A Comparative Study of Technical Writing Feedback Quality: Evaluating LLMs, SLMs, and Humans in Computer Science Topics

TL;DR

This study compares the quality of feedback from Large Language Models, Small Language Models, and humans across different computer science courses, highlighting strengths, limitations, and scalability of AI-generated feedback.

Contribution

It provides a comprehensive evaluation of AI versus human feedback in technical writing, emphasizing the potential of hybrid approaches for scalable, high-quality educational feedback.

Findings

AI models deliver clear, actionable feedback in large courses.

Humans provide more nuanced, personalized guidance.

AI feedback is effective at scale but less personalized.

Abstract

Feedback is a critical component of the learning process, particularly in computer science education. This study investigates the quality of feedback generated by Large Language Models (LLMs), Small Language Models (SLMs), compared with human feedback, in three computer science course with technical writing components: an introductory computer science course (CS2), a third-year advanced systems course (operating systems), and a third-year writing course (a topics course on artificial intelligence). Using a mixed-methods approach which integrates quantitative Likert-scale questions with qualitative commentary, we analyze the student perspective on feedback quality, evaluated based on multiple criteria, including readability, detail, specificity, actionability, helpfulness, and overall quality. The analysis reveals that in the larger upper-year operating systems course ($N=80$), SLMs and LLMs are perceived to deliver clear, actionable, and well-structured feedback, while humans provide more contextually nuanced guidance. As for the high-enrollment CS2 course ($N=176$) showed the same preference for the AI tools' clarity and breadth, but students noted that AI feedback sometimes lacked the concise, straight-to-the-point, guidance offered by humans. Conversely, in the smaller upper-year technical writing course on AI topics ($N=7$), all students preferred feedback from the course instructor, who was able to provide clear, specific, and personalized feedback, compared to the more general and less targeted AI-based feedback. We also highlight the scalability of AI-based feedback by focusing on its effectiveness at large scale. Our findings underscore the potential of hybrid approaches that combine AI and human feedback to achieve efficient and high-quality feedback at scale.