Scalable Educational Question Generation with Pre-trained Language Models

The automatic generation of educational questions will play a key role in scaling online education, enabling self-assessment at scale when a global population is manoeuvring their personalised learning journeys. We develop $\mathit{\text{EduQG}}$, a novel educational question generation model built by adapting a large language model. Our extensive experiments demonstrate that $\mathit{\text{EduQG}}$ can produce superior educational questions by further pre-training and fine-tuning a pre-trained language model on the scientific text and science question data.