EUVIMEDEUVIMED entdecken
Crossref

Large language models-as-a-judge validity is strongly task-dependent across physics assessment formats

Will Yeadon, Tom Hardy, Paul Mackay, Elise Agra

Physical Review Physics Education Research · 17.11.2026

DOI: 10.1103/b5dd-p8v3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physical Review Physics Education Research, online erschienen am 17.11.2026. Verfasst von Will Yeadon und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Zitieren

APA

Yeadon, W., Hardy, T., Mackay, P., & Agra, E. (2026). Large language models-as-a-judge validity is strongly task-dependent across physics assessment formats. Physical Review Physics Education Research. https://doi.org/10.1103/b5dd-p8v3

Vancouver

Yeadon W, Hardy T, Mackay P, Agra E. Large language models-as-a-judge validity is strongly task-dependent across physics assessment formats. Physical Review Physics Education Research. 2026. doi:10.1103/b5dd-p8v3

BibTeX
@article{Yeadon2026,
  author = {Yeadon, Will and Hardy, Tom and Mackay, Paul and Agra, Elise},
  title = {Large language models-as-a-judge validity is strongly task-dependent across physics assessment formats},
  journal = {Physical Review Physics Education Research},
  year = {2026},
  doi = {10.1103/b5dd-p8v3}
}
Kostenlos starten →