Direct preference optimization (DPO), introduced by Rafailov et al. in 2024, is a method used to align model outputs and behaviors with human preferences.

Authors

• Person: Not available Organization: medRxiv
  Medical Hallucination in Foundation Models and Their ...

Sources

• Medical Hallucination in Foundation Models and Their ... www.medrxiv.org medRxiv via serper

Referenced by nodes (1)

• Direct Preference Optimization (DPO) concept