Summary of Player-driven Emergence in Llm-driven Game Narrative, by Xiangyu Peng et al.
Player-Driven Emergence in LLM-Driven Game Narrative
by Xiangyu Peng, Jessica Quaye, Sudha Rao, Weijia Xu, Portia Botchway, Chris Brockett, Nebojsa Jojic, Gabriel DesGarennes, Ken Lobb, Michael Xu, Jorge Leandro, Claire Jin, Bill Dolan
First submitted to arxiv on: 25 Apr 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 abstract presents research on how interacting with large language models (LLMs) can lead to emergent behaviors, enabling players to shape game narratives. In a text-adventure game, gamers interact with non-player characters generated by GPT-4, a large language model. The study recruits 28 gamers and uses GPT-4 to convert gameplay logs into a node-graph representing the narrative. Results show that player interactions with the LLM’s non-deterministic behavior lead to the discovery of new emergent nodes that can be fun and engaging. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Players interact with large language models (LLMs) in a text-adventure game, creating new narratives through their conversations with non-player characters generated by GPT-4. The study finds that players who enjoy discovering new things tend to create the most emergent nodes, which were not part of the original story. |
Keywords
» Artificial intelligence » Gpt » Large language model
