Harnessing the Power of Prompt-based Techniques for Generating School-Level Questions Using LLMs

What is it about?

Crafting impactful educational questions presents a significant challenge. Our research pioneers a novel methodology, leveraging prompt-based techniques and advanced large language models (LLMs) to craft school-level questions that enhance comprehension and critical thinking. We meticulously curated the EduProbe dataset from school-level textbooks, enabling us to delve into the performance of various LLMs in comparison to human experts.

Featured Image

Photo by Kenny Eliason on Unsplash

Photo by Kenny Eliason on Unsplash

Why is it important?

The creation of high-quality questions is a fundamental task for educators seeking to foster deep understanding and critical thinking in students. However, the process of designing educational questions manually is often burdensome and time-consuming. Through this research effort, we aim to provide a valuable tool that empowers educators to create descriptive and reasoning-based questions more efficiently. By allowing teachers to allocate more time to classroom interactions and student participation, our proposed question-generation method has the potential to positively impact teaching practices and enhance learning outcomes. This work introduces EduProbe, a novel dataset encompassing school-level subjects such as History, Geography, Economics, Environmental Studies, and Science. Conducting a comprehensive comparative analysis, we explore prompt-based techniques alongside state-of-the-art large language models (LLMs) on EduProbe.

Perspectives