GENEVA: GENErating and Visualizing branching narratives using LLMs
This tool assists game developers and creative teams by automating narrative generation, potentially reducing the time and effort required for storytelling in RPGs and similar applications.
The authors tackled the challenge of creating branching narratives for dialogue-based role-playing games by developing GENEVA, a tool that uses GPT-4 to generate and visualize narrative graphs from high-level descriptions, demonstrating its application on four well-known stories.
Dialogue-based Role Playing Games (RPGs) require powerful storytelling. The narratives of these may take years to write and typically involve a large creative team. In this work, we demonstrate the potential of large generative text models to assist this process. \textbf{GENEVA}, a prototype tool, generates a rich narrative graph with branching and reconverging storylines that match a high-level narrative description and constraints provided by the designer. A large language model (LLM), GPT-4, is used to generate the branching narrative and to render it in a graph format in a two-step process. We illustrate the use of GENEVA in generating new branching narratives for four well-known stories under different contextual constraints. This tool has the potential to assist in game development, simulations, and other applications with game-like properties.