Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision

Collin Burns; Pavel Izmailov; Jan Hendrik Kirchner; Bowen Baker; Leo Gao; Leopold Aschenbrenner; Yining Chen; Adrien Ecoffet; Manas Joglekar; Jan Leike; Ilya Sutskever; Jeffrey Wu

2024 ICML ICML 2024

Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner, Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas Joglekar, Jan Leike, Ilya Sutskever, Jeffrey Wu

Topics

Artificial Intelligence > Core AI > AI Safety Machine Learning > Learning Types > Weakly Supervised Learning Artificial Intelligence > Core AI > Large Language Models

Keywords

weak supervision pre-trained model rlhf alignment strong generalization superhuman models

Download PDF