Large Language Models in German Continuing Medical Education Assessments: Protocol for a Fully Crossed Experimental Study
Leyla Özmen, Christian Burisch, Daniel Gödde, Frank Breuckmann, Jan Ehlers, Timur Sellmann, Javad Sarvestan · 2026
Read Large Language Models in German Continuing Medical Education Assessments: Protocol for a Fully Crossed Experimental Study by Leyla Özmen, Christian Burisch, Daniel Gödde, Frank Breuckmann, Jan Ehlers, Timur Sellmann, Javad Sarvestan (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/PMC13411715.txt.
Description
Leyla Özmen and colleagues set out in 2026 an experiment on whether file format can stop chatbots from cheating on German doctors' continuing education tests. Passing those tests is a legal and ethical duty for physicians, yet language models already clear them. Blocking easy text extraction might restore some integrity.
Eighteen expired course articles from three publishers and six specialties will be converted into three hardened PDF formats plus the original. Four current models will each answer every article three times per format, giving sixteen model-format pairings. Scores will be compared against each module's pass bar, usually seventy percent. Ethics approval and preregistration are in place, with data collection planned for mid-2026.
Catalog record
| CREATOR | Leyla Özmen, Christian Burisch, Daniel Gödde, Frank Breuckmann, Jan Ehlers, Timur Sellmann, Javad Sarvestan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |