Saved in:
Bibliographic Details
Main Authors: Moein, Mohammad, Hajiagha, Mohammadreza Molavi, Faraji, Abdolali, Tavakoli, Mohammadreza, Kismihòk, Gàbor
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.07422
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910737512792064
author Moein, Mohammad
Hajiagha, Mohammadreza Molavi
Faraji, Abdolali
Tavakoli, Mohammadreza
Kismihòk, Gàbor
author_facet Moein, Mohammad
Hajiagha, Mohammadreza Molavi
Faraji, Abdolali
Tavakoli, Mohammadreza
Kismihòk, Gàbor
contents 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Online Learning is growing and becoming widespread, the associated curricula often suffer from a lack of coverage and outdated content.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
format Preprint
id arxiv_https___arxiv_org_abs_2412_07422
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond Search Engines: Can Large Language Models Improve Curriculum Development?
Moein, Mohammad
Hajiagha, Mohammadreza Molavi
Faraji, Abdolali
Tavakoli, Mohammadreza
Kismihòk, Gàbor
Computers and Society
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Online Learning is growing and becoming widespread, the associated curricula often suffer from a lack of coverage and outdated content.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
title Beyond Search Engines: Can Large Language Models Improve Curriculum Development?
topic Computers and Society
url https://arxiv.org/abs/2412.07422