TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching

arXiv:2605.12288v3 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences over full sequences even though generation is driven by per-token decisions. Existing token-level extensions typically decompose a...

Läs hela artikeln hos källan.