mlsanityData to 7 Oct 2026

Grammar-based Game Description Generation using Large Language Models

arXiv 2407.17404 ↗First posted 24 Jul 2024cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

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 paper 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. Our code is available at https://github.com/tsunehiko/ggdg

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 51 of its 80 references that are in the map. First posted on arXiv 24 Jul 2024.

Builds on

51 of 80 references.

References · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2022Training language models to follow instructions with human feedbackcited by 15,712
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  7. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  8. 2021Program Synthesis with Large Language Modelscited by 3,509
  9. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,115
  10. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  11. 2024A Survey on Large Language Models for Code Generationcited by 646
  12. 2022PAL: Program-aided Language Modelscited by 635
38 more
  1. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 542
  2. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
  3. 2022A Systematic Evaluation of Large Language Models of Codecited by 360
  4. 2024Long-context LLMs Struggle with Long In-context Learningcited by 285
  5. 2023Grammar-Constrained Decoding for Structured NLP Tasks without Finetuningcited by 186
  6. 2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 162
  7. 2022Synchromesh: Reliable code generation from pre-trained language modelscited by 156
  8. 2017Procedural Content Generation via Machine Learning (PCGML)cited by 136
  9. 2024LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuningcited by 133
  10. 2022Evolution through Large Modelscited by 131
  11. 2020Task-Oriented Dialogue as Dataflow Synthesiscited by 122
  12. 2023Language Model Crossover: Variation through Few-Shot Promptingcited by 119
  13. 2024Large Language Models and Games: A Survey and Roadmapcited by 91
  14. 2020PCGRL: Procedural Content Generation via Reinforcement Learningcited by 90
  15. 2023LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimizationcited by 86
  16. 2024LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discoverycited by 82
  17. 2020Deep Learning for Procedural Content Generationcited by 73
  18. 2023Level Generation Through Large Language Modelscited by 68
  19. 2023Evaluating Spatial Understanding of Large Language Modelscited by 65
  20. 2023MarioGPT: Open-Ended Text2Level Generation through Large Language Modelscited by 63
  21. 2023Grammar Prompting for Domain-Specific Language Generation with Large Language Modelscited by 58
  22. 2024Grammar-Aligned Decodingcited by 54
  23. 2019Ludii -- The Ludemic General Game Systemcited by 39
  24. 2024Game Generation via Large Language Modelscited by 24
  25. 2024GAVEL: Generating Games Via Evolution and Language Modelscited by 24
  26. 2023Practical PCG Through Large Language Modelscited by 21
  27. 2024Faster and Lighter LLMs: A Survey on Current Challenges and Way Forwardcited by 20
  28. 2024Word2World: Generating Stories and Worlds through Large Language Modelscited by 18
  29. 2019General Video Game Rule Generationcited by 17
  30. 2024DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraftcited by 17
  31. 2020Towards Game Design via Creative Machine Learning (GDCML)cited by 12
  32. 2024The Ink Splotch Effect: A Case Study on ChatGPT as a Co-Creative Game Designercited by 12
  33. 2020Conceptual Game Expansioncited by 11
  34. 2021General Board Game Conceptscited by 8
  35. 2021General Game Heuristic Prediction Based on Ludeme Descriptionscited by 7
  36. 2023Measuring Board Game Distancecited by 5
  37. 2021Adversarial Random Forest Classifier for Automated Game Designcited by 3
  38. 2022The Ludii Game Description Language is Universalcited by 3

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 2.

7 papers.

  1. 2024GPT for Games: An Updated Scoping Review (2020-2024)cited by 10
  2. 2025Grammar and Gameplay-aligned RL for Game Description Generation with LLMscited by 2
  3. 2025Boardwalk: Towards a Framework for Creating Board Games with LLMscited by 2
  4. 2026From Gameplay Traces to Game Mechanics: Causal Induction with Large Language Modelscited by 2
  5. 2025Automated Unity Game Template Generation from GDDs via NLP and Multi-Modal LLMscited by 1
  6. 2025Usando LLMs para Programar Jogos de Tabuleiro e Variacc~oescited by 0
  7. 2026Reasoning Capabilities of Large Language Models. Lessons Learned from General Game Playingcited by 0