AI Framework for Automated and Balanced Examination Question Paper Generation System

Author

B. Jyothsna, G. Tulasi, Ch. Roshini

Abstract

 Question paper preparation is a time-consuming task in educational institutions, requiring balanced syllabus coverage, appropriate difficulty levels, and alignment with course outcomes and bloom’s taxonomy. Existing automated systems mainly rely on manually prepared question banks or simple AI-based question generation, which often require human intervention to create a balanced examination paper. This paper proposes an AI-Framework for Automated and Balanced Examination Question Paper Generation System, which generates optimized question papers directly from course syllabus based on a predefined examination blueprint. The faculty can submit the syllabus of their respective courses in the form of a PDF file, and the text content of the PDF file is extracted and processed to extract important topics and concepts. Using RAG and LLMs, relevant examination questions are generated based on the uploaded file. The optimization process then selects and organizes the questions based on certain criteria, such as weightage, marks distribution, course objectives, Bloom’s taxonomy, difficulty level, and type of question. The generated question paper can be exported in PDF format for examination purposes. Overall, the proposed system reduces the time and effort involved in question paper preparation, improves consistency in assessment, and provides an efficient, scalable, and intelligent solution for automated examination paper generation. 

Keywords

Automated Question Paper Generation, Retrieval-Augmented Generation (RAG), Large Language Models (LLMs), Bloom’s Taxonomy, Course Outcomes, Constraint Optimization, Document Processing.

Full Text:

Download Paper PDF

References

[1] N. Pradeesh, T. Remya, M. G. Thushara, K. Arun Krishna, and V. Pranav, “Retrieval-Augmented Generation for Multiple-Choice Questions and Answers Generation,” Procedia Computer Science, vol. 259, pp. 504–511, 2025, doi: 10.1016/j.procs.2025.03.352.

[2] K. P. Kumar, G. A. Reddy, D. Vignesh, A. Pavan, T. Vamsi, K. Rishi, and K. S. Kumar, “Automated Question Paper Generator Using LLM,” International Journal of Research and Innovation in Applied Science, vol. X, no. IV, Apr. 2025, doi: 10.51584/IJRIAS.2025.10040020.

[3] G. Kurdi, J. Leo, B. Parsia, U. Sattler, and S. Al-Emari, “A Systematic Review of Automatic Question Generation for Educational Purposes,” International Journal of Artificial Intelligence in Education, vol. 30, no. 1, pp. 121–204, 2020, doi: 10.1007/s40593-019-00186-y.

[4] D. Mitroulias and S. Sioutas, “A Systematic Review and Bibliometric Analysis of Automated Multiple-Choice Question Generation,” Big Data and Cognitive Computing, vol. 10, no. 1, Art. no. 35, 2026, doi: 10.3390/bdcc10010035.

[5] A. Chaube, P. Chaurasia, K. Gupta, and S. Ghanate, “An AI-Driven System for Automated Question Paper Generation from Curriculum Documents,” PaperPilot, 2025.

[6] A. Kumar, R. Sharma, P. Gupta, and S. Patel, “AI-Based Question Paper Generation Using Historical Examination Data,” 2024.

[7] M. R. Anwar, S. Khalid, S. Alshahrani, H. S. M. Bilal, and M. Aldawsari, “MCQs Generation With Large Language Models: A Survey of Methodologies, Evolution, and Open Research Issues,” IEEE Access, vol. 14, 2026, doi: 10.1109/ACCESS.2026.3652006.

[8] C. Zhang, Y. Sun, H. Chen, and J. Wang, “Generating Adequate Distractors for Multiple-Choice Questions,” 2020.

[9] 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.

[10] P. H. S. Praveen, P. Khot, and O. Shinde, “AI-Driven Automated Question Paper Generator Using Past Exam Datasets,” IRE Journals, vol. 9, no. 10, 2026, doi: 10.64388/IREV9I10-1716734.

[11] N. Mulla and P. Gharpure, “Automatic Question Generation: A Review of Methodologies, Datasets, Evaluation Metrics, and Applications,” Progress in Artificial Intelligence, vol. 12, pp. 1–32, 2023, doi: 10.1007/s13748-023-00295-9.

[12] B. J. L. Narayana, V. N. S. Harsha, K. Prudhvi, B. G. H. Vardhan, and A. Sravika, “Automated Question Paper Generation using Natural Language Processing,” in 2024 International Conference on Computational Intelligence for Green and Sustainable Technologies (ICCIGST), 2024, doi: 10.1109/ICCIGST60741.2024.10717510.

[13] S. Mishra et al., “Towards Automatic Generation of Questions from Long Answers,” 2020.

[14] R. Bhirangi and S. Bhoir, “Automated Question Paper Generation System,” International Journal of Emerging Research in Management & Technology, vol. 5, no. 4, pp. 28–34, Apr. 2016.

[15] R. T. Sairaj and S. R. Balasundaram, “Ensemble learning with RAG model to reduce redundant question topics in auto-generated exam questions,” Discover Computing, vol. 28, no. 1, Art. no. 161, 2025.

 

 

 

 

 

Share your valuable work from Social Media Buttons