Practical PCG Through Large Language Models
This provides a practical method for procedural content generation in game development, though it is incremental as it applies existing LLM techniques to a specific domain.
The study tackled the problem of generating 2D-game rooms for a game called Metavoidal using Large Language Models (LLMs), achieving 37% playable-novel levels from only 60 hand-designed rooms through human-in-the-loop fine-tuning.
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.