GENEVA: GENErating and Visualizing branching narratives using LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Leandro, Jorge, Rao, Sudha, Xu, Michael, Xu, Weijia, Jojic, Nebosja, Brockett, Chris, Dolan, Bill
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913379335012352
author Leandro, Jorge
Rao, Sudha
Xu, Michael
Xu, Weijia
Jojic, Nebosja
Brockett, Chris
Dolan, Bill
author_facet Leandro, Jorge
Rao, Sudha
Xu, Michael
Xu, Weijia
Jojic, Nebosja
Brockett, Chris
Dolan, Bill
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2311_09213
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle GENEVA: GENErating and Visualizing branching narratives using LLMs
Leandro, Jorge
Rao, Sudha
Xu, Michael
Xu, Weijia
Jojic, Nebosja
Brockett, Chris
Dolan, Bill
Computation and Language
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.
title GENEVA: GENErating and Visualizing branching narratives using LLMs
topic Computation and Language
url https://arxiv.org/abs/2311.09213