Comparing Chinese-language large language models for caregiver questions about developmental dysplasia of the hip

Fangyuan Wang, Xianhong Li, Yinghui Guan, Jiaqi Tian, Le Xu, Bing Huang, Jianhui Xie · 2026

Read Comparing Chinese-language large language models for caregiver questions about developmental dysplasia of the hip by Fangyuan Wang, Xianhong Li, Yinghui Guan, Jiaqi Tian, Le Xu, Bing Huang, Jianhui Xie (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-13582505.txt.

Description

Fangyuan Wang and co-authors compare two large language models on Chinese-language questions about a childhood hip condition, developmental dysplasia of the hip. Caregivers increasingly turn to such models for health advice, but reliability in pediatric orthopedics is unproven. The team poses 53 questions: 31 common caregiver questions and 22 drawn from guidelines. Each model answers once, in five sentences, under a standard prompt.

Six blinded pediatric orthopedic surgeons rate the answers for accuracy and agreement with Chinese guidance. DeepSeek-R1 scores clearly higher than ChatGPT-4o on both counts. Rater agreement is good for accuracy and moderate for guideline agreement. Readability measures give mixed results, with some favoring ChatGPT before adjustment. The authors caution that findings on surgery questions are exploratory. They frame the study as a check on how safe these tools are for caregiver education.

Catalog record

CREATORFangyuan Wang, Xianhong Li, Yinghui Guan, Jiaqi Tian, Le Xu, Bing Huang, Jianhui Xie
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE39 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13582505

Browse the full library · About the Tower of Babel