Human-AI Interaction Generation: A Connective Lens for Generative AI and Procedural Content Generation

Human-AI Interaction Generation: A Connective Lens for Generative AI and Procedural Content Generation

Matthew Guzdial

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Early Career. Pages 8529-8534. https://doi.org/10.24963/ijcai.2024/977

Generative AI has recently gained popularity as a paradigm for content generation. In this paper, we link this paradigm to an older one: Procedural Content Generation (PCG). We propose a lens to identify the commonalities between both paradigms that we call human-AI interactive generation. Using this lens, we identify three beneficial attributes then survey recent related work and summarize relevant findings.
Keywords:
Humans and AI: HAI: Human-computer interaction
Machine Learning: ML: Generative models
Multidisciplinary Topics and Applications: MTA: Computer games
Humans and AI: HAI: Intelligent user interfaces