基于WHO指南的智能心理聊天机器人，能随咨询阶段自动调整对话策略。
Structured Dialogue System for Mental Health: An LLM Chatbot Leveraging the PM+ Guidelines
- 根据心理辅导不同阶段动态调整对话内容，保持连贯性。
- 在客观与主观评估中均表现逻辑清晰、响应合理。
- 适合心理健康应用开发人员和临床心理研究者参考。
本文提出一种名为SuDoSys的结构化对话系统，是一个基于大语言模型（LLM）的心理健康咨询聊天机器人。该系统遵循世界卫生组织（WHO）的PM+问题管理指南，能够识别并适应心理咨询的不同阶段，实现阶段感知的多轮对话。传统方法通常直接微调模型以生成对话，却忽视了咨询过程中的阶段变化。相比之下，SuDoSys通过阶段控制器、话题数据库、指令生成器和响应解析器，持续存储关键信息，确保对话的连贯性和方向性。此外，本文还提出一种新方法：利用模拟咨询者自动交互并评估系统性能。经客观与主观测试，系统展现出良好的逻辑一致性。相关代码与评估脚本已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。