arXiv (All)
open access
Beyond Distribution Matching: Selective Margin Preservation for Supervised Fine-Tuning
Supervised fine-tuning (SFT) changes logit margins among non-target tokens at teacher-forced prefixes. Matching a local reference distribution keeps those probabilities and also penalizes margin expansions. We ask whether a soft auxiliary can preserve selected local non-target margin relations witho
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
- CompassOPD: Cross-Family On-Policy Distillation via Within-Family Likelihood Shifts#997065
- CLIP-RD: Relational Distillation for Efficient CLIP Knowledge Distillation#998160
- Domain Mixture Design via Log-Likelihood Differences for Aligning Language Models with a Target Model#799978
- Relative Generalization Invariance of LLM Pretraining#1117728
- Recursive Self-Improvement in Unified Multimodal Models#1187680
Record · ID 1354374
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