Visualization in the Era of Artificial Intelligence: Experiments for Creating Structural Visualizations by Prompting Large Language Models

Abstract

Large Language Models (LLMs) have revolutionized natural language processing by generating human-like text and images from textual input. However, their potential to generate complex 2D/3D visualizations has been largely unexplored. We report initial experiments showing that LLMs can generate 2D/3D visualizations that may be used for legal visualization. Further research is needed for complex 2D visualizations and 3D scenes. LLMs can become a powerful tool for many industries and applications, generating complex visualizations with minimal training.