# Scalable Educational Question Generation with Pre-trained Language Models

arXiv: https://arxiv.org/abs/2305.07871 · HTML: https://mlsanity.com/paper/2305.07871/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 13 May 2023.

## Builds on (most cited first, 14 of 14)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Crowdsourcing Multiple Choice Science Questions](https://mlsanity.com/paper/1707.06209/) (2017)
- [Learning to Ask: Neural Question Generation for Reading Comprehension](https://mlsanity.com/paper/1705.00106/) (2017)
- [BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation](https://mlsanity.com/paper/2109.04588/) (2021)
- [Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation](https://mlsanity.com/paper/1805.11004/) (2018)
- [TrueLearn: A Family of Bayesian Algorithms to Match Lifelong Learners to Open Educational Resources](https://mlsanity.com/paper/1911.09471/) (2019)
- [Simplifying Paragraph-level Question Generation via Transformer Language Models](https://mlsanity.com/paper/2005.01107/) (2020)
- [Leaf: Multiple-Choice Question Generation](https://mlsanity.com/paper/2201.09012/) (2022)
- [Could AI Democratise Education? Socio-Technical Imaginaries of an EdTech Revolution](https://mlsanity.com/paper/2112.02034/) (2021)
- [A Question Type Driven and Copy Loss Enhanced Frameworkfor Answer-Agnostic Neural Question Generation](https://mlsanity.com/paper/2005.11665/) (2020)
- [Semantic TrueLearn: Using Semantic Knowledge Graphs in Recommendation Systems](https://mlsanity.com/paper/2112.04368/) (2021)
- [Pre-Training With Scientific Text Improves Educational Question Generation](https://mlsanity.com/paper/2212.03869/) (2022)

## Built on by (most cited first, 19 of 19)

- [Automated Educational Question Generation at Different Bloom's Skill Levels using Large Language Models: Strategies and Evaluation](https://mlsanity.com/paper/2408.04394/) (2024)
- [Can We Trust AI-Generated Educational Content? Comparative Analysis of Human and AI-Generated Learning Resources](https://mlsanity.com/paper/2306.10509/) (2023)
- [An Automatic Question Usability Evaluation Toolkit](https://mlsanity.com/paper/2405.20529/) (2024)
- [Building a Domain-specific Guardrail Model in Production](https://mlsanity.com/paper/2408.01452/) (2024)
- [Large Language Models Meet User Interfaces: The Case of Provisioning Feedback](https://mlsanity.com/paper/2404.11072/) (2024)
- [MathViz-E: A Case-study in Domain-Specialized Tool-Using Agents](https://mlsanity.com/paper/2407.17544/) (2024)
- [Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trends](https://mlsanity.com/paper/2401.07518/) (2024)
- [GPT-Powered Elicitation Interview Script Generator for Requirements Engineering Training](https://mlsanity.com/paper/2406.11439/) (2024)
- [TrueReason: An Exemplar Personalised Learning System Integrating Reasoning with Foundational Models](https://mlsanity.com/paper/2502.10411/) (2025)
- [Rethinking the Potential of Multimodality in Collaborative Problem Solving Diagnosis with Large Language Models](https://mlsanity.com/paper/2504.15093/) (2025)
- [Enhancing Diversity of LLM-Generated Educational Tasks](https://mlsanity.com/paper/2512.23601/) (2025)
- [Cognitively Diverse Multiple-Choice Question Generation: A Hybrid Multi-Agent Framework with Large Language Models](https://mlsanity.com/paper/2602.03704/) (2026)
- [Small, Private Language Models as Teammates for Educational Assessment Design](https://mlsanity.com/paper/2605.15015/) (2026)
- [Catching The Correct Answer Trap: Characterising AI Tutor Blind Spots When Analysing Student Reasoning](https://mlsanity.com/paper/2605.23925/) (2026)
- [Multi-dimensional data refining strategy for effective fine-tuning LLMs](https://mlsanity.com/paper/2311.01049/) (2023)
- [Tell Me Who Your Students Are: GPT Can Generate Valid Multiple-Choice Questions When Students' (Mis)Understanding Is Hinted](https://mlsanity.com/paper/2505.05815/) (2025)
- [Harnessing IoT and Generative AI for Weather-Adaptive Learning in Climate Resilience Education](https://mlsanity.com/paper/2508.21666/) (2025)
- [Mix and Match: Context Pairing for Scalable Topic-Controlled Educational Summarisation](https://mlsanity.com/paper/2604.18087/) (2026)
- [KT4EQG: Personalized Exercise Question Generation via Knowledge Tracing](https://mlsanity.com/paper/2605.23933/) (2026)

## Abstract (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 textitEduQG, a novel educational question generation model built by adapting a large language model. Our extensive experiments demonstrate that textitEduQG 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.