An Automated MCQ Generator using NLP

The automation of multiple-choice question (MCQ) generation has emerged as a crucial advancement in educational assessment, aiming to reduce the time, effort, and domain expertise required for manual question creation. This research introduces a Natural Language Processing (NLP)-based system that generates high-quality, contextually relevant MCQs from textual content. The system accepts diverse input formats, including plain text and PDF documents, and utilizes advanced transformer models such as T5 (Text-to-Text Transfer Transformer), Flan-T5(Fine-tuned Language Net T5), and DistilBERT (Distilled Bidirectional Encoder Representations from Transformers) for keyword extraction, question formulation, and distractor generation. A web-based interface, developed using Django, enables users to customize parameters like question quantity and model selection, ensuring flexibility across educational domains. Evaluation using BLEU (Bilingual Evaluation Understudy) and ROUGE (Recall-Oriented Understudy for Gisting Evaluation) metrics confirms that fine-tuned models outperform their base counterparts in coherence and relevance. Additionally, the use of efficient fine-tuning techniques like LoRA (Low-Rank Adaptation) and QLoRA (Quantized Low-Rank Adaptation) significantly reduces computational overhead without degrading performance. The proposed system demonstrates strong potential to streamline formative assessment and enhance learning feedback loops, while future work will focus on mobile deployment and integration with digital learning platforms to expand accessibility.