Assessing confidence in AI-assisted grading of physics exams through psychometrics: An exploratory study
Physical Review Physics Education Research · 07.04.2025 · 21 (1)
DOI: 10.1103/physrevphyseducres.21.010136 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physical Review Physics Education Research, online erschienen am 07.04.2025. Verfasst von Gerd Kortemeyer und 1 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 95 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study explores the use of artificial intelligence in grading high-stakes physics exams, emphasizing the application of psychometric methods, particularly item response theory, to evaluate the reliability of AI-assisted grading. We examine how grading rubrics can be iteratively refined and how threshold parameters can determine when AI-generated grades are reliable versus when human intervention is necessary. By adjusting thresholds for correctness measures and uncertainty, AI can grade with high precision, significantly reducing grading workloads while maintaining accuracy. Our findings show that AI can achieve a coefficient of determination of R 2 ≈ 0.91 when handling half of the grading load, and R 2 ≈ 0.96 for one-fifth of the load. These results demonstrate AI’s potential to assist in grading large-scale assessments, reducing both human effort and associated costs. However, the study underscores the importance of human oversight in cases of uncertainty or complex problem solving, ensuring the integrity of the grading process.
Zitieren
APA
Kortemeyer, G., & Nöhl, J. (2025). Assessing confidence in AI-assisted grading of physics exams through psychometrics: An exploratory study. Physical Review Physics Education Research, 21(1). https://doi.org/10.1103/physrevphyseducres.21.010136
Vancouver
Kortemeyer G, Nöhl J. Assessing confidence in AI-assisted grading of physics exams through psychometrics: An exploratory study. Physical Review Physics Education Research. 2025;21(1). doi:10.1103/physrevphyseducres.21.010136
BibTeX
@article{Kortemeyer2025,
author = {Kortemeyer, Gerd and Nöhl, Julian},
title = {Assessing confidence in AI-assisted grading of physics exams through psychometrics: An exploratory study},
journal = {Physical Review Physics Education Research},
year = {2025},
volume = {21},
number = {1},
doi = {10.1103/physrevphyseducres.21.010136}
}
EUVIMED