LLMs generate diverse multilingual educational questions using new frameworks

Researchers have explored generating high-order questions for educational purposes using Large Language Models (LLMs) in a multilingual setting. The study introduced prompts based on Claim-Evidence-Reasoning and Divergent Questioning frameworks, moving beyond the traditional Bloom's Taxonomy and focusing on Basque, Spanish, and English. While both open-source and proprietary models showed effectiveness in generating questions across these languages, educators identified only about half of the generated questions as high-order. However, the alternative frameworks successfully produced structurally and conceptually diverse questions, indicating their potential to complement or serve as alternatives to Bloom's Taxonomy. AI

IMPACT This research could lead to more effective AI-powered educational tools capable of generating diverse, high-order questions across multiple languages.

RANK_REASON The cluster contains a research paper detailing a novel approach to question generation using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• arXiv
• Basque
• Bloom's taxonomy
• Claim-Evidence-Reasoning
• Divergent Questioning
• English
• Hugging Face
• Spanish

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →