Saurav Kadavath, Tom Conerly, Amanda Askell, Tom Henighan, Dawn Drain, Ethan Perez, Nicholas Schiefer, Zac Hatfield-Dodds, Nova DasSarma, Eli Tran-Johnson · 2022 · arXiv
Finds that large models are fairly well calibrated about whether their answers are right and can be trained to predict whether they know an answer. An early baseline for self-knowledge.