Generative Agent-Based Modeling: Unveiling Social System Dynamics through Coupling Mechanistic Models with Generative Artificial Intelligence
This provides a new approach for researchers and practitioners in social sciences to build more realistic simulation models of human behavior, though it is incremental as it applies existing AI methods to a new domain.
The paper tackles modeling social systems by coupling mechanistic models with generative AI to create Generative Agent-Based Models (GABMs), using a simple case of social norm diffusion in an organization to demonstrate feasibility and sensitivity to prompts.
We discuss the emerging new opportunity for building feedback-rich computational models of social systems using generative artificial intelligence. Referred to as Generative Agent-Based Models (GABMs), such individual-level models utilize large language models such as ChatGPT to represent human decision-making in social settings. We provide a GABM case in which human behavior can be incorporated in simulation models by coupling a mechanistic model of human interactions with a pre-trained large language model. This is achieved by introducing a simple GABM of social norm diffusion in an organization. For educational purposes, the model is intentionally kept simple. We examine a wide range of scenarios and the sensitivity of the results to several changes in the prompt. We hope the article and the model serve as a guide for building useful diffusion models that include realistic human reasoning and decision-making.