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

• URL: http://arxiv.org/abs/2601.11541v1
• Date: Mon, 01 Dec 2025 22:51:54 GMT
• Title: A Comparative Study of Technical Writing Feedback Quality: Evaluating LLMs, SLMs, and Humans in Computer Science Topics
• Authors: Suqing Liu, Bogdan Simion, Christopher Eaton, Michael Liut,
• Abstract summary: This study investigates the quality of feedback generated by Large Language Models (LLMs), Small Language Models (SLMs), and artificial intelligence (AI) tools.<n>We analyze the student perspective on feedback quality, evaluated based on multiple criteria, including readability, detail, specificity, actionability, helpfulness, and overall quality.<n>Our findings underscore the potential of hybrid approaches that combine AI and human feedback to achieve efficient and high-quality feedback at scale.
• Score: 3.2351366072725596
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Exposía: Academic Writing Assessment of Exposés and Peer Feedback [56.428320613219306]
  We present Exposa, the first public dataset that connects writing and feedback assessment in higher education.<n>We use Exposa to benchmark state-of-the-art open-source large language models (LLMs) for two tasks: automated scoring of (1) the proposals and (2) the student reviews.
  arXiv  Detail & Related papers  (2026-01-10T11:33:26Z)
• A Survey on Feedback Types in Automated Programming Assessment Systems [3.9845307287664973]
  This study investigates how different feedback mechanisms in APASs are perceived by students, and how effective they are in supporting problem-solving.<n>Results indicate that while students rate unit test feedback as the most helpful, AI-generated feedback leads to significantly better performances.
  arXiv  Detail & Related papers  (2025-10-21T09:08:22Z)
• CoCoNUTS: Concentrating on Content while Neglecting Uninformative Textual Styles for AI-Generated Peer Review Detection [60.52240468810558]
  We introduce CoCoNUTS, a content-oriented benchmark built upon a fine-grained dataset of AI-generated peer reviews.<n>We also develop CoCoDet, an AI review detector via a multi-task learning framework, to achieve more accurate and robust detection of AI involvement in review content.
  arXiv  Detail & Related papers  (2025-08-28T06:03:11Z)
• Teaching at Scale: Leveraging AI to Evaluate and Elevate Engineering Education [3.557803321422781]
  This article presents a scalable, AI-supported framework for qualitative student feedback using large language models.<n>The system employs hierarchical summarization, anonymization, and exception handling to extract actionable themes from open-ended comments.<n>We report on its successful deployment across a large college of engineering.
  arXiv  Detail & Related papers  (2025-08-01T20:27:40Z)
• The AI Imperative: Scaling High-Quality Peer Review in Machine Learning [49.87236114682497]
  We argue that AI-assisted peer review must become an urgent research and infrastructure priority.<n>We propose specific roles for AI in enhancing factual verification, guiding reviewer performance, assisting authors in quality improvement, and supporting ACs in decision-making.
  arXiv  Detail & Related papers  (2025-06-09T18:37:14Z)
• Enhancing tutoring systems by leveraging tailored promptings and domain knowledge with Large Language Models [2.5362697136900563]
  AI-driven tools like ChatGPT and Intelligent Tutoring Systems (ITS) have enhanced learning experiences through personalisation and flexibility.<n>ITSs can adapt to individual learning needs and provide customised feedback based on a student's performance, cognitive state, and learning path.<n>Our research aims to address these gaps by integrating skill-aligned feedback via Retrieval Augmented Generation (RAG) into prompt engineering for Large Language Models (LLMs)
  arXiv  Detail & Related papers  (2025-05-02T02:30:39Z)
• Analyzing Feedback Mechanisms in AI-Generated MCQs: Insights into Readability, Lexical Properties, and Levels of Challenge [0.0]
  This study delves into the linguistic and structural attributes of feedback generated by Google's Gemini 1.5-flash text model for computer science multiple-choice questions (MCQs)<n>Key linguistic metrics, such as length, readability scores (Flesch-Kincaid Grade Level), vocabulary richness, and lexical density, were computed and examined.<n>The findings reveal significant interaction effects between feedback tone and question difficulty, demonstrating the dynamic adaptation of AI-generated feedback within diverse educational contexts.
  arXiv  Detail & Related papers  (2025-04-19T09:20:52Z)
• Constructive Large Language Models Alignment with Diverse Feedback [76.9578950893839]
  We introduce Constructive and Diverse Feedback (CDF) as a novel method to enhance large language models alignment. We exploit critique feedback for easy problems, refinement feedback for medium problems, and preference feedback for hard problems. By training our model with this diversified feedback, we achieve enhanced alignment performance while using less training data.
  arXiv  Detail & Related papers  (2023-10-10T09:20:14Z)
• UltraFeedback: Boosting Language Models with Scaled AI Feedback [99.4633351133207]
  We present textscUltraFeedback, a large-scale, high-quality, and diversified AI feedback dataset. Our work validates the effectiveness of scaled AI feedback data in constructing strong open-source chat language models.
  arXiv  Detail & Related papers  (2023-10-02T17:40:01Z)
• Investigating Fairness Disparities in Peer Review: A Language Model Enhanced Approach [77.61131357420201]
  We conduct a thorough and rigorous study on fairness disparities in peer review with the help of large language models (LMs) We collect, assemble, and maintain a comprehensive relational database for the International Conference on Learning Representations (ICLR) conference from 2017 to date. We postulate and study fairness disparities on multiple protective attributes of interest, including author gender, geography, author, and institutional prestige.
  arXiv  Detail & Related papers  (2022-11-07T16:19:42Z)
• Effects of Human vs. Automatic Feedback on Students' Understanding of AI Concepts and Programming Style [0.0]
  The use of automatic grading tools has become nearly ubiquitous in large undergraduate programming courses. There is a relative lack of data directly comparing student outcomes when receiving computer-generated feedback and human-written feedback. This paper addresses this gap by splitting one 90-student class into two feedback groups and analyzing differences in the two cohorts' performance.
  arXiv  Detail & Related papers  (2020-11-20T21:40:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.