"Don't Forget Your Reward Values: Language Model Alignment via Value-based ..."

Xin Mao et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2402.16030

access: open

type: Informal or Other Publication

metadata version: 2024-03-25

a service of  Schloss Dagstuhl - Leibniz Center for Informatics