Benchmarking Generative Artificial Intelligence Against Human Judgment in Eating Disorder Case Recognition and Treatment Recommendations
Jake Linardon, Mariel Messer · 2026
Read Benchmarking Generative Artificial Intelligence Against Human Judgment in Eating Disorder Case Recognition and Treatment Recommendations by Jake Linardon, Mariel Messer (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-13536227.txt.
Description
Jake Linardon and Mariel Messer tested a chatbot against human judgment on eating disorders in a 2026 study. People increasingly ask generative AI about eating problems, so the quality of its answers matters. The team gave a current chatbot two case stories and standard questions about diagnosis and care.
One story showed a restrictive eating disorder at three body weights; the other showed binge-eating disorder. Each prompt was run twenty times and scored against published clinician and community answers. The chatbot flagged an eating disorder in nearly every run, including at higher weight, where clinicians often missed it. It also recommended specialist treatment every time, far more often than clinicians did. On the binge-eating case it named the disorder in every run. The authors say the tool's case recognition looked strong here, while noting that recognition is only one part of safe care.
Catalog record
| CREATOR | Jake Linardon, Mariel Messer |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 27 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |