DPL: Diverse Preference Learning Without A Reference Model

Abhijnan Nath | Andrey Volozin | Saumajit Saha | Albert Aristotle Nanda | Galina Grunin | Rahul Bhotika | Nikhil Krishnaswamy |

Paper Details:

Month: April
Year: 2025
Location: Albuquerque, New Mexico
Venue: NAACL |