"Are self-explanations from Large Language Models faithful?"

Andreas Madsen, Sarath Chandar, Siva Reddy (2024)

Details and statistics

DOI: 10.48550/ARXIV.2401.07927

access: open

type: Informal or Other Publication

metadata version: 2024-02-01

a service of  Schloss Dagstuhl - Leibniz Center for Informatics