GENEVA: GENErating and Visualizing branching narratives using LLMs
Abstract
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.
Cite
@article{arxiv.2311.09213,
title = {GENEVA: GENErating and Visualizing branching narratives using LLMs},
author = {Jorge Leandro and Sudha Rao and Michael Xu and Weijia Xu and Nebosja Jojic and Chris Brockett and Bill Dolan},
journal= {arXiv preprint arXiv:2311.09213},
year = {2024}
}
Comments
Accepted at IEEE Conference on Games 2024