mlsanityData to 14 Oct 2026

Question Type, Cognitive Load, and CEFR Alignment: Evaluating LLM-Generated EFL Grammar Drill Exercises

arXiv 2606.01592 ↗First posted 1 Jun 2026cs.CY cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

This study evaluates the pedagogical viability of LLM-generated English as a Foreign Language (EFL) learning content. Utilising log data from Japanese junior high school students practicing on a grammar drilling application, we analysed how different question modalities impact student performance and whether theoretical localised CEFR difficulty tiers accurately predict empirical task difficulty. Results reveal a clear performance hierarchy: multiple-choice questions carried the lowest cognitive load, cloze tasks posed the greatest barrier to active recall, and drag-and-drop exercises incurred the heaviest time penalties. Furthermore, learner data validated the CEFR-J grammar framework, showing a steady decline in accuracy and increased response times as proficiency levels advanced. These findings demonstrate that LLMs can successfully generate learning content, while highlighting the need for developers to strategically sequence question modalities to transition learners from passive recognition to active linguistic production.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 1 of its 19 references that are in the map. First posted on arXiv 1 Jun 2026.

Builds on

1 of 19 references.

References · 1

  1. 2025An overview of artificial intelligence in computer-assisted language learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Alignment Drift in CEFR-prompted LLMs for Interactive Spanish Tutoring
  2. 2023NLPBench: Evaluating Large Language Models on Solving NLP Problems
  3. 2024Exploring the Capabilities of Prompted Large Language Models in Educational and Assessment Applications
  4. 2026Clause Encounters of the Third Kind: Can LLMs Replace Language Teachers?
  5. 2024The Future of Learning in the Age of Generative AI: Automated Question Generation and Assessment with Large Language Models
  6. 2024Why We Build Local Large Language Models: An Observational Analysis from 35 Japanese and Multilingual LLMs
  7. 2024Leveraging LLM Tutoring Systems for Non-Native English Speakers in Introductory CS Courses
  8. 2026From Memorization to Creation: Evaluating the Cognitive Depth of LLM-Generated Educational Questions