Structured Dialogue System for Mental Health: An LLM Chatbot Leveraging the PM+ Guidelines
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 16 of its 18 references that are in the map. First posted on arXiv 16 Nov 2024.
Builds on
16 of 18 references.
References · 16
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
- 2023A Survey of Large Language Modelscited by 2,576
- 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
- 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,121
- 2023RRHF: Rank Responses to Align Language Models with Human Feedback without tearscited by 463
- 2023SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversationscited by 110
- 2023LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Modelscited by 101
- 2024CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counselingcited by 89
- 2023Building Emotional Support Chatbots in the Era of LLMscited by 62
- 2023SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health Supportcited by 46
4 more
- 2023ChatCounselor: A Large Language Models for Mental Health Supportcited by 44
- 2023Towards LLM-driven Dialogue State Trackingcited by 25
- 2024Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulationcited by 24
- 2023PsyChat: A Client-Centric Dialogue System for Mental Health Supportcited by 11
Built on by
Citing papers per year: 2025: 5; 2026: 1.
6 papers.
- 2025HamRaz: A Culture-Based Persian Conversation Dataset for Person-Centered Therapy Using LLM Agentscited by 6
- 2025Method-Based Reasoning for Large Language Models: Extraction, Reuse, and Continuous Improvementcited by 6
- 2025Position: Beyond Assistance -- Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Carecited by 3
- 2025EmoStage: A Framework for Accurate Empathetic Response Generation via Perspective-Taking and Phase Recognitioncited by 1
- 2025Are Today's LLMs Ready to Explain Well-Being Concepts?cited by 0
- 2026StageWell: A Process-Aligned Chinese Corpus for Positive-Psychology Support Dialoguecited by 0
- 2026StageWell: A Process-Aligned Chinese Corpus for Positive-Psychology Support Dialogue29 Aug 2026
- 2025Method-Based Reasoning for Large Language Models: Extraction, Reuse, and Continuous Improvement6 Aug 2025
- 2025Are Today's LLMs Ready to Explain Well-Being Concepts?6 Aug 2025
- 2025EmoStage: A Framework for Accurate Empathetic Response Generation via Perspective-Taking and Phase Recognition24 Jun 2025
- 2025Position: Beyond Assistance -- Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care21 Feb 2025
- 2025HamRaz: A Culture-Based Persian Conversation Dataset for Person-Centered Therapy Using LLM Agents9 Feb 2025