"RLHF and IIA: Perverse Incentives."

Wanqiao Xu et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2312.01057

access: open

type: Informal or Other Publication

metadata version: 2023-12-08

a service of  Schloss Dagstuhl - Leibniz Center for Informatics