Assessing confidence in AI-assisted grading of physics exams through psychometrics: An exploratory study
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 t...
Saved in:
| Main Authors: | Gerd Kortemeyer, Julian Nöhl |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Physical Society
2025-04-01
|
| Series: | Physical Review Physics Education Research |
| Online Access: | http://doi.org/10.1103/PhysRevPhysEducRes.21.010136 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Multifaceted confidence in exploratory choice.
by: Oleg Solopchuk, et al.
Published: (2025-01-01) -
Comparison of AI-generated and clinician-designed multiple-choice questions in emergency medicine exam: a psychometric analysis
by: Murtaza Kaya, et al.
Published: (2025-07-01) -
Algebra and other relevant physics skills: The effectiveness of mastery practice on skills accuracy and exam grade in introductory physics
by: Qiaoyi Liu, et al.
Published: (2025-03-01) -
Co-assessment at the boundary: judges and advocates grading students’ performances in oral exams
by: Marte Søve Syverud, et al.
Published: (2025-03-01) -
Multilingual performance of a multimodal artificial intelligence system on multisubject physics concept inventories
by: Gerd Kortemeyer, et al.
Published: (2025-07-01)