Large-Language-Model-Powered Agent-Based Framework for Misinformation and Disinformation Research: Opportunities and Open Challenges

TL;DR

This paper discusses a new AI-powered agent-based framework for simulating and understanding misinformation and disinformation in social networks, highlighting opportunities and open challenges in this research area.

Contribution

It introduces a novel framework leveraging large language models to generate customizable social network agents for disinformation research.

Findings

Framework enables detailed simulation of disinformation spread

Highlights open challenges in AI-driven misinformation research

Provides opportunities for improved understanding of disinformation dynamics

Abstract

This article presents the affordances that Generative Artificial Intelligence can have in misinformation and disinformation contexts, major threats to our digitalized society. We present a research framework to generate customized agent-based social networks for disinformation simulations that would enable understanding and evaluating the phenomena whilst discussing open challenges.