Tag
Icahn School of Medicine at Mount Sinai researchers evaluate four open-weight audio-language models on verifying whether a targeted speaker (clinician or patient) was fully removed from 48 dyadic psychiatry recordings, finding that a disjunctive OR ensemble over fourteen model-view configurations achieves F1 of 0.478 driven by recall gains.
The American Psychiatric Association is updating the DSM to incorporate biological and neurobiological factors into psychiatric diagnoses, marking a significant modernization of diagnostic standards despite the current lack of reliable biomarkers.
Introduces Safe-Psych, a sequential benchmark for evaluating how large language models handle diagnostic uncertainty in psychiatry, revealing that even strong models often fail to abstain or seek clarification when clinical evidence is incomplete.