Summary of Game Plot Design with An Llm-powered Assistant: An Empirical Study with Game Designers, by Seyed Hossein Alavi et al.
Game Plot Design with an LLM-powered Assistant: An Empirical Study with Game Designers
by Seyed Hossein Alavi, Weijia Xu, Nebojsa Jojic, Daniel Kennett, Raymond T. Ng, Sudha Rao, Haiyan Zhang, Bill Dolan, Vered Shwartz
First submitted to arxiv on: 5 Nov 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
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 GamePlot is an LLM-powered assistant designed for game designers to craft immersive narratives for turn-based games. It allows users to test and refine the plot through collaborative gameplay. The user study with 14 game designers found high satisfaction and sense of ownership, but also highlighted limitations in generating complex content. Additionally, the paper explores how diverse user populations have different expectations from AI assistants, suggesting opportunities for tailored solutions that could boost job satisfaction, creativity, and innovation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary GamePlot is a tool that helps game designers make better games by creating stories and testing them with players. People who used GamePlot liked the results and felt like they had control over the story. However, it’s not perfect and can’t create super original ideas. The researchers also found that people from different backgrounds have different ideas about what makes a good AI tool, which could lead to better tools in the future. |
