"ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety ..."

Zhexin Zhang et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2402.16444

access: open

type: Informal or Other Publication

metadata version: 2024-03-25

a service of  Schloss Dagstuhl - Leibniz Center for Informatics