Beyond Search Engines: Can Large Language Models Improve Curriculum Development?

TL;DR

This paper investigates whether large language models like GPT-4 can enhance curriculum development by generating accurate course topics, using a new dataset based on YouTube playlists across diverse subjects.

Contribution

The study introduces a novel framework and dataset for evaluating LLMs in curriculum topic generation, demonstrating GPT-4's superior performance over YouTube playlist extraction.

Findings

GPT-4 outperforms YouTube playlist topics in accuracy

The dataset covers over 100 courses and 7,000 playlists

LLMs show promise in dynamic curriculum development

Abstract

While Online Learning is growing and becoming widespread, the associated curricula often suffer from a lack of coverage and outdated content. In this regard, a key question is how to dynamically define the topics that must be covered to thoroughly learn a subject (e.g., a course). Large Language Models (LLMs) are considered candidates that can be used to address curriculum development challenges. Therefore, we developed a framework and a novel dataset, built on YouTube, to evaluate LLMs' performance when it comes to generating learning topics for specific courses. The experiment was conducted across over 100 courses and nearly 7,000 YouTube playlists in various subject areas. Our results indicate that GPT-4 can produce more accurate topics for the given courses than extracted topics from YouTube video playlists in terms of BERTScore