Elio AI Question Paper Generator Using Natural Language Processing

The rapid advancement of artificial intelligence and natural language processing (NLP) technologies has created new opportunities to automate academic assessment processes. This research presents Elio, an AI-powered question paper generator designed to automatically produce high-quality and contextually relevant examination questions from academic topics. The system integrates transformer-based language models, domain-specific fine-tuning, and a structured question generation pipeline to create diverse question types including conceptual, analytical, application-based, and critical-thinking questions. The architecture includes modules for input processing, NLP-based understanding, question diversification, and structured output formatting. Experimental evaluation demonstrates that the proposed system achieves a semantic relevance score of 91.4% and a human evaluator acceptance rate of 87.6%. Additionally, the system reduces the time required for question paper preparation by nearly 78% compared to traditional manual methods. The proposed approach contributes to the growing field of AI-assisted education by enabling scalable, automated, and intelligent examination content generation suitable for universities, research institutions, and online learning platforms.