CoachGPT: A Scaffolding-based Academic Writing Assistant
Fumian Chen, Sotheara Veng, Joshua Wilson, Xiaoming Li, and Hui Fang

TL;DR
CoachGPT is an AI-powered web application that uses large language models to provide personalized, real-time feedback and guidance for academic writing, especially benefiting students with limited resources or self-paced learners.
Contribution
This paper introduces CoachGPT, a novel scaffolding-based system leveraging LLMs to enhance academic writing instruction and feedback.
Findings
User studies confirm CoachGPT's usefulness.
CoachGPT offers personalized, real-time feedback.
The system effectively assists learners with limited resources.
Abstract
Academic writing skills are crucial for students' success, but can feel overwhelming without proper guidance and practice, particularly when writing in a second language. Traditionally, students ask instructors or search dictionaries, which are not universally accessible. Early writing assistants emerged as rule-based systems that focused on detecting misspellings, subject-verb disagreements, and basic punctuation errors; however, they are inaccurate and lack contextual understanding. Machine learning-based assistants demonstrate a strong ability for language understanding but are expensive to train. Large language models (LLMs) have shown remarkable capabilities in generating responses in natural languages based on given prompts. Still, they have a fundamental limitation in education: they generate essays without teaching, which can have detrimental effects on learning when misused. To…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
