AI text detection in dentistry: a comparative analysis across generative models
Jacopo Villa, Daniele Garcovich, Luca Lombardo, Giuseppe Siciliani, Milagros Adobes Martin · 2026
Read AI text detection in dentistry: a comparative analysis across generative models by Jacopo Villa, Daniele Garcovich, Luca Lombardo, Giuseppe Siciliani, Milagros Adobes Martin (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/pmc-13474814.txt.
Description
Villa and co-authors tested how well six popular detectors spot AI-written dentistry manuscripts in a 2026 benchmarking study for journal editors. They built a set of 120 full manuscripts: 30 each from GPT-4.5, GPT-4o, and DeepSeek-R2, plus 30 written by humans. Each detector scored every text from zero to 100 percent, and a score of 60 percent or more counted as a call of AI authorship.
Four detectors separated human and machine writing sharply, and none of them flagged any of the 30 human manuscripts as AI work at the chosen threshold. Turnitin performed only moderately, while DetectingAI failed to separate the groups at all in this test of full-length papers. Texts from DeepSeek-R2 were the easiest for every tool to catch, and the four leading detectors agreed with each other almost perfectly on their calls.
Catalog record
| CREATOR | Jacopo Villa, Daniele Garcovich, Luca Lombardo, Giuseppe Siciliani, Milagros Adobes Martin |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 37 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |