Large language models for formative feedback in writing instruction: a systematic review of classroom interventions, feedback quality, and student outcomes
Authors:
Open Access
- 25 June 2026
- journal article
- review article
- Published by Frontiers Media SA in Frontiers in Education
- Vol. 11
Abstract
Introduction: Large language models (LLMs) are increasingly used to provide formative feedback in writing instruction, yet their pedagogical design, feedback quality, and effects on student outcomes require systematic synthesis. Methods: Following PRISMA 2020 guidelines, this review searched Scopus, IEEE Xplore, and ERIC for peer-reviewed studies published between November 2022 and February 2026. After screening and eligibility assessment, 34 studies were included. The synthesis focused on classroom interventions, the quality of LLM-generated feedback, and student learning outcomes. Results: The reviewed studies were conducted across 19 countries, with a strong concentration in university-level writing courses. Most interventions used ChatGPT or GPT-based systems through chatbot interfaces or integrated learning platforms. LLM-generated feedback supported writing productivity, linguistic accuracy, engagement, and feedback literacy, particularly by enabling rapid and iterative revision. However, human feedback remained stronger for higher-order writing issues, including argument development, contextual interpretation, prioritization of revision needs, and dialogic guidance. Discussion: The findings suggest that LLMs are most effective when used as supplementary feedback mechanisms rather than replacements for teachers. Hybrid feedback models that combine AI-generated suggestions with teacher mediation appear especially promising. Future research should strengthen instructional design, feedback literacy, ethical safeguards, and evidence from primary and secondary education contexts.Keywords
This publication has 47 references indexed in Scilit:
- The impact of ChatGPT’s feedback on L2 Chinese learners’ writing outcome, confidence, and emotions: A mixed-method quasi-experimental studyAssessing Writing, 2026
- Mediating L2 writing revision: The impact of teacher-moderated ChatGPT feedback on L2 accuracy and lexical diversityJournal of Second Language Writing, 2026
- Exploring the Use of Generative Artificial Intelligence as a Tool to Mediate the Emotional Nature of Feedback in Writing InstructionTESOL Journal, 2026
- Chinese EFL learners’ engagement with ChatGPT feedback on academic writing: A case study in MalaysiaComputers and Composition, 2025
- Large language models in education: a systematic review of empirical applications, benefits, and challengesComputers and Education: Artificial Intelligence, 2025
- Does metalinguistic explanation of teacher and ChatGPT feedback improve EFL learners’ writing quality and engagement? Findings from an intervention studyAssessment & Evaluation in Higher Education, 2025
- Designing ChatGPT-mediated feedback activities in EFL writing: a design-based study of the dialogic feedback triangleAssessment & Evaluation in Higher Education, 2025
- “ChatGPT is the companion, not enemies”: EFL learners’ perceptions and experiences in using ChatGPT for feedback in writingComputers and Education: Artificial Intelligence, 2024
- Exploring the impact of ChatGPT-generated feedback on technical writing skills of computing students: A blinded studyEducation and Information Technologies, 2024
- Comparing the quality of human and ChatGPT feedback of students’ writingLearning and Instruction, 2024