"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, ..."

Deep Ganguli et al. (2022)

Details and statistics

DOI: 10.48550/ARXIV.2209.07858

access: open

type: Informal or Other Publication

metadata version: 2022-09-27

a service of  Schloss Dagstuhl - Leibniz Center for Informatics