arXiv Open Access 2023

Generative Agent-Based Modeling: Unveiling Social System Dynamics through Coupling Mechanistic Models with Generative Artificial Intelligence

Navid Ghaffarzadegan Aritra Majumdar Ross Williams Niyousha Hosseinichimeh
Lihat Sumber

Abstrak

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.

Penulis (4)

N

Navid Ghaffarzadegan

A

Aritra Majumdar

R

Ross Williams

N

Niyousha Hosseinichimeh

Format Sitasi

Ghaffarzadegan, N., Majumdar, A., Williams, R., Hosseinichimeh, N. (2023). Generative Agent-Based Modeling: Unveiling Social System Dynamics through Coupling Mechanistic Models with Generative Artificial Intelligence. https://arxiv.org/abs/2309.11456

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2023
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓