Exam Paper Generation

Exam paper generation (EPG) leverages artificial intelligence to automate the creation of assessments, aiming to reduce instructor workload and improve efficiency. Current research focuses on using large language models (LLMs) and reinforcement learning to generate high-quality exams that meet specific criteria, such as difficulty level, skill coverage, and score distribution, often incorporating techniques like Item Response Theory (IRT) for question selection and evaluation. This automated approach has the potential to significantly streamline assessment creation across various educational settings and provide valuable insights into the performance of LLMs in complex reasoning tasks.