Examining the potential and pitfalls of ChatGPT in science and engineering problem-solving
Frontiers in Education · 18.01.2024 · 8
DOI: 10.3389/feduc.2023.1330486 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Education, online erschienen am 18.01.2024. Verfasst von Karen D. Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 74-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The study explores the capabilities of OpenAI's ChatGPT in solving different types of physics problems. ChatGPT (with GPT-4) was queried to solve a total of 40 problems from a college-level engineering physics course. These problems ranged from well-specified problems, where all data required for solving the problem was provided, to under-specified, real-world problems where not all necessary data were given. Our findings show that ChatGPT could successfully solve 62.5% of the well-specified problems, but its accuracy drops to 8.3% for under-specified problems. Analysis of the model's incorrect solutions revealed three distinct failure modes: (1) failure to construct accurate models of the physical world, (2) failure to make reasonable assumptions about missing data, and (3) calculation errors. The study offers implications for how to leverage LLM-augmented instructional materials to enhance STEM education. The insights also contribute to the broader discourse on AI's strengths and limitations, serving both educators aiming to leverage the technology and researchers investigating human-AI collaboration frameworks for problem-solving and decision-making.
Zitieren
APA
Wang, K. D., Burkholder, E., Wieman, C., Salehi, S., & Haber, N. (2024). Examining the potential and pitfalls of ChatGPT in science and engineering problem-solving. Frontiers in Education, 8. https://doi.org/10.3389/feduc.2023.1330486
Vancouver
Wang KD, Burkholder E, Wieman C, Salehi S, Haber N. Examining the potential and pitfalls of ChatGPT in science and engineering problem-solving. Frontiers in Education. 2024;8. doi:10.3389/feduc.2023.1330486
BibTeX
@article{Wang2024,
author = {Wang, Karen D. and Burkholder, Eric and Wieman, Carl and Salehi, Shima and Haber, Nick},
title = {Examining the potential and pitfalls of ChatGPT in science and engineering problem-solving},
journal = {Frontiers in Education},
year = {2024},
volume = {8},
doi = {10.3389/feduc.2023.1330486}
}
EUVIMED