Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO

arXiv:2505.19770 · cs.LG, cs.CL · Submitted 2025-05-26 · Read on arXiv

cs.LG, cs.CL

Submitted: 2025-05-26

Updated: 2026-10-31

Code: https://github.com/ZHZisZZ/modpo

Terminology

Sources

Related papers