International Journal of Artificial Intelligence and Education Technology
2835-2432ISSN (Online)
Volume 5 , Issue 1 , PP: 13–27, 2026 | Cite this article as | XML | Html | PDF | Full Length Article
Islombek Abdurakhmanov 1 * , Eugene Q. Castro 2
Doi: https://doi.org/10.54216/IJAIET.050102
AI-based quiz and assessment tools are widely studied for supporting adaptive learning, yet existing work is distributed across different tasks (e.g., question generation, automatic evaluation, feedback, and conversational assessment) and often uses inconsistent datasets and metrics, making comparisons difficult. This paper reports a Systematic Literature Review (SLR) conducted under PRISMA 2020 to summarize approaches and evaluation practices for AI-based quiz and assessment systems. Searches were performed in IEEE Xplore, ACM Digital Library, and Google Scholar using keyword combinations related to automated question generation, assessment, evaluation, and large language models. The search returned Nidentified=57 records; after duplicate removal, Ndedup=55 records remained for screening. Following title/abstract screening and full-text eligibility assessment, Nincluded=9 studies were included for qualitative synthesis and structured data extraction. The reviewed studies show strong attention to transformer/LLM-based question generation, automatic scoring and evaluation frameworks, and formative feedback generation for learning. However, recurring limitations include reliability of automated judging, lack of standardized benchmarks, domain transferissues, and risks impacting fairness and academic integrity. We conclude with practical recommendations for stronger evalua-tion design (e.g., shared benchmarks, transparent rubrics, and human-in-the-loop validation) to improve trust and real-world adoption.
Systematic literature review , PRISMA 2020 , AI in education , Adaptive learning , Automated assessment , Question generation , Evaluation metrics , Formative feedback , Large language models
[1] Awalurahman, H. W., Aji, R. F., & Budi, I. (2025). Transformer and large language models for automatic multiple-choice question generation: A systematic literature review. IEEE Access, 13, 127100–127112. doi: https://doi.org/10.1109/ACCESS.2025.3590423
[2] Bergerhoff, J., Bendler, J., Stefanov, S., Cavinato, E., Esser, L., Tran, T., & H¨arm¨a, A. (2024). Automatic conversational assessment using large language model technology. In Proceedings of the 2024 16th International Conference on Education Technology and Computers (ICETC 2024) (pp. 39–45). ACM. doi: https://doi.org/10.1145/3702163.3702169
[3] Dong, X., Zhang, X., Li, Z., Hou, Q., Xue, J., & Li, X. (2025). A literature review of research on question generation in education. PeerJ Computer Science, 11, e3203. doi: https://doi.org/10.7717/ peerj-cs.3203
[4] Hassan, A., & Eid, M. (2025). A systematic review of automatic neural question generation. Journal of the ACS Advances in Computer Science, 16(1). doi: https://doi.org/10.21608/asc.2025.445988
[5] Li, Y., Wu, J., Tu, S., Yu, J., Liu, H., Hou, L., & Li, J. (2025). VocQuiz: Vocabulary question generation for English language education. In Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM ’25) (pp. 5847–5854). ACM. doi: https://doi.org/10.1145/ 3746252.3761546
[6] Mahinpei, R., Xu, I., Wolfman, S. A., & Moosvi, F. (2025). A generalized framework for describing question randomization. In Proceedings of the 2025 ACM Conference on International Computing Education Research, Volume 1 (ICER 2025) (pp. 344–353). ACM. doi: https://doi.org/10.1145/3702652. 3744222
[7] Toba, H., Yudha, L. G. O. P., Karnalim, O., Bunyamin, H., & Tada, T. (2024). A large language model question generator based on Bloom’s taxonomy template. In Proceedings of the 2024 8th International Conference on Education and E-Learning (ICEEL 2024) (pp. 25–31). ACM. doi: https://doi.org/10.1145/ 3719487.3719537
[8] van Campenhout, R., Clark, M. W., Dittel, J. S., Jerome, B., Brown, N., & Johnson, B. (2025). AIgenerated formative practice and feedback: Performance benchmarks and applications in higher education. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIMECon): Full Papers (pp. 337–344). National Council on Measurement in Education. Available at https: //aclanthology.org/2025.aimecon-main.36/
[9] Van Campenhout, R., Autry, K. S., Clark, M. W., & Johnson, B. G. (2025). Scaling the doer effect: A replication analysis using AI-generated questions. In Proceedings of the Twelfth ACM Conference on Learning @ Scale (L@S ’25) (pp. 24–34). ACM. doi: https://doi.org/10.1145/3698205.3729545
