Automatic Exam Paper Generator

Abstract

This research presents an advanced AI-powered system designed to automate the generation of examination papers by leveraging PDF content extraction techniques, OpenAI’s large language models (LLMs), and the structured cognitive framework provided by Bloom’s Taxonomy. The system intelligently extracts and processes content from syllabus documents and previous examination papers in PDF format. Utilizing the analytical capabilities of LLMs, the extracted material is then transformed into high-quality, pedagogically sound questions mapped across various cognitive levels from knowledge recall to critical thinkingas defined by Bloom’s Taxonomy. The integration of artificial intelligence not only automates question generation but also streamlines the formatting and organization of the final exam paper, ensuring uniformity and alignment with curriculum standards. By reducing the manual workload involved in exam creation, this solution empowers educators to allocate more time toward meaningful instructional strategies and student engagement. Furthermore, the system promotes educational consistency, reduces human error, and enhances the overall efficiency of academic assessment planning.