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

A novel application of large language models (LLMs) has been developed to enhance active learning in introductory programming education. This system, ESSE, functions as a self-explanation tutor, providing immediate, automated feedback on student explanations of programming concepts. The initiative addresses the traditional scalability challenges associated with assessing free-text explanations, aiming to transform passive learning from 'worked examples' into an active, engaging process.

Why it matters

This development represents a significant step in leveraging AI for educational transformation, particularly in technical fields. It offers a scalable solution for fostering active learning and critical thinking, which can improve educational outcomes and address skill gaps in technical workforces. Institutions adopting such technologies could gain a strategic advantage in learner engagement and efficiency.

Key insights

• Worked examples are a recognized pedagogical tool in introductory programming, but their study is often passive.
• Self-explanation is an active learning strategy where students explain problems and solutions, including subgoal-level analysis.
• Scaling self-explanation traditionally faces challenges due to the difficulty of automated assessment and timely feedback on free-text student responses.
• A new self-explanation tutor, ESSE, leverages large language models (LLMs) to provide immediate feedback on the correctness and completeness of student explanations.
• The research investigates the capacity of LLMs to effectively assess student explanations, filling a critical gap in scalable active learning methods.

Source

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