推进对话式心理治疗：将隐私、双记忆与领域专业知识同大语言模型相整合
Advancing Conversational Psychotherapy: Integrating Privacy, Dual-Memory, and Domain Expertise with Large Language Models
AI总结：
本文提出 SoulSpeak，借助 RAG 双记忆、隐私模块、咨询数据与提示技术实现个性化心理治疗对话，并用微调 BERT 评估模型验证其效果。
摘要：
心理健康已日益成为一个全球性问题，暴露出传统对话式心理治疗的局限：其受到地点、时间、费用和隐私顾虑的制约。为应对这些挑战，我们推出 SoulSpeak，这是一款由大语言模型（LLM）驱动的聊天机器人，旨在让心理治疗的获取更加普惠。SoulSpeak 对标准 LLM 聊天机器人的能力进行了改进，纳入了一种新颖的双记忆组件：该组件通过检索增强生成（RAG）结合短期与长期上下文，以提供个性化回复，同时借助专用隐私模块确保用户隐私与亲密感得到保护。此外，它利用一个包含治疗师与来访者互动的咨询聊天数据集以及多种提示技术，使生成的回复与心理治疗方法保持一致。我们引入两个经过微调的 BERT 模型，将该系统与现有 LLM 和人类治疗师进行评估：其中对话式心理治疗偏好模型（Conversational Psychotherapy Preference Model，CPPM）用于模拟人类对不同回复的偏好，另一个模型用于评估回复与用户输入的相关性。CPPM 可独立于 SoulSpeak 用于训练和评估聚焦心理治疗的语言模型，有助于缓解心理治疗领域资源有限的问题。此外，本文还检验了双记忆组件的有效性以及隐私模块的稳健性。研究结果凸显了通过提供一种将传统治疗的专业知识与 LLM 的优势相结合的替代方案来增强心理健康护理的潜力与挑战，为弥补当前心理健康服务在可及性和个性化方面的差距提供了一条有前景的路径。
英文摘要：
Mental health has increasingly become a global issue that reveals the limitations of traditional conversational psychotherapy, constrained by location, time, expense, and privacy concerns. In response to these challenges, we introduce SoulSpeak, a Large Language Model (LLM)-enabled chatbot designed to democratize access to psychotherapy. SoulSpeak improves upon the capabilities of standard LLM-enabled chatbots by incorporating a novel dual-memory component that combines short-term and long-term context via Retrieval Augmented Generation (RAG) to offer personalized responses while ensuring the preservation of user privacy and intimacy through a dedicated privacy module. In addition, it leverages a counseling chat dataset of therapist-client interactions and various prompting techniques to align the generated responses with psychotherapeutic methods. We introduce two fine-tuned BERT models to evaluate the system against existing LLMs and human therapists: the Conversational Psychotherapy Preference Model (CPPM) to simulate human preference among responses and another to assess response relevance to user input. CPPM is useful for training and evaluating psychotherapy-focused language models independent from SoulSpeak, helping with the constrained resources available for psychotherapy. Furthermore, the effectiveness of the dual-memory component and the robustness of the privacy module are also examined. Our findings highlight the potential and challenge of enhancing mental health care by offering an alternative that combines the expertise of traditional therapy with the advantages of LLMs, providing a promising way to address the accessibility and personalization gap in current mental health services.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
