A comparative analysis of readability, quality, and reliability in large language model outputs pertaining to knee osteoarthritis queries
Erdem Maraşlı, Erkan Ozduran, Volkan Hancı · 2026
Read A comparative analysis of readability, quality, and reliability in large language model outputs pertaining to knee osteoarthritis queries by Erdem Maraşlı, Erkan Ozduran, Volkan Hancı (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-0353355.txt.
Description
Erdem Maraşlı, Erkan Ozduran, and Volkan Hancı published this 2026 study grading artificial intelligence chatbots on knee osteoarthritis, a worn-joint condition behind most arthritis disability. They posed common search terms as questions to three leading chatbots and scored the answers for readability, reliability against medical benchmarks, and overall quality.
The chatbots wrote at reading levels many patients would struggle with, and their reliability and quality scores raised real concerns about scientific soundness. The authors argue that medical chatbot answers need an effective oversight system before patients can safely trust them.
Catalog record
| CREATOR | Erdem Maraşlı, Erkan Ozduran, Volkan Hancı |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 56423 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |