AI & NLP-Based Question Generation Using the T5 Model for Education

Abstract

With the increasing demand for efficient and scalable educational assessments, Artificial Intelligence (AI) and Natural Language Processing (NLP) have emerged as transformative tools. Automated Question Generation (AQG) is a key application that leverages AI to generate relevant and diverse questions from textual content. This study explores the implementation of AQG using the Text-To-Text Transfer Transformer (T5) model, a state-of-the-art deep learning model for NLP tasks. The proposed system is fine-tuned on educational datasets to enhance question fluency, relevance, and accuracy. Unlike traditional rule-based approaches, the T5 model can dynamically generate factual, inferential, and multiple-choice questions across various subjects. This research aims to improve assessment quality, reduce the manual workload of educators, and support adaptive learning environments. The findings highlight the model’s potential in creating high-quality questions while addressing challenges such as contextual accuracy, grammatical correctness, and bias mitigation. Future work will focus on refining question quality, integrating AQG into intelligent tutoring systems, and enhancing contextual understanding.