Rafailov, 2023 — Direct Preference Optimization: Your Language Model is Secretly a Reward Model

DOI: <a href="https://doi.org/10.52202/075280-2338" target="_blank" rel="noopener noreferrer">https://doi.org/10.52202/075280-2338
URL: <a href="https://arxiv.org/abs/2305.18290" target="_blank" rel="noopener noreferrer">https://arxiv.org/abs/2305.18290

Covers preference-learning or reward-modeling methods used in modern alignment pipelines.

Publication links

Covers preference-learning or reward-modeling methods used in modern alignment pipelines.