Assessing the accuracy and consistency of responses from Chat Generative Pre-trained Transformer in human papillomavirus infection and protection
Oguz Arslan, Burak Giray · 2026
Read Assessing the accuracy and consistency of responses from Chat Generative Pre-trained Transformer in human papillomavirus infection and protection by Oguz Arslan, Burak Giray (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/PMC13268229.txt.
Description
Oguz Arslan and Burak Giray present a 2026 study grading ChatGPT's answers about HPV. Patients increasingly ask chatbots about this common infection, which can cause cancers and is preventable by vaccine. The pair fed the chatbot 123 common questions drawn from recognized health organizations, grouped into basic knowledge, diagnosis, treatment, and prevention. Three independent reviewers scored each answer.
The chatbot gave comprehensive answers to about 94 percent of questions. Treatment questions scored perfectly, prevention about 94 percent, basic knowledge about 94 percent, and diagnosis about 88 percent. Answers were also consistent when repeated, for about 98 percent of questions. The authors judge the tool a useful information source for patients, as long as it supports rather than replaces professional care.
Catalog record
| CREATOR | Oguz Arslan, Burak Giray |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 27972 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |