Saved in:
Bibliographic Details
Main Authors: Vu, Sinh Trong, Truong, Huong Thu, Do, Oanh Tien, Le, Tu Anh, Mai, Tai Tan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.21174
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913965648379904
author Vu, Sinh Trong
Truong, Huong Thu
Do, Oanh Tien
Le, Tu Anh
Mai, Tai Tan
author_facet Vu, Sinh Trong
Truong, Huong Thu
Do, Oanh Tien
Le, Tu Anh
Mai, Tai Tan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21174
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A ChatGPT-based approach for questions generation in higher education
Vu, Sinh Trong
Truong, Huong Thu
Do, Oanh Tien
Le, Tu Anh
Mai, Tai Tan
Computers and Society
Artificial Intelligence
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.
title A ChatGPT-based approach for questions generation in higher education
topic Computers and Society
Artificial Intelligence
url https://arxiv.org/abs/2507.21174