"Provably Robust DPO: Aligning Language Models with Noisy Feedback."

Sayak Ray Chowdhury, Anush Kini, Nagarajan Natarajan (2024)

Details and statistics

DOI: 10.48550/ARXIV.2403.00409

access: open

type: Informal or Other Publication

metadata version: 2024-04-02

a service of  Schloss Dagstuhl - Leibniz Center for Informatics