A Comparative Study of Technical Writing Feedback Quality: Evaluating LLMs, SLMs, and Humans in Computer Science Topics
Suqing Liu, Bogdan Simion, Christopher Eaton, Michael Liut
TL;DR
This study compares AI generated feedback from LLMs and SLMs to human feedback across three CS courses with technical writing components. Employing a mixed-methods design, it analyzes six facets of feedback quality and the ability of students to discern sources, revealing that AI helps with clarity and scalability in large courses while human feedback provides depth in writing intensive contexts. The findings support a hybrid, human in the loop approach that combines AI efficiency with personalized instructor input to achieve scalable yet high quality feedback. The work has practical implications for implementing scalable feedback systems in computing education while preserving essential human guidance.
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.