"BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models."

Zhen Xiang et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2401.12242

access: open

type: Informal or Other Publication

metadata version: 2024-07-22

a service of  Schloss Dagstuhl - Leibniz Center for Informatics