Conversational Swarm Intelligence (CSI) Enhances Groupwise Deliberation

Real-time conversational deliberation is a critical groupwise method for reaching decisions, solving problems, evaluating priorities, generating ideas, and producing insights. Unfortunately, real-time conversation is difficult to scale, losing effectiveness in groups above 5–7 members. Conversational Swarm Intelligence (CSI) is a new method modeled on the dynamics of biological swarms. It aims to enable networked groups of any size to hold productive real-time deliberations that converge on unified solutions. CSI leverages the power of Large Language Models (LLMs) in a unique manner, allowing real-time dialog among small local groups while simultaneously enabling content propagation across much larger populations. In this way, CSI combines the benefits of small-scale deliberative reasoning and large-scale Collective Intelligence. In this study, we compare groups of 48 people using standard online chat to equally sized groups using a prototype chat-based CSI system called Thinkscape™. Results show that participants using CSI contributed 51% more content (p < 0.001) than those using standard chat, and that deliberations using CSI showed 37% less difference in contribution quantity between the most active versus least active members, indicating more balanced dialog. Also, a large majority of participants preferred deliberating using CSI over standard chat (p < 0.05) and reported feeling more impactful when doing so (p < 0.01). These results suggest that Conversational Swarm Intelligence is a promising technology for enabling large-scale deliberation.