Evaluation of Five Large Language Models for Parental Education in Pediatric Anesthesia: Reliability and Readability Study
Fulin Pu, Jishuang Hong, Xiaoying Wei, Yanling Chen, Andrew Coristine · 2026
Read Evaluation of Five Large Language Models for Parental Education in Pediatric Anesthesia: Reliability and Readability Study by Fulin Pu, Jishuang Hong, Xiaoying Wei, Yanling Chen, Andrew Coristine (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/PMC13278617.txt.
Description
Fulin Pu leads a 2026 study rating five large language models as teachers for parents facing pediatric anesthesia, anesthesia care for children during surgery. Such models are popular but unvalidated for this high-risk topic. Experts drafted thirty-three common parental questions and put them to five named models in December 2025, then scored the answers blind for accuracy, reliability, and readability.
All five models scored above ninety percent on clinical accuracy, and one reached full marks in this sample. Still, unsafe content appeared in a small share of answers from three models, and invented content appeared in all but one. High average accuracy does not erase safety risk, the study shows, so clinical use needs care and checking.
Catalog record
| CREATOR | Fulin Pu, Jishuang Hong, Xiaoying Wei, Yanling Chen, Andrew Coristine |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60170 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |