Research Summary: Self-Explanation Tutor for Active Study of CS1 Worked Examples

Research explores using Large Language Models (LLMs) to create an automated self-explanation tutor, ESSE, for introductory programming (CS1) worked examples. This tutor aims to transform passive learning into active study by providing immediate feedback on student-generated explanations, addressing the scalability challenge of human assessment in self-explanation techniques.

Why it matters

This development is strategically important as it introduces a potential technological solution to enhance active learning and personalized feedback in educational settings. By leveraging AI for pedagogical support, it could significantly improve learning outcomes and scale educational interventions that were previously resource-intensive.

Key insights

• Worked examples are a key pedagogical tool in introductory programming.
• Traditional expert explanations often lead to passive student engagement.
• Self-explanation, involving students analyzing and explaining solutions, converts passive learning into active study.
• Scaling self-explanation is difficult due to the challenges of assessing free-text explanations and providing timely feedback.
• The research investigates the potential of LLMs to automate the assessment and feedback process for self-explanations.
• ESSE, a self-explanation tutor, is being developed to allow students to explain lines of worked examples and receive immediate LLM-driven feedback on correctness and completeness.

Source

arXiv — Computers and Society — https://arxiv.org/abs/2608.25180