Automated Safety Plan Scoring in Outpatient Mental Health Settings Using Large Language Models: Exploratory Study.

JMIR Ment Health · 2026 · PMC12782459 · PMID 41505705

Europe PMC DOI

hedged sentence

—

closest p

—

boldest claim

The sentences

partially significantno p-value reported

Our post hoc evaluation using the McNemar test revealed that performance differences between the LLMs (GPT-4, LLaMa 3, and o3-mini) were only partially significant.

also in 166 other papers

Quoted from the open-access full text in Europe PMC under the licence the publisher applied. The sentence is reproduced exactly as published; the emphasis is ours.