Evaluating large language models for assessment of psychosis risk
Taiyu Zhu, Alexander Tashevski, Maxime Taquet, Matilda Azis, Tia Jani, Matthew R Broome, Thomas Kabir, Amedeo Minichino, Graham K Murray, Matthew M Nour, Ilina Singh, Paolo Fusar-Poli, Alejo Nevado-Holgado, Philip McGuire, Dominic Oliver · 2026
Read Evaluating large language models for assessment of psychosis risk by Taiyu Zhu, Alexander Tashevski, Maxime Taquet, Matilda Azis, Tia Jani, Matthew R Broome, Thomas Kabir, Amedeo Minichino, Graham K Murray, Matthew M Nour, Ilina Singh, Paolo Fusar-Poli, Alejo Nevado-Holgado, Philip McGuire, Dominic Oliver (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/PMC13396665.txt.
Description
Taiyu Zhu and co-authors tested whether large language models can help judge psychosis risk from interview transcripts, a job now limited to scarce specialists. Their 2026 study used interviews from the PSYCHS program, which follows young people at clinical high risk for psychosis.
Eleven open-weight models read 678 partial transcripts from 373 people, of whom 77.7 percent were in the high-risk group. Each model had to infer risk status and rate the severity and frequency of 15 symptom areas, and its answers were scored against researcher ratings. Bigger models performed better. A reliable version could widen screening where trained interviewers are few.
Catalog record
| CREATOR | Taiyu Zhu, Alexander Tashevski, Maxime Taquet, Matilda Azis, Tia Jani, Matthew R Broome, Thomas Kabir, Amedeo Minichino, Graham K Murray, Matthew M Nour, Ilina Singh, Paolo Fusar-Poli, Alejo Nevado-Holgado, Philip McGuire, Dominic Oliver |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 57665 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |