Saved in:
Bibliographic Details
Main Authors: Lee, Yeonji, Park, Sangjun, Cho, Kyunghyun, Bak, JinYeong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.02736
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866907966586748928
author Lee, Yeonji
Park, Sangjun
Cho, Kyunghyun
Bak, JinYeong
author_facet Lee, Yeonji
Park, Sangjun
Cho, Kyunghyun
Bak, JinYeong
contents As mental health issues globally escalate, there is a tremendous need for advanced digital support systems. We introduce MentalAgora, a novel framework employing large language models enhanced by interaction between multiple agents for tailored mental health support. This framework operates through three stages: strategic debating, tailored counselor creation, and response generation, enabling the dynamic customization of responses based on individual user preferences and therapeutic needs. We conduct experiments utilizing a high-quality evaluation dataset TherapyTalk crafted with mental health professionals, shwoing that MentalAgora generates expert-aligned and user preference-enhanced responses. Our evaluations, including experiments and user studies, demonstrate that MentalAgora aligns with professional standards and effectively meets user preferences, setting a new benchmark for digital mental health interventions.
format Preprint
id arxiv_https___arxiv_org_abs_2407_02736
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MentalAgora: A Gateway to Advanced Personalized Care in Mental Health through Multi-Agent Debating and Attribute Control
Lee, Yeonji
Park, Sangjun
Cho, Kyunghyun
Bak, JinYeong
Computation and Language
As mental health issues globally escalate, there is a tremendous need for advanced digital support systems. We introduce MentalAgora, a novel framework employing large language models enhanced by interaction between multiple agents for tailored mental health support. This framework operates through three stages: strategic debating, tailored counselor creation, and response generation, enabling the dynamic customization of responses based on individual user preferences and therapeutic needs. We conduct experiments utilizing a high-quality evaluation dataset TherapyTalk crafted with mental health professionals, shwoing that MentalAgora generates expert-aligned and user preference-enhanced responses. Our evaluations, including experiments and user studies, demonstrate that MentalAgora aligns with professional standards and effectively meets user preferences, setting a new benchmark for digital mental health interventions.
title MentalAgora: A Gateway to Advanced Personalized Care in Mental Health through Multi-Agent Debating and Attribute Control
topic Computation and Language
url https://arxiv.org/abs/2407.02736