arXiv (All)
open access
Gradient-Gated DPO: Stabilizing Preference Optimization in Language Models
Direct Preference Optimization (DPO) improves relative preference by increasing the margin between chosen and rejected responses, but this objective does not specify how probability mass should be redistributed to achieve that margin. Consequently, preference separation can improve even as probabili
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
- Gradient-Aligned Pair Selection for Personalized Preference Optimization#1154684
- ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking#147101
- Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference Data#1122560
- AI Revealed Preferences#971869
- Patterning in Practice: Debiasing Reward Models with Susceptibilities#820715
Record · ID 1049823
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