Players, creators, and AI collaborate to build and expand rich game narratives
Players, creators, and AI collaborate to build and expand rich game narratives
Players, creators, and AI collaborate to build and expand rich game narratives
Sudha Rao, Chris Brockett, Bill Dolan
August, 5, 2024
Summary
In the paper "Player-Driven Emergence in LLM-Driven Game Narrative," the authors explore how large language models (LLMs) like GPT-4 can enhance game narratives by empowering players to contribute creatively. Instead of replacing designers, LLMs enable dynamic interactions with nonplayer characters (NPCs), offering designers valuable feedback. The authors tested this approach in their game, Dejaboom!, a text-adventure where players interact with NPCs to prevent a village disaster. By analyzing player interactions through narrative graphs, they found that players introduced unique strategies, highlighting the potential for collaborative game design and the role of AI in creating evolving, player-driven experiences.
Reference
Rao, S., Brockett, C., & Dolan, B. (2024, August 5). Players, creators, and AI collaborate to build and expand rich game narratives. Microsoft Research. https://www.microsoft.com/en-us/research/blog/players-creators-and-ai-collaborate-to-build-and-expand-rich-game-narratives/