Large Language Models Perform on Par with Experts Identifying Mental Health Factors in Adolescent Online Forums

arXiv:2404.16461v1 Announce Type: new
Abstract: Mental health in children and adolescents has been steadily deteriorating over the past few years [ 1 ]. The recent advent of Large Language Models (LLMs) offers much hope for cost and time efficient scaling of monitoring and intervention, yet despite specifically prevalent issues such as school bullying and eating disorders, previous studies on have not investigated performance in this domain or for open information extraction where the set of answers is not predetermined. We …

abstract arxiv children cost cs.cl experts health language language models large language large language models llms mental health monitoring scaling type