High-Order Question Generation in a Multilingual Educational Context

2026-07-15

AI Summary

This study addresses the persistent challenge educators face in designing effective higher-order questions, a task further complicated by the predominant reliance on Bloom’s Taxonomy and English-language contexts in existing research. For the first time, this work introduces two non-Bloom frameworks—Claim-Evidence-Reasoning (CER) and Divergent Questioning—into multilingual educational settings. By integrating both open- and closed-source large language models with multilingual prompt engineering, the approach automatically generates higher-order questions exhibiting structural and conceptual diversity across Basque, Spanish, and English. Experimental results demonstrate that the models consistently produce answerable questions in all three languages, with approximately half rated by teachers as genuinely higher-order, thereby validating the feasibility of these alternative frameworks and their complementary value for enhancing pedagogical questioning practices.

Abstract

Critical thinking is a fundamental skill that helps learners move beyond simple memorization. One way to develop this skill is through high-order questioning. However, crafting such questions remains a challenge for educators, and classroom practices tend to rely on low-order questions. Large Language Models have demonstrated strong capabilities in generating high-order questions, especially when guided by prompts based on Bloom's Taxonomy. Yet, existing research has largely centered on this framework and focused only on English. This study addresses these gaps by introducing prompts grounded in two alternative frameworks: Claim-Evidence-Reasoning and Divergent Questioning within a multilingual context using Basque, Spanish, and English. Results indicate that while both an open-source and a proprietary model rather effectively generate questions in all three languages, only about half of the answerable questions are recognized by teachers as high-order. A positive finding is that the alternative frameworks produce structurally and conceptually varied questions, suggesting they could complement each other and provide viable alternatives to Bloom's Taxonomy.

Problem

• high-order question generation
• multilingual education
• critical thinking
• Bloom's Taxonomy
• questioning frameworks

Innovation

• high-order question generation
• multilingual education
• Claim-Evidence-Reasoning
• Divergent Questioning
• Large Language Models