Ai-Driven Automated Question Paper Generation Using Syllabus Analysis and Difficulty-Level Modeling

Abstract

The AI-Based Question Paper Generation System is a smart web application designed to automate the creation of question papers using artificial intelligence. The system aims to reduce the manual effort involved in paper setting while ensuring quality, consistency, and syllabus coverage. The application is built using a modern full-stack architecture, where the frontend is developed using React with TypeScript to provide an interactive and user-friendly interface for teachers. The backend is implemented using Node.js and Express.js, which handles business logic, API requests, authentication, and communication with external services. The system integrates with an AI model (such as a large language model) to dynamically generate question papers based on user inputs like subject, topics, difficulty level, and marks distribution. For data management, Supabase (PostgreSQL) is used to store user information, generated question papers, and historical data, while Supabase Storage is utilized for handling uploaded files such as syllabus documents. The system follows a secure authentication mechanism using JSON Web Tokens (JWT) to ensure protected access to resources. The overall workflow involves users providing input through the frontend, which is sent to the backend via REST APIs. The backend processes the request, interacts with the AI service to generate questions, stores the results in the database, and returns the generated paper to the user for preview and download. This system improves efficiency, reduces human errors, and enables scalable and customizable question paper generation, making it highly beneficial for educational institutions and teachers

Introduction

The AI-Based Question Paper Generation System is a web-based platform designed to automate and optimize the creation of academic question papers. It addresses limitations of traditional manual methods, such as time consumption, human errors, uneven difficulty distribution, and incomplete syllabus coverage. The system allows teachers to input parameters like subject, topics, question types, marks distribution, and difficulty levels. Using AI techniques, it generates well-structured, syllabus-aligned, and balanced question papers efficiently.

Built on a full-stack architecture with React (frontend) and Node.js/Express.js (backend), the system integrates a database to manage question banks, user data, and historical records. Features include automatic marks allocation, customizable formats, preview/download options, and secure access. The platform enhances productivity, ensures fairness, and reduces human bias, while being scalable and adaptable for future improvements such as multi-language support, automatic answer key generation, and advanced AI-based question optimization.

It represents a modern, intelligent, and sustainable solution that streamlines the examination process and improves assessment quality in educational institutions.

References

[1] K. Smith, “Automated Question Generation Using Natural Language Processing,” Int. J. Artificial Intelligence Research, vol. 4, no. 2, pp. 34–45, 2015. [2] R. Gupta, “Intelligent Examination System Using Machine Learning,” Int. J. Computer Applications, vol. 6, no. 3, pp. 78–89, 2017. [3] S. Lee, “Web-Based Examination Management System,” Int. J. Web Engineering, vol. 8, no. 1, pp. 22–35, 2018. [4] A. Kumar, “Role of Artificial Intelligence in Education Systems,” Int. J. Educational Technology, vol. 9, no. 2, pp. 50–62, 2019. [5] P. Sharma, “Secure Online Examination Systems Using Authentication Techniques,” Int. J. Cyber Security, vol. 10, no. 3, pp. 90–102, 2020. [6] L. Wang, “Cloud-Based Scalable Architecture for E-Learning Platforms,” Int. J. Cloud Computing, vol. 11, no. 1, pp. 60–75, 2020. [7] D. Patel, “Automated Question Paper Generation Using Rule-Based Systems,” Int. J. Software Engineering, vol. 12, no. 2, pp. 110–125, 2021. [8] M. Singh, “AI-Based Question Generation and Evaluation System,” Int. J. Intelligent Systems, vol. 13, no. 3, pp. 140–155, 2021. [9] N. Verma, “Personalized Learning and Assessment Using AI,” Int. J. Advanced Education Systems, vol. 14, no. 2, pp. 200–215, 2022. [10] T. Joseph, “Integrated Examination System with Question Generation and Management Modules,” Int. J. Advanced Computing Systems, vol. 15, no. 1, pp. 85–100, 2023. [11] J. Brown, “Natural Language Processing for Automatic Question Generation in Educational Systems,” Int. J. Computational Linguistics, vol. 16, no. 2, pp. 120–135, 2022.

Copyright

Copyright © 2026 Jesilyn L, Kavipriya B, Nandhitha S K, Mr. S. Vinoth Kumar. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.