Key points are not available for this paper at this time.
Generative Intelligent Tutoring Systems (ITSs), powered by advanced language models like GPT-4, represent a transformative approach to personalized education through real-time adaptability, dynamic content generation, and interactive learning. This study presents a modular framework for designing and evaluating such systems, leveraging GPT-4’s capabilities to enable Socratic-style interactions and personalized feedback. A pilot implementation, the Socratic Playground for Learning (SPL), was tested with 30 undergraduate students, focusing on foundational English skills. The results showed significant improvements in vocabulary, grammar, and sentence construction, alongside high levels of engagement, adaptivity, and satisfaction. The framework employs lightweight JSON structures to ensure scalability and versatility across diverse educational contexts. Despite its promise, challenges such as computational demands and content validation highlight the main areas for future refinement. This research establishes a foundational approach for advancing Generative ITSs, offering key insights into personalized learning and the broader potential of Generative AI in education.
Liu et al. (Wed,) studied this question.