"ORPO: Monolithic Preference Optimization without Reference Model."

Jiwoo Hong, Noah Lee, James Thorne (2024)

Details and statistics

DOI: 10.48550/ARXIV.2403.07691

access: open

type: Informal or Other Publication

metadata version: 2024-04-04

a service of  Schloss Dagstuhl - Leibniz Center for Informatics