Prototyping the use of Large Language Models (LLMs) for adult learning content creation at scale
Project Overview
The document explores the transformative role of generative AI, specifically Large Language Models (LLMs), in education, emphasizing their use in developing asynchronous course content aimed at adult learners for training and upskilling purposes. It highlights a human-in-the-loop approach that ensures the accuracy and clarity of the generated materials. Initial findings indicate that LLMs can greatly enhance the efficiency of content creation, significantly reducing the time required while upholding quality standards. This suggests that LLMs have the potential to fundamentally change educational practices by facilitating more rapid and effective learning resources tailored to the needs of adult learners. Overall, the integration of generative AI in educational settings could lead to a more dynamic and responsive learning environment, ultimately improving educational outcomes.
Key Applications
Creation of asynchronous course content using LLMs
Context: Adult learners in the renewable energy industry, specifically for training and upskilling
Implementation: Developed a course prototype using an OpenAI LLM with a human-in-the-loop process involving prompt engineering and expert reviews
Outcomes: Course content produced was nearly equivalent in accuracy and clarity to traditionally created content, with a significant reduction in development time (up to 25 times faster)
Challenges: Concerns about the accuracy and reliability of LLM-generated outputs, and the need for effective prompt engineering
Implementation Barriers
Accuracy and Reliability
Concerns about the accuracy and reliability of content generated by LLMs, along with limited availability of individuals who can provide subject matter expertise for creating high-quality content.
Proposed Solutions: Implementing a human-in-the-loop process with subject matter experts and using LLMs to expedite instructional design, decreasing reliance on subject matter experts.
Project Team
Daniel Leiker
Researcher
Sara Finnigan
Researcher
Ashley Ricker Gyllen
Researcher
Mutlu Cukurova
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: Daniel Leiker, Sara Finnigan, Ashley Ricker Gyllen, Mutlu Cukurova
Source Publication: View Original PaperLink opens in a new window
Project Contact: Dr. Jianhua Yang
LLM Model Version: gpt-4o-mini-2024-07-18
Analysis Provider: Openai