Saved in:
Bibliographic Details
Main Authors: Woollaston, Steve, Flanagan, Brendan, Toyokawa, Yuko, Ogata, Hiroaki
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2606.01592
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914621736091648
author Woollaston, Steve
Flanagan, Brendan
Toyokawa, Yuko
Ogata, Hiroaki
author_facet Woollaston, Steve
Flanagan, Brendan
Toyokawa, Yuko
Ogata, Hiroaki
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2606_01592
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Question Type, Cognitive Load, and CEFR Alignment: Evaluating LLM-Generated EFL Grammar Drill Exercises
Woollaston, Steve
Flanagan, Brendan
Toyokawa, Yuko
Ogata, Hiroaki
Computers and Society
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.
title Question Type, Cognitive Load, and CEFR Alignment: Evaluating LLM-Generated EFL Grammar Drill Exercises
topic Computers and Society
url https://arxiv.org/abs/2606.01592