AI-Based UGC NET Quiz Generator Using Generative AI

Author

A. Asiyathul Sajitha , Dr. J. Evangelin Deva Sheela

Abstract

 Preparing for competitive examinations such as the University Grants Commission National Eligibility Test (UGC NET) requires continuous practice with subject-specific multiple-choice questions. Conventional online quiz systems generally depend on predefined question banks, which may provide limited question variety and require manual effort to create and maintain questions. This paper presents an AI-Based UGC NET Quiz Generator that uses Generative Artificial Intelligence to automatically create multiple-choice questions for UGC NET Computer Science and Applications preparation. The proposed system is developed using Python and Flask for the web application, MySQL for data management, and Gemini AI for question generation. The system provides Computer Science topics such as Programming in C, Computer Networks, Operating Systems, Database Management Systems, and Artificial Intelligence. Based on the selected topic, Gemini AI generates multiple-choice questions with four options, the correct answer, and an explanation. Students can attempt the generated quiz through an interactive interface, while the system automatically evaluates submitted answers and calculates the score and percentage. Quiz attempts are stored in the database so that students can review their previous performance through quiz history. A topic-wise leaderboard is also provided to display student rankings based on quiz performance. The proposed system provides a flexible approach to AI-assisted examination preparation by reducing manual question creation and providing topic-based practice.

Keywords

UGC NET, Generative AI, Gemini AI, Multiple Choice Questions, Quiz Generator, Computer Science, Flask, MySQL, Educational Technology.

Full Text:

Download Paper PDF

References

[1] A. Hadifar, S. K. Bitew, J. Deleu, C. Develder, and T. Demeester, “EduQG: A multi-format multiple-choice dataset for the educational domain,” IEEE Access, vol. 11, pp. 20885–20896, 2023, doi: 10.1109/ACCESS.2023.3248790.

[2] J. Ling and M. Afzaal, “Automatic question-answer pairs generation using pre-trained large language models in higher education,” Computers and Education: Artificial Intelligence, vol. 6, Art. no. 100252, 2024, doi: 10.1016/j.caeai.2024.100252.

[3] C. Grévisse, M. A. S. Pavlou, and J. G. Schneider, “Docimological quality analysis of LLM-generated multiple choice questions in computer science and medicine,” SN Computer Science, vol. 5, Art. no. 636, 2024, doi: 10.1007/s42979-024-02963-6.

[4] C. N. Hang, C. W. Tan, and P.-D. Yu, “MCQGen: A large language model-driven MCQ generator for personalized learning,” IEEE Access, vol. 12, pp. 102261–102273, 2024, doi: 10.1109/ACCESS.2024.3420709.

[5] S. Maity, A. Deroy, and S. Sarkar, “Can large language models meet the challenge of generating school-level questions?” Computers and Education: Artificial Intelligence, vol. 8, Art. no. 100370, 2025, doi: 10.1016/j.caeai.2025.100370.

[6] A. Tran, K. Angelikas, E. Rama, C. Okechukwu, D. H. Smith IV, and S. MacNeil, “Generating multiple choice questions for computing courses using large language models,” in 2023 IEEE Frontiers in Education Conference (FIE), College Station, TX, USA, 2023, pp. 1–8, doi: 10.1109/FIE58773.2023.10342898.

[7] S. Al Faraby, A. Romadhony, and Adiwijaya, “Analysis of LLMs for educational question classification and generation,” Computers and Education: Artificial Intelligence, vol. 7, Art. no. 100298, 2024, doi: 10.1016/j.caeai.2024.100298.

[8] S. Bhandari, Y. Liu, Y. Kwak, and Z. A. Pardos, “Evaluating the psychometric properties of ChatGPT-generated questions,” Computers and Education: Artificial Intelligence, vol. 7, Art. no. 100284, 2024, doi: 10.1016/j.caeai.2024.100284.

[9] G. Biancini, A. Ferrato, and C. Limongelli, “Multiple-choice question generation using large language models: Methodology and educator insights,” in Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization (UMAP '24), 2024, pp. 584–590, doi: 10.1145/3631700.3665233.

[10] L. Wang, R. Song, W. Guo, and H. Yang, “Exploring prompt pattern for generative artificial intelligence in automatic question generation,” Interactive Learning Environments, vol. 33, no. 3, pp. 2559–2584, 2025, doi: 10.1080/10494820.2024.2412082.

Share your valuable work from Social Media Buttons