Turning large language models into cognitive models
This work addresses the problem of making AI models more human-like for cognitive psychology and behavioral sciences, offering a potentially transformative but incremental approach by adapting existing models.
The paper tackles the gap between large language models' capabilities and their unhuman-like characteristics by finetuning them on psychological experiment data, resulting in accurate representations of human behavior that outperform traditional cognitive models in decision-making domains and enable prediction in unseen tasks.
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.