Turning large language models into cognitive models

TL;DR

This paper demonstrates that large language models, when fine-tuned on psychological data, can serve as accurate and versatile cognitive models of human behavior across various decision-making tasks.

Contribution

It shows that large language models can be transformed into cognitive models that outperform traditional models and generalize across tasks after fine-tuning.

Findings

Fine-tuned models accurately replicate human decision-making behavior.

Models outperform traditional cognitive models in two decision domains.

Fine-tuning enables models to predict behavior in unseen tasks.

Abstract

Large language models are powerful systems that excel at many tasks, ranging from translation to mathematical reasoning. Yet, at the same time, these models often show unhuman-like characteristics. In the present paper, we address this gap and ask whether large language models can be turned into cognitive models. We find that -- after finetuning them on data from psychological experiments -- these models offer accurate representations of human behavior, even outperforming traditional cognitive models in two decision-making domains. In addition, we show that their representations contain the information necessary to model behavior on the level of individual subjects. Finally, we demonstrate that finetuning on multiple tasks enables large language models to predict human behavior in a previously unseen task. Taken together, these results suggest that large, pre-trained models can be adapted to become generalist cognitive models, thereby opening up new research directions that could transform cognitive psychology and the behavioral sciences as a whole.