Testing standards for AI-based scores in automated essay scoring
Rudolf Debelak, Matthias Ziegler · 2026
Read Testing standards for AI-based scores in automated essay scoring by Rudolf Debelak, Matthias Ziegler (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0354680.txt.
Description
Rudolf Debelak and Matthias Ziegler published this 2026 methods paper on judging the quality of scores that artificial intelligence gives to essays. Classic test standards assume many small items, but an essay is one open response, so validity, fairness, and consistency need rethinking. The authors review current checks, propose new ones, and try them on a public essay data set.
Their trial model scored consistently and showed signs of real validity. Yet scores differed unfairly across essay topics when human and machine grading were compared. Debelak and Ziegler offer their framework as a shared toolkit for anyone grading by machine.
Catalog record
| CREATOR | Rudolf Debelak, Matthias Ziegler |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 91069 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |