mlsanityData to 14 Oct 2026

How Useful are Educational Questions Generated by Large Language Models?

arXiv 2304.06638 ↗First posted 13 Apr 2023cs.CL cs.AI cs.CYcited by 23

Not on the map. Why?

Abstract (arXiv)

Controllable text generation (CTG) by large language models has a huge potential to transform education for teachers and students alike. Specifically, high quality and diverse question generation can dramatically reduce the load on teachers and improve the quality of their educational content. Recent work in this domain has made progress with generation, but fails to show that real teachers judge the generated questions as sufficiently useful for the classroom setting; or if instead the questions have errors and/or pedagogically unhelpful content. We conduct a human evaluation with teachers to assess the quality and usefulness of outputs from combining CTG and question taxonomies (Bloom's and a difficulty taxonomy). The results demonstrate that the questions generated are high quality and sufficiently useful, showing their promise for widespread use in the classroom setting.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 4 of its 11 references that are in the map. First posted on arXiv 13 Apr 2023.

Builds on

4 of 11 references.

References · 4

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  3. 2022A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Modelscited by 129
  4. 2022Seed-Guided Topic Discovery with Out-of-Vocabulary Seedscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 11; 2025: 5; 2026: 4.

23 papers.

Sort:

By area:

  1. 2024Large Language Models in Cybersecurity: State-of-the-Artcited by 34
  2. 2023User Modeling in the Era of Large Language Models: Current Research and Future Directionscited by 18
  3. 2024ChIRAAG: ChatGPT Informed Rapid and Automated Assertion Generationcited by 16
  4. 2024ChatNVD: Advancing Cybersecurity Vulnerability Assessment with Large Language Modelscited by 11
  5. 2024Math Multiple Choice Question Generation via Human-Large Language Model Collaborationcited by 9
  6. 2025Large Language Models for Security Operations Centers: A Comprehensive Surveycited by 9
  7. 2024Contrastive Learning for Knowledge-Based Question Generation in Large Language Modelscited by 8
  8. 2025Multiple-Choice Question Generation Using Large Language Models: Methodology and Educator Insightscited by 8
  9. 2024Building a Domain-specific Guardrail Model in Productioncited by 6
  10. 2024FairMonitor: A Dual-framework for Detecting Stereotypes and Biases in Large Language Modelscited by 5
  11. 2024MathViz-E: A Case-study in Domain-Specialized Tool-Using Agentscited by 4
  12. 2023Scaling Evidence-based Instructional Design Expertise through Large Language Modelscited by 3
11 more
  1. 2024On Few-Shot Prompting for Controllable Question-Answer Generation in Narrative Comprehensioncited by 3
  2. 2024Comparison of Large Language Models for Generating Contextually Relevant Questionscited by 2
  3. 2026Small, Private Language Models as Teammates for Educational Assessment Designcited by 2
  4. 2024FairytaleQA Translated: Enabling Educational Question and Answer Generation in Less-Resourced Languagescited by 1
  5. 2025Enhancing the Learning Experience: Using Vision-Language Models to Generate Questions for Educational Videoscited by 1
  6. 2023Releasing the CRaQAn (Coreference Resolution in Question-Answering): An open-source dataset and dataset creation methodology using instruction-following modelscited by 0
  7. 2025Tell Me Who Your Students Are: GPT Can Generate Valid Multiple-Choice Questions When Students' (Mis)Understanding Is Hintedcited by 0
  8. 2025From Model to Classroom: Evaluating Generated MCQs for Portuguese with Narrative and Difficulty Concernscited by 0
  9. 2026ActuBench: A Multi-Agent LLM Pipeline for Generation and Evaluation of Actuarial Reasoning Taskscited by 0
  10. 2026Ask-E: An Environment for Calibrated Question Generationcited by 0
  11. 2026The Architect, the Adversary, and the Judge: Closed-Loop Generation of Standards-Aligned Assessment Items at Scalecited by 0