arXiv (All)
open access
GAW-PO: Preference Optimization with Gradient-Aligned Token Weights
Most preference optimization methods, such as Direct Preference Optimization (DPO), apply preference supervision at the response level, although autoregressive language models are optimized token by token. As a result, all tokens in a rejected response contribute to the negative training signal, inc
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
- Masking Frequent Tokens Sharpens Direct Preference Optimization#1116776
- TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching#178925
- Token-weighted Direct Preference Optimization with Attention#670599
- Token-weighted Direct Preference Optimization with Attention#668534
- PrefMoE: Robust Preference Modeling with Mixture-of-Experts Reward Learning#798876
Record · ID 1156783
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