Multilingual Performance of a Multimodal Artificial Intelligence System on Multisubject Physics Concept Inventories

TL;DR

This study evaluates GPT-4o's multilingual multimodal capabilities on physics concept inventories, revealing strengths in language and subject variation, but weaknesses in laboratory skills and visual interpretation, with implications for education.

Contribution

It is the first to assess GPT-4o's performance on physics inventories across multiple languages and modalities, highlighting its potential and limitations in physics education.

Findings

GPT-4o outperforms undergraduate students in most physics subjects.

Performance varies across languages, with European languages performing better.

Laboratory skills are the weakest area for GPT-4o.

Abstract

We investigate the multilingual and multimodal performance of a large language model-based artificial intelligence (AI) system, GPT-4o, using a diverse set of physics concept inventories spanning multiple languages and subject categories. The inventories, sourced from the PhysPort website, cover classical physics topics such as mechanics, electromagnetism, optics, and thermodynamics, as well as relativity, quantum mechanics, astronomy, mathematics, and laboratory skills. Unlike previous text-only studies, we uploaded the inventories as images to reflect what a student would see on paper, thereby assessing the system's multimodal functionality. Our results indicate variation in performance across subjects, with laboratory skills standing out as the weakest. We also observe differences across languages, with English and European languages showing the strongest performance. Notably, the relative difficulty of an inventory item is largely independent of the language of the survey. When comparing AI results to existing literature on student performance, we find that the AI system outperforms average post-instruction undergraduate students in all subject categories except laboratory skills. Furthermore, the AI performs worse on items requiring visual interpretation of images than on those that are purely text-based. While our exploratory findings show GPT-4o's potential usefulness in physics education, they highlight the critical need for instructors to foster students' ability to critically evaluate AI outputs, adapt curricula thoughtfully in response to AI advancements, and address equity concerns associated with AI integration.