"Jailbreak and Guard Aligned Language Models with Only Few In-Context ..."

Zeming Wei, Yifei Wang, Yisen Wang (2023)

Details and statistics

DOI: 10.48550/ARXIV.2310.06387

access: open

type: Informal or Other Publication

metadata version: 2023-10-25

a service of  Schloss Dagstuhl - Leibniz Center for Informatics