Utilizing ChatGPT in a Data Structures and Algorithms Course: A Teaching Assistant's Perspective
Pooriya Jamie, Reyhaneh Hajihashemi, Sharareh Alipour
TL;DR
This study investigates a TA-guided integration of ChatGPT in a DSA course, employing structured prompts and human verification to mitigate AI shortcomings. In a randomized trial with 40 undergraduates, the TA+ChatGPT group outperformed the traditional TA group, achieving a mean improvement of $16.50$ points with $p<0.001$, and excelling in advanced topics like recursion and dynamic programming. The research demonstrates that ChatGPT-4o and ChatGPT-o1 can play complementary roles in content generation and deep reasoning, respectively, when used under TA supervision. The findings support a scalable, human-in-the-loop approach to AI-assisted instruction that enhances learning outcomes while preserving accuracy and pedagogical integrity.
Abstract
Integrating large language models (LLMs) like ChatGPT into computer science education offers transformative potential for complex courses such as data structures and algorithms (DSA). This study examines ChatGPT as a supplementary tool for teaching assistants (TAs), guided by structured prompts and human oversight, to enhance instruction and student outcomes. A controlled experiment compared traditional TA-led instruction with a hybrid approach where TAs used ChatGPT-4o and ChatGPT o1 to generate exercises, clarify concepts, and provide feedback. Structured prompts emphasized problem decomposition, real-world context, and code examples, enabling tailored support while mitigating over-reliance on AI. Results demonstrated the hybrid approach's efficacy, with students in the ChatGPT-assisted group scoring 16.50 points higher on average and excelling in advanced topics. However, ChatGPT's limitations necessitated TA verification. This framework highlights the dual role of LLMs: augmenting TA efficiency while ensuring accuracy through human oversight, offering a scalable solution for human-AI collaboration in education.