Practical PCG Through Large Language Models

Muhammad U Nasir, Julian Togelius
5/20/2023
cs.CLcs.AI

No confident code implementation found for this paper. 3 possible matches can be shown below.

Abstract

Large Language Models (LLMs) have proven to be useful tools in various domains outside of the field of their inception, which was natural language processing. In this study, we provide practical directions on how to use LLMs to generate 2D-game rooms for an under-development game, named Metavoidal. Our technique can harness the power of GPT-3 by Human-in-the-loop fine-tuning which allows our method to create 37% Playable-Novel levels from as scarce data as only 60 hand-designed rooms under a scenario of the non-trivial game, with respect to (Procedural Content Generation) PCG, that has a good amount of local and global constraints.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 3 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Level Generation Through Large Language Models

86% match2023

Instruction-Driven Game Engines on Large Language Models

85% match1 repo132024

Instruction-Driven Game Engine: A Poker Case Study

85% match2024

From Code to Play: Benchmarking Program Search for Games Using Large Language Models

84% match2024

CALYPSO: LLMs as Dungeon Masters' Assistants

83% match1 repo282023

Large Language Models and Games: A Survey and Roadmap

83% match2024

Cite this paper

@article{nasir2023practical,
  title  = {Practical PCG Through Large Language Models},
  author = {Muhammad U Nasir and Julian Togelius},
  year   = {2023},
  eprint = {2305.18243},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.18243v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.18243.svg)](https://codeofpaper.com/paper/2305.18243)

Discussion