Scalable Educational Question Generation with Pre-trained Language Models

Sahan Bulathwela, Hamze Muse, Emine Yilmaz
5/13/2023
cs.AIcs.CYcs.IR

No official code found. Best implementation: hmuus01/Educational_QG (8 stars, last commit 2022-10-06).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

hmuus01/Educational_QGCommunity100%
81CSS, HTMLOct 6, 20224 years ago

Similar Papers

Automated Educational Question Generation at Different Bloom's Skill Levels using Large Language Models: Strategies and Evaluation

88% match1 repo82024

A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education

88% match2025

How Useful are Educational Questions Generated by Large Language Models?

87% match2023

Leveraging Large Language Models to Generate Course-specific Semantically Annotated Learning Objects

85% match2024

How Teachers Can Use Large Language Models and Bloom's Taxonomy to Create Educational Quizzes

85% match2024

The Future of Learning in the Age of Generative AI: Automated Question Generation and Assessment with Large Language Models

85% match2024

Cite this paper

@article{bulathwela2023scalable,
  title  = {Scalable Educational Question Generation with Pre-trained Language Models},
  author = {Sahan Bulathwela and Hamze Muse and Emine Yilmaz},
  year   = {2023},
  eprint = {2305.07871},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.07871v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.07871.svg)](https://codeofpaper.com/paper/2305.07871)

Discussion