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

2025-07-16

AI Summary

This work investigates the mechanisms underlying unconscious language generation in multi-person collaboration, focusing on phenomena such as Ouija boards—where implicit linguistic knowledge across individuals merges via shared physical interaction to yield coherent yet unintentional linguistic output. We propose CoCre-Sam, the first framework formalizing collective language generation as Langevin dynamics sampling over a superimposed energy landscape governed by multiple agents. Theoretically, we prove that group pointer motion is equivalent to Markov chain Monte Carlo (MCMC) sampling on a fused language model. Methodologically, individual energy functions are constructed from pretrained language models to encode distributed implicit knowledge, while stochastic inter-agent forces enable knowledge fusion. Simulations demonstrate stable generation of semantically meaningful character sequences. Ablation studies confirm that both collective interaction and stochasticity are indispensable for emergent linguistic coherence.

Technology Category

• Natural Language Processing: Generation
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

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.

Problem

• Modeling Ouija board as collective Langevin dynamics
• Understanding decentralized linguistic knowledge fusion
• Linking individual knowledge to emergent linguistic phenomena

Innovation

• Modeling Ouija board as collective Langevin dynamics
• Agents sample from fused language models
• Collective interaction enables emergent linguistic outputs