1 code implementation • NeurIPS 2023 • Ben Prystawski, Michael Y. Li, Noah D. Goodman
We investigate why and how chain-of-thought reasoning is useful in language models, testing the hypothesis that reasoning is effective when training data consists of overlapping local clusters of variables that influence each other strongly.
no code implementations • 6 Feb 2023 • Nishad Singhi, Florian Mohnert, Ben Prystawski, Falk Lieder
This creates an untapped opportunity to derive practical recommendations for which subgoals managers and individuals should set from cognitive models of bounded rationality.
1 code implementation • 16 Sep 2022 • Ben Prystawski, Paul Thibodeau, Christopher Potts, Noah D. Goodman
Probabilistic models of language understanding are valuable tools for investigating human language use.