A ChatGPT-based approach for questions generation in higher education

Sinh Trong Vu, Huong Thu Truong, Oanh Tien Do, Tu Anh Le, Tai Tan Mai
7/26/2025
cs.CYcs.AI

No official code found. Best implementation: monke-letus/AIQAM-1st-24 (0 stars, last commit 2025-08-08).

Abstract

Large language models have been widely applied in many aspects of real life, bringing significant efficiency to businesses and offering distinctive user experiences. In this paper, we focus on exploring the application of ChatGPT, a chatbot based on a large language model, to support higher educator in generating quiz questions and assessing learners. Specifically, we explore interactive prompting patterns to design an optimal AI-powered question bank creation process. The generated questions are evaluated through a "Blind test" survey sent to various stakeholders including lecturers and learners. Initial results at the Banking Academy of Vietnam are relatively promising, suggesting a potential direction to streamline the time and effort involved in assessing learners at higher education institutes.

View on arXivView PDF

Code Implementations(1)

AIQAM’24 paper A ChatGPT-based approach for questions generation in higher education to the project. The work investigates prompt patterns for using ChatGPT to build university-level question banks, and evaluates quality via a “Blind Test” with lecturers and students; initial results are promising for reducing assessment time/effort.

00TeXAug 8, 20251 years ago

Similar Papers

Cite this paper

@article{vu2025chatgptbased,
  title  = {A ChatGPT-based approach for questions generation in higher education},
  author = {Sinh Trong Vu and Huong Thu Truong and Oanh Tien Do and Tu Anh Le and Tai Tan Mai},
  year   = {2025},
  eprint = {2507.21174},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2507.21174v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2507.21174.svg)](https://codeofpaper.com/paper/2507.21174)

Discussion