Evaluating the Effectiveness of LLMs in Introductory Computer Science Education: A Semester-Long Field Study

TL;DR

This semester-long study evaluates how LLM-powered AI assistants like CodeTutor impact beginner programming students, showing improved scores but highlighting challenges in critical thinking development and user engagement.

Contribution

The paper provides empirical evidence on the effectiveness, student perceptions, and engagement dynamics of LLM-based tools in introductory computer science education.

Findings

Students using CodeTutor achieved higher final scores.

Students without prior LLM experience gained more from the tool.

User prompt quality significantly affected response effectiveness.

Abstract

The integration of AI assistants, especially through the development of Large Language Models (LLMs), into computer science education has sparked significant debate. An emerging body of work has looked into using LLMs in education, but few have examined the impacts of LLMs on students in entry-level programming courses, particularly in real-world contexts and over extended periods. To address this research gap, we conducted a semester-long, between-subjects study with 50 students using CodeTutor, an LLM-powered assistant developed by our research team. Our study results show that students who used CodeTutor (the experimental group) achieved statistically significant improvements in their final scores compared to peers who did not use the tool (the control group). Within the experimental group, those without prior experience with LLM-powered tools demonstrated significantly greater performance gain than their counterparts. We also found that students expressed positive feedback regarding CodeTutor's capability, though they also had concerns about CodeTutor's limited role in developing critical thinking skills. Over the semester, students' agreement with CodeTutor's suggestions decreased, with a growing preference for support from traditional human teaching assistants. Our analysis further reveals that the quality of user prompts was significantly correlated with CodeTutor's response effectiveness. Building upon our results, we discuss the implications of our findings for integrating Generative AI literacy into curricula to foster critical thinking skills and turn to examining the temporal dynamics of user engagement with LLM-powered tools. We further discuss the discrepancy between the anticipated functions of tools and students' actual capabilities, which sheds light on the need for tailored strategies to improve educational outcomes.