{
  "id": 3314,
  "url": "https://arxiv.org/abs/2606.01592v2",
  "title": "Question Type, Cognitive Load, and CEFR Alignment: Evaluating LLM-Generated EFL Grammar Drill Exercises",
  "summary": "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",
  "authors": "Steve Woollaston, Brendan Flanagan, Yuko Toyokawa, Hiroaki Ogata",
  "category": "research",
  "topics": "safety-alignment,children-education",
  "orgs": null,
  "regions": "japan",
  "published_at": "2026-06-01T02:42:33.000Z",
  "fetched_at": "2026-07-14T16:30:09.961Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3314",
  "original_url": "https://arxiv.org/abs/2606.01592v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}