Skip to main content Skip to navigation

Elucidating STEM Concepts through Generative AI: A Multi-modal Exploration of Analogical Reasoning

Project Overview

The document explores the transformative role of generative AI, specifically large language models, in STEM education by employing a multimodal approach to enhance teaching and learning outcomes. It introduces an innovative system that translates complex STEM concepts into relatable metaphors and visual aids, thereby improving student comprehension and engagement. Through randomized testing, the study assesses learning gains and shifts in motivation, revealing that generative AI can substantially enhance the understanding of abstract STEM algorithms. The findings underscore the potential of generative AI to revolutionize educational practices in STEM disciplines, effectively addressing longstanding pedagogical challenges and fostering a more engaging learning environment for students.

Key Applications

AI-driven multimodal learning tool for generating analogies and visual storyboards.

Context: STEM education targeting students learning complex concepts in mathematics, physics, and programming.

Implementation: Developed a prototype using GPT-4 to generate analogies based on provided STEM concepts, which are then transformed into visual storyboards and animated videos.

Outcomes: Improved comprehension of complex STEM algorithms and enhanced learner engagement.

Challenges: Difficulty in generating comprehensive visual representations for complex concepts and ensuring effective transitions in animated visuals.

Implementation Barriers

Technical limitations

Technological tools for creating interactive content are often expensive or difficult to use.

Proposed Solutions: Developing user-friendly systems that can generate engaging content efficiently.

Resource constraints

Limited time and funding make lesson planning for complex topics challenging.

Proposed Solutions: Leveraging AI to ease the content generation process, thereby reducing the workload on educators.

Project Team

Chen Cao

Researcher

Zijian Ding

Researcher

Gyeong-Geon Lee

Researcher

Jiajun Jiao

Researcher

Jionghao Lin

Researcher

Xiaoming Zhai

Researcher

Contact Information

For information about the paper, please contact the authors.

Authors: Chen Cao, Zijian Ding, Gyeong-Geon Lee, Jiajun Jiao, Jionghao Lin, Xiaoming Zhai

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

Let us know you agree to cookies