Examining the Feasibility of AI-Generated Questions in Educational Settings

Zeghouani, Omar; Ali, Zawar; Simson Van Dijkhuizen, William; Wei Hong, Jia; Clos, Jeremie

Abstract

Educators face ever-growing time constraints, leading to poor work-life balance and a negative impact on work quality. Through their language generation capabilities, large language models offer an interesting avenue to ease this academic workload, allowing both students and lecturers to generate educational content. In this work, we leverage the latest developments in automatic speech recognition, natural language generation, retrieval-augmented generation, and multimodal models to design the Augmented Lecture Integration Network (ALINet), a system capable of producing a diverse range of high-quality assessment questions from lecture content. We inform the design of our system through a series of automated experiments using public datasets and evaluate it with a user study conducted on students and educators. Our results indicate a generally positive perception of the system’s performance, particularly in generating natural and clear questions relevant to the taught content, demonstrating its potential as a valuable resource in educational settings. This project lays the foundation for future research in multimodal educational question generation and is available for reuse in our public repository.

Citation

Zeghouani, O., Ali, Z., Simson Van Dijkhuizen, W., Wei Hong, J., & Clos, J. (2024, September). Examining the Feasibility of AI-Generated Questions in Educational Settings. Presented at Second International Symposium on Trustworthy Autonomous Systems (TAS '24), Austin, Texas, USA

• Presentation Conference Type: Conference Paper (published)
• Conference Name: Second International Symposium on Trustworthy Autonomous Systems (TAS '24)
• Start Date: Sep 16, 2024
• End Date: Sep 18, 2024
• Acceptance Date: Jul 22, 2024
• Online Publication Date: Sep 16, 2024
• Publication Date: Sep 16, 2024
• Deposit Date: Aug 19, 2024
• Publicly Available Date: Sep 24, 2024
• Publisher: Association for Computing Machinery (ACM)
• Peer Reviewed: Peer Reviewed
• Article Number: 36
• Pages: 1-6
• Book Title: TAS '24: Proceedings of the Second International Symposium on Trustworthy Autonomous Systems
• ISBN: 9798400709890
• DOI: https://doi.org/10.1145/3686038.3686652
• Keywords: CCS Concepts; Computing methodologies → Natural language processing;; Human-centered computing → Interactive systems and tools Keywords Educational Question Generation, Large Language Models, Genera- tive AI
• Public URL: https://nottingham-repository.worktribe.com/output/38634416
• Publisher URL: https://dl.acm.org/doi/10.1145/3686038.3686652
• Related Public URLs: https://symposium.tas.ac.uk/2024/