Saved in:
Bibliographic Details
Main Authors: Chen, Yixiang, Zhang, Xinyu, Wang, Jinran, Xie, Xurong, Yan, Nan, Chen, Hui, Wang, Lan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.10681
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910700849332224
author Chen, Yixiang
Zhang, Xinyu
Wang, Jinran
Xie, Xurong
Yan, Nan
Chen, Hui
Wang, Lan
author_facet Chen, Yixiang
Zhang, Xinyu
Wang, Jinran
Xie, Xurong
Yan, Nan
Chen, Hui
Wang, Lan
contents The Structured Dialogue System, referred to as SuDoSys, is an innovative Large Language Model (LLM)-based chatbot designed to provide psychological counseling. SuDoSys leverages the World Health Organization (WHO)'s Problem Management Plus (PM+) guidelines to deliver stage-aware multi-turn dialogues. Existing methods for employing an LLM in multi-turn psychological counseling typically involve direct fine-tuning using generated dialogues, often neglecting the dynamic stage shifts of counseling sessions. Unlike previous approaches, SuDoSys considers the different stages of counseling and stores essential information throughout the counseling process, ensuring coherent and directed conversations. The system employs an LLM, a stage-aware instruction generator, a response unpacker, a topic database, and a stage controller to maintain dialogue flow. In addition, we propose a novel technique that simulates counseling clients to interact with the evaluated system and evaluate its performance automatically. When assessed using both objective and subjective evaluations, SuDoSys demonstrates its effectiveness in generating logically coherent responses. The system's code and program scripts for evaluation are open-sourced.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10681
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Structured Dialogue System for Mental Health: An LLM Chatbot Leveraging the PM+ Guidelines
Chen, Yixiang
Zhang, Xinyu
Wang, Jinran
Xie, Xurong
Yan, Nan
Chen, Hui
Wang, Lan
Computation and Language
The Structured Dialogue System, referred to as SuDoSys, is an innovative Large Language Model (LLM)-based chatbot designed to provide psychological counseling. SuDoSys leverages the World Health Organization (WHO)'s Problem Management Plus (PM+) guidelines to deliver stage-aware multi-turn dialogues. Existing methods for employing an LLM in multi-turn psychological counseling typically involve direct fine-tuning using generated dialogues, often neglecting the dynamic stage shifts of counseling sessions. Unlike previous approaches, SuDoSys considers the different stages of counseling and stores essential information throughout the counseling process, ensuring coherent and directed conversations. The system employs an LLM, a stage-aware instruction generator, a response unpacker, a topic database, and a stage controller to maintain dialogue flow. In addition, we propose a novel technique that simulates counseling clients to interact with the evaluated system and evaluate its performance automatically. When assessed using both objective and subjective evaluations, SuDoSys demonstrates its effectiveness in generating logically coherent responses. The system's code and program scripts for evaluation are open-sourced.
title Structured Dialogue System for Mental Health: An LLM Chatbot Leveraging the PM+ Guidelines
topic Computation and Language
url https://arxiv.org/abs/2411.10681