Benchmarking large language models against practicing clinicians on psychopathological assessment
✦ NabkaNews BriefAuto-summarized from multiple outlets · verify with the source
A study has been conducted to compare the performance of large language models with that of practicing clinicians in assessing psychopathology. The study utilized a multi-task benchmark and a non-parametric cognitive diagnostic modeling approach to evaluate the language models. The results of this fine-grained evaluation have been reported in a pair of studies published in Nature.