned teacher. This fixes teacher influence at the full-teacher endpoint, providing no control over how much demonstration informa
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
- iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs#1028706
- Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?#629949
- Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?#628087
- Understanding Off- vs On-Policy Distillation: A Tale of Distinct Training Objectives#1143267
- Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation#924147
Record · ID 1051053
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