From accuracy to robustness: a comparative study of five advanced large language models on the Chinese dental licensing examination
Jiarui Zhang, Pascal Ubuzima, Gaoyang Huang, En-Hsuan Lee, Yuting Wang, Huifang Xu, Lei Xia, Tingting Wu · 2025
Read From accuracy to robustness: a comparative study of five advanced large language models on the Chinese dental licensing examination by Jiarui Zhang, Pascal Ubuzima, Gaoyang Huang, En-Hsuan Lee, Yuting Wang, Huifang Xu, Lei Xia, Tingting Wu (2025) 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-12750740.txt.
Description
Jiarui Zhang and seven co-authors test five leading AI chat models on a dental exam in a 2025 study. The exam is the Chinese Dental Licensing Examination, which dentists must pass to practice. The team wanted to know both how often the models answer well and how steady they stay when questions are twisted.
Each model faced 600 questions taken from the official review book, all in Chinese. Their answers were checked against the official keys, subject by subject. The team then retested 120 questions with planted traps to see if scores held up. Results show where the models are strong and where they slip. The work helps teachers judge how much trust these tools deserve in dental training.
Catalog record
| CREATOR | Jiarui Zhang, Pascal Ubuzima, Gaoyang Huang, En-Hsuan Lee, Yuting Wang, Huifang Xu, Lei Xia, Tingting Wu |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 35 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |