ARTIFICIAL INTELLIGENCE AND QUESTION GENERATION TECHNOLOGIES
The article examines the integration of artificial intelligence into the educational process, with a particular focus on the development
of question generation (QG) technologies. It analyzes the main types of QG systems, their functional principles, and the role of
large language models (GPT, LLaMA, T5) in generating contextually appropriate questions. Multimodal approaches and methods
based on deep contextual understanding are presented as key directions in modern QG research. The study also highlights major
challenges such as semantic ambiguity, hallucination, and the lack of sufficient language resources. The conclusion offers practical
recommendations for improving QG technologies and adapting them to educational needs.
1. Bayaliyev J. Bugungi kunda sun’iy intellekt // International scientific and practical conference “Worldview Horizons of
Artificial Intelligence Development”. – 2025. – № 5(24). – P. 71–81. – (E)ISSN 2181-1784. – DOI: 10.24412/2181-1784-
2025-24-71-81.
2. Wilcox J. Solving the Enigma: History of the Cryptanalytic Bombe. – Washington: Center for Cryptologic History, National
Security Agency, Revised 2006. – 54 p.
3. Say C. Yapay zekânın tohumları // Yapay zekâ (50 soruda). – İstanbul: İş Bankası Kültür Yayınları, 2020. – S. 1–2.
4. Du X., Shao J., Cardie C. Learning to Ask: Neural Question Generation for Reading Comprehension // Proceedings of the
55th Annual Meeting of the Association for Computational Linguistics. – Vancouver: ACL, 2017. – P. 1342–1352.
5. Mostafazadeh N., Misra I., Devlin J., Mitchell M., He X., Vanderwende L. Generating Natural Questions About an Image
[Electronic resource] // Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume
1: Long Papers). – Berlin: ACL, 2016. – P. 1802–1813. – Available at: https://aclanthology.org/P16-1169 (accessed:
12.12.2025).
6. Guo Sh., Liao L., Li C., Chua T.-S. A Survey on Neural Question Generation: Methods, Applications, and Prospects //
Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI-2024). – Jeju: IJCAI, 2024. – P.
8038–8047.
7. Hill F., Bordes A., Chopra S., Weston J. The Goldilocks Principle: Reading Children’s Books with Explicit Memory
Representations // International Conference on Learning Representations (ICLR). – San Juan: ICLR, 2016.
8. Yang Z., Qi P., Zhang S., et al. HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering // Proceedings
of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP). – Brussels: ACL, 2018. – P. 2369–
2380.
9. Alibekova R. O‘zbek tilshunosligida pragmatik birliklarning nutq jarayonidagi funksional xususiyatlari // Modern Education
and Development. – 2025. – № 38, ch. 3. – P. 228.
10. Kalai A. T., Vempala S. S. Calibrated Language Models Must Hallucinate. – OpenAI; Georgia Tech, 2024. – 21 March. –
12 p.
Copyright (c) 2025 «ACTA NUUz»
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
.jpg)
1.png)
