Date
Publisher
arXiv
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
\textit{EduQG}, a novel educational question generation model built by adapting
a large language model. Our extensive experiments demonstrate that
\textit{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.
Study at a glance
- Question: Can artificial intelligence be adapted to automatically generate educational science questions?
- Setting and data: Scientific text and science question data.
- Method: Model development and computational experiments.
Why it matters
The automatic generation of educational questions will play a key role in scaling online education. It enables self-assessment at scale as a global population navigates personalized learning journeys.
Key findings
- In online science education, an adapted AI model called EduQG produced superior educational questions.
- Specializing an AI model on science reading materials and questions improved its ability to create educational questions.
- Automated question generation enables students worldwide to conduct self-assessments at scale during personalized online learning.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who age?
Why use AI?
Study design
