Using LLMs to Advance the Cognitive Science of Collectives

2025/05/28 by Ilia Sucholutsky, Sucholutsky, Ilia, Katherine M. Collins +8 · 1 voice · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · #Artificial Intelligence (cs.AI) #FOS: Biological sciences #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Multiagent Systems (cs.MA) #Neurons and Cognition (q-bio.NC) #Semantic Web and Ontologies #Social and Information Networks (cs.SI) #cs.AI #cs.HC #cs.MA #cs.SI #q-bio.NC

paper · pdf · doi:10.48550/arxiv.2506.00052

openalex publication_date 2025/05/28 · arxiv published 2025/05/28 · arxiv updated 2025/05/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• On Benchmarking Human-Like Intelligence in Machines
• LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals
• Benchmarking Distributional Alignment of Large Language Models
• Centaur: a foundation model of human cognition
• AI can help humans find common ground in democratic deliberation
• Building Machines that Learn and Think with People
• Large Language Models and Games: A Survey and Roadmap
• Unintended Impacts of LLM Alignment on Global Representation
• Machine culture
• Getting aligned on representational alignment
• From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought
• Large language models predict human sensory judgments across six modalities
• From partners to populations: A hierarchical Bayesian account of coordination and convention
• The Dynamics of Collective Creativity in Human-AI Hybrid Societies

Cited by

• Generation and Evaluation in the Human Invention Process through the Lens of Game Design

Discussions

• Using LLMs to advance the cognitive science of collectives Very interesting new paper by @sucholutsky.bsky.social Katherine Collins @norijacoby.bsky.social @billdthompson @roberthawkins.bsky.social ar [bsky, 3 points, 0 comments]

Related

• United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory
• GPT-ology, Computational Models, Silicon Sampling: How should we think about LLMs in Cognitive Science?
• A Survey on Human-Centric LLMs
• Mind the (Belief) Gap: Group Identity in the World of LLMs
• Enhancing Computational Cognitive Architectures with LLMs: A Case Study