Using LLMs to Advance the Cognitive Science of Collectives

TL;DR

This paper explores how large language models can be utilized to advance the understanding of collective cognition, addressing existing complexities and highlighting potential risks that require new methodological approaches.

Contribution

It proposes a novel application of LLMs to study collective cognition and discusses associated challenges and risks.

Findings

LLMs can model complex collective cognitive processes.

Potential risks include biases and misinterpretations in collective modeling.

New methods are needed to mitigate these risks.

Abstract

LLMs are already transforming the study of individual cognition, but their application to studying collective cognition has been underexplored. We lay out how LLMs may be able to address the complexity that has hindered the study of collectives and raise possible risks that warrant new methods.