Summary of Word2world: Generating Stories and Worlds Through Large Language Models, by Muhammad U. Nasir et al.
Word2World: Generating Stories and Worlds through Large Language Models
by Muhammad U. Nasir, Steven James, Julian Togelius
First submitted to arxiv on: 6 May 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper introduces Word2World, a system that enables Large Language Models (LLMs) to procedurally design playable games through stories without task-specific fine-tuning. LLMs are leveraged to create diverse content and extract information, allowing them to create a story for the game, design narrative, and place tiles in appropriate places to create coherent worlds and playable games. The system is tested with different LLMs, and an ablation study is performed to validate each step. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Word2World uses Large Language Models (LLMs) to make video games. Normally, making games takes a lot of work and expertise. But Word2World makes it easier by using the same kind of models that are good at understanding language to create stories and designs for games. This means that people who aren’t experts in game-making can still create fun and playable games with the help of these language models. |
Keywords
» Artificial intelligence » Fine tuning
