Copyright © 2026 Authors retain the copyright of this article. This article 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.

@article{181283,
        author = {Dr.Rajesh Saturi and Gorige Anusha and C.Sony},
        title = {AI-Driven MCQ Generation Using NLP},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {4443-4447},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181283},
        abstract = {An AI-driven framework is proposed for automating the generation of Multiple-Choice Questions (MCQs) using Natural Language Processing (NLP), with the T5 model at its core. Traditional methods of MCQ creation are labor-intensive and depend heavily on subject-matter experts, limiting efficiency and scalability. This system addresses those limitations by leveraging transformer-based NLP models capable of processing educational materials in formats such as PDF, DOCX, and TXT. It generates context-aware questions and relevant distractors through modules focused on question generation, answer identification, and semantic similarity. The backend is implemented using FastAPI, while the user interface is built with React. Evaluation based on language quality, answer accuracy, and distractor relevance shows that the AI-generated MCQs closely match the quality of manually crafted ones, making the solution highly suitable for educational purposes.},
        keywords = {AI-driven MCQ generation, Natural Language Processing, T5 Model, Text-to-Text, NLP-based Question Generation},
        month = {June},
        }