.png){kind=icon}
.png){kind=icon}
Return
Grammar-Based Game Description Generation Using Large Language Models
.png){kind=icon}
PRE
AI
DOI：10.1109/TG.2024.3520214.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Game description language (GDL) provides a standardized way to express diverse games in a machine-readable format, enabling automated game simulation, and evaluation. While previous research has explored game description generation using search-based methods, generating GDL descriptions from natural language remains a challenging task. This article presents a novel framework that leverages large language models (LLMs) to generate grammatically accurate game descriptions from natural language. Our approach consists of two stages: first, we gradually generate a minimal grammar based on GDL specifications; second, we iteratively improve the game description through grammar-guided generation. Our framework employs a specialized parser that identifies valid subsequences and candidate symbols from LLM responses, enabling gradual refinement of the output to ensure grammatical correctness. Experimental results demonstrate that our iterative improvement approach significantly outperforms baseline methods that directly use LLM outputs.
Keywords:
Games
Grammar
Natural languages
Iterative decoding
Accuracy
Large language models
Decoding
Symbols
Evolutionary computation
Semantics
Game description generation (GDG)
game description language (GDL)
grammar
large language model (LLM)
ludii