mpathic Psychologist-led AI Clinical Tests Suicide Benchmark (mPACT-S-v1.0)

Abstract excerpt

<p>Large language models (LLMs) are increasingly used for emotional support and mental health guidance, including in conversations that may involve suicide-related risk. Existing evaluation approaches often rely on automated users or LLM-based judges and may not adequately capture clinically meaningful distinctions among detection, risk interpretation, and response generation. We developed the mpathic Psychologist...

Topics

Open a Topic to create a Post that cites this publication.

• Algorithms
• Data Mining
• Electronic Health Records
• International Classification of Diseases
• Natural Language Processing
• Phenotype
• Suicidal Ideation
• Suicide

Identifiers and source

Literature Corpus work

f71b6a12-da4e-5180-9a4b-8f9a4016d82f

DOI

10.31234/osf.io/3ep4v_v1