Repository Feedback

Your feedback helps us improve the repository's content relevance and usability. Please share your thoughts to help us better serve researchers and practitioners.

Submit feedback

Submit a research study

Contribute to the repository:

Add a paper

A ChatGPT-Based Approach For Questions Generation In Higher Education

Authors
Sinh Trong Vu,
Huong Thu Truong,
Oanh Tien Do,
Tu Anh Le,
Tai Tan Mai
Date
Publisher
arXiv
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.
Study at a glance
  • Question: How can ChatGPT be used to help higher education instructors generate quiz questions?
  • Setting and data: Banking Academy of Vietnam, with stakeholders including lecturers and learners.
  • Method: Blind test survey of lecturers and learners evaluating AI-generated quiz questions.
Why it matters

Educators need support generating quiz questions and assessing learners. Exploring interactive prompting patterns helps design an optimal AI-powered question bank creation process using ChatGPT.

Key findings
  • At the Banking Academy of Vietnam, ChatGPT produced relatively promising initial results for generating quiz questions to assess higher education learners.
  • Lecturers and learners gave relatively promising evaluations to the AI-generated quiz questions in blind test surveys.
  • AI-generated questions showed potential to streamline the time and effort involved in assessing learners at higher education institutes.

Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.

What is the application?
Who is the user?
Who age?
Why use AI?