Leveraging the Potential of Large Language Models in Education Through Playful and Game-Based Learning

• DOI: 10.1007/s10648-024-09868-z
• Publication Date: 2024-02-27T03:02:11Z
• Authors: Stefan E. Huber; Kristian Kiili; Steve Nebel; Richard M. Ryan; Michael Sailer; Manuel Ninaus
• Keywords: Transformative Learning; Limiting; Educational Psychology

Abstract This perspective piece explores the transformative potential and associated challenges of large language models (LLMs) in education how those might be addressed utilizing playful game-based learning. While providing many opportunities, stochastic elements incorporated present LLMs process text, requires domain expertise for a critical evaluation responsible use generated output. Yet, due to their low opportunity cost, may pose some risk over-reliance, potentially unintendedly limiting development such expertise. Education is thus faced with challenge preserving reliable while not losing out on emergent opportunities. To address this challenge, we first propose approach focusing skill practice human judgment. Drawing from learning research, then go beyond account by reflecting well-designed games foster willingness practice, nurturing domain-specific We finally give new pedagogy AI utilize generating gamifying materials, leveraging full human-AI interaction education.