Pre-Training With Scientific Text Improves Educational Question Generation
This work addresses the need for scalable self-assessment in e-learning systems, though it appears incremental as it adapts existing methods to a specific domain.
The paper tackles the problem of generating educational questions for personalized learning by developing EduQG, a model adapted from a large language model, and shows that pre-training on scientific text leads to superior question generation.
With the boom of digital educational materials and scalable e-learning systems, the potential for realising AI-assisted personalised learning has skyrocketed. In this landscape, the automatic generation of educational questions will play a key role, enabling scalable self-assessment when a global population is manoeuvring their personalised learning journeys. We develop EduQG, a novel educational question generation model built by adapting a large language model. Our initial experiments demonstrate that EduQG can produce superior educational questions by pre-training on scientific text.