"Technical Report: Large Language Models can Strategically Deceive their ..."

Jérémy Scheurer, Mikita Balesni, Marius Hobbhahn (2023)

Details and statistics

DOI: 10.48550/ARXIV.2311.07590

access: open

type: Informal or Other Publication

metadata version: 2023-11-21

a service of  Schloss Dagstuhl - Leibniz Center for Informatics