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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ghaffarzadegan, Navid, Majumdar, Aritra, Williams, Ross, Hosseinichimeh, Niyousha
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913192990474240
author Ghaffarzadegan, Navid
Majumdar, Aritra
Williams, Ross
Hosseinichimeh, Niyousha
author_facet Ghaffarzadegan, Navid
Majumdar, Aritra
Williams, Ross
Hosseinichimeh, Niyousha
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2309_11456
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Generative Agent-Based Modeling: Unveiling Social System Dynamics through Coupling Mechanistic Models with Generative Artificial Intelligence
Ghaffarzadegan, Navid
Majumdar, Aritra
Williams, Ross
Hosseinichimeh, Niyousha
Artificial Intelligence
Machine Learning
Multiagent Systems
Adaptation and Self-Organizing Systems
Physics and Society
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.
title Generative Agent-Based Modeling: Unveiling Social System Dynamics through Coupling Mechanistic Models with Generative Artificial Intelligence
topic Artificial Intelligence
Machine Learning
Multiagent Systems
Adaptation and Self-Organizing Systems
Physics and Society
url https://arxiv.org/abs/2309.11456