Towards an LLM-powered Social Digital Twinning Platform

TL;DR

This paper introduces Social Digital Twinner, a social simulation platform powered by large language models that enables real-time, natural language interaction with complex social systems for scenario testing and intervention planning.

Contribution

It presents a novel integrated architecture combining real-world data, LLM-enabled simulation, and user interaction for social digital twinning.

Findings

Demonstrated real-time scenario testing for youth dropout intervention.

Enabled natural language interaction with complex social simulations.

Showcased collaborative design and refinement of social interventions.

Abstract

We present Social Digital Twinner, an innovative social simulation tool for exploring plausible effects of what-if scenarios in complex adaptive social systems. The architecture is composed of three seamlessly integrated parts: a data infrastructure featuring real-world data and a multi-dimensionally representative synthetic population of citizens, an LLM-enabled agent-based simulation engine, and a user interface that enable intuitive, natural language interactions with the simulation engine and the artificial agents (i.e. citizens). Social Digital Twinner facilitates real-time engagement and empowers stakeholders to collaboratively design, test, and refine intervention measures. The approach is promoting a data-driven and evidence-based approach to societal problem-solving. We demonstrate the tool's interactive capabilities by addressing the critical issue of youth school dropouts in Kragero, Norway, showcasing its ability to create and execute a dedicated social digital twin using natural language.