CoCre-Sam (Kokkuri-san): Modeling Ouija Board as Collective Langevin Dynamics Sampling from Fused Language Models

TL;DR

This paper models the emergent linguistic outputs of collective activities like Ouija boards as Langevin dynamics sampling from fused language models, providing a computational framework for understanding collective implicit knowledge fusion.

Contribution

It introduces CoCre-Sam, a novel collective Langevin dynamics framework that mathematically links individual language priors, collective interaction, and emergent linguistic phenomena.

Findings

Simulations show effective fusion of models and meaningful sequence generation.

Theoretical proof connects collective motion to Langevin MCMC sampling.

Ablation studies confirm the importance of stochasticity and interaction.

Abstract

Collective human activities like using an Ouija board (or Kokkuri-san) often produce emergent, coherent linguistic outputs unintended by any single participant. While psychological explanations such as the ideomotor effect exist, a computational understanding of how decentralized, implicit linguistic knowledge fuses through shared physical interaction remains elusive. We introduce CoCre-Sam (Collective-Creature Sampling), a framework modeling this phenomenon as collective Langevin dynamics sampling from implicitly fused language models. Each participant is represented as an agent associated with an energy landscape derived from an internal language model reflecting linguistic priors, and agents exert stochastic forces based on local energy gradients. We theoretically prove that the collective motion of the shared pointer (planchette) corresponds to Langevin MCMC sampling from the sum of individual energy landscapes, representing fused collective knowledge. Simulations validate that CoCre-Sam dynamics effectively fuse different models and generate meaningful character sequences, while ablation studies confirm the essential roles of collective interaction and stochasticity. Altogether, CoCre-Sam provides a novel computational mechanism linking individual implicit knowledge, embodied collective action, and emergent linguistic phenomena, grounding these complex interactions in the principles of probabilistic sampling.