Multiple-Choice Question Generation Using Large Language Models: Methodology and Educator Insights
This addresses the challenge for educators in efficiently creating assessment materials, though it is incremental as it applies existing LLMs to a specific educational task.
The paper tackled the problem of resource-intensive manual generation of multiple-choice questions (MCQs) by comparing three large language models (LLMs) for automated creation, finding that GPT-3.5 generated the most effective MCQs based on educator evaluations.
Integrating Artificial Intelligence (AI) in educational settings has brought new learning approaches, transforming the practices of both students and educators. Among the various technologies driving this transformation, Large Language Models (LLMs) have emerged as powerful tools for creating educational materials and question answering, but there are still space for new applications. Educators commonly use Multiple-Choice Questions (MCQs) to assess student knowledge, but manually generating these questions is resource-intensive and requires significant time and cognitive effort. In our opinion, LLMs offer a promising solution to these challenges. This paper presents a novel comparative analysis of three widely known LLMs - Llama 2, Mistral, and GPT-3.5 - to explore their potential for creating informative and challenging MCQs. In our approach, we do not rely on the knowledge of the LLM, but we inject the knowledge into the prompt to contrast the hallucinations, giving the educators control over the test's source text, too. Our experiment involving 21 educators shows that GPT-3.5 generates the most effective MCQs across several known metrics. Additionally, it shows that there is still some reluctance to adopt AI in the educational field. This study sheds light on the potential of LLMs to generate MCQs and improve the educational experience, providing valuable insights for the future.