Information quality, readability, and empathy of AI-generated public mental health information: a comparative evaluation of eight large language models
Qilong Wang, Siheng Ma, Jian Sun, Xin Qi, Jianpeng Zhao, Dongmei Ma, Xiaofei Liu, Qiang An, Dongrong Zhao, Songkai He · 2026
Read Information quality, readability, and empathy of AI-generated public mental health information: a comparative evaluation of eight large language models by Qilong Wang, Siheng Ma, Jian Sun, Xin Qi, Jianpeng Zhao, Dongmei Ma, Xiaofei Liu, Qiang An, Dongrong Zhao, Songkai He (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/PMC13350173.txt.
Description
Qilong Wang and colleagues compared eight large language model chatbots in 2026 on public mental health information. With mental illness burdens rising and professional help scarce, people increasingly ask chatbots, whose quality, clarity, and warmth in this sensitive area needed testing.
A bank of 48 questions from literature, search trends, and clinic consultations was put to each model. Scores covered information quality, source openness, reading level, and empathy as judged by psychiatrists and from a user's view. Two models led on quality, but none wrote at the recommended easy reading level, and models rarely volunteered their sources. The results urge caution and better design before chatbots advise on mental health.
Catalog record
| CREATOR | Qilong Wang, Siheng Ma, Jian Sun, Xin Qi, Jianpeng Zhao, Dongmei Ma, Xiaofei Liu, Qiang An, Dongrong Zhao, Songkai He |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 59081 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |