PuSH - Publication Server of Helmholtz Zentrum München

Schubert, J.A.* ; Jagadish, A.K. ; Binz, M. ; Schulz, E.

In-context learning agents are asymmetric belief updaters.

In: (Proceedings of Machine Learning Research). 2024. 43928-43946 (Proceedings of Machine Learning Research ; 235)
We study the in-context learning dynamics of large language models (LLMs) using three instrumental learning tasks adapted from cognitive psychology. We find that LLMs update their beliefs in an asymmetric manner and learn more from better-than-expected outcomes than from worse-than-expected ones. Furthermore, we show that this effect reverses when learning about counterfactual feedback and disappears when no agency is implied. We corroborate these findings by investigating idealized in-context learning agents derived through meta-reinforcement learning, where we observe similar patterns. Taken together, our results contribute to our understanding of how in-context learning works by highlighting that the framing of a problem significantly influences how learning occurs, a phenomenon also observed in human cognition.
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Conference contribution
Corresponding Author
Conference Title Proceedings of Machine Learning Research
Quellenangaben Volume: 235, Issue: , Pages: 43928-43946 Article Number: , Supplement: ,
Non-patent literature Publications
Institute(s) Institute of AI for Health (AIH)