Using LLMs to Advance the Cognitive Science of Collectives
arXiv:2506.00052v19 citationsh-index: 13Nat Comput Sci
Originality Synthesis-oriented
AI Analysis
This work addresses the challenge of studying collective cognition for researchers in cognitive science, but it is incremental as it primarily outlines potential applications without new results.
The paper tackles the underexplored problem of applying LLMs to study collective cognition, proposing they can address complexity and highlighting risks that require new methods.
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.