Word2World: Generating Stories and Worlds through Large Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Nasir, Muhammad U., James, Steven, Togelius, Julian
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916241992581120
author Nasir, Muhammad U.
James, Steven
Togelius, Julian
author_facet Nasir, Muhammad U.
James, Steven
Togelius, Julian
contents Large Language Models (LLMs) have proven their worth across a diverse spectrum of disciplines. LLMs have shown great potential in Procedural Content Generation (PCG) as well, but directly generating a level through a pre-trained LLM is still challenging. This work introduces Word2World, a system that enables LLMs to procedurally design playable games through stories, without any task-specific fine-tuning. Word2World leverages the abilities of LLMs to create diverse content and extract information. Combining these abilities, LLMs can create a story for the game, design narrative, and place tiles in appropriate places to create coherent worlds and playable games. We test Word2World with different LLMs and perform a thorough ablation study to validate each step. We open-source the code at https://github.com/umair-nasir14/Word2World.
format Preprint
id arxiv_https___arxiv_org_abs_2405_06686
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Word2World: Generating Stories and Worlds through Large Language Models
Nasir, Muhammad U.
James, Steven
Togelius, Julian
Computation and Language
Artificial Intelligence
Large Language Models (LLMs) have proven their worth across a diverse spectrum of disciplines. LLMs have shown great potential in Procedural Content Generation (PCG) as well, but directly generating a level through a pre-trained LLM is still challenging. This work introduces Word2World, a system that enables LLMs to procedurally design playable games through stories, without any task-specific fine-tuning. Word2World leverages the abilities of LLMs to create diverse content and extract information. Combining these abilities, LLMs can create a story for the game, design narrative, and place tiles in appropriate places to create coherent worlds and playable games. We test Word2World with different LLMs and perform a thorough ablation study to validate each step. We open-source the code at https://github.com/umair-nasir14/Word2World.
title Word2World: Generating Stories and Worlds through Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2405.06686