WundtGPT: Shaping Large Language Models To Be An Empathetic, Proactive Psychologist

Abstract

Large language models (LLMs) are raging over the medical domain, and their momentum has carried over into the mental health domain, leading to the emergence of few mental health LLMs. Although such mental health LLMs could provide reasonable suggestions for psychological counseling, how to develop an authentic and effective doctor-patient relationship (DPR) through LLMs is still an important problem. To fill this gap, we dissect DPR into two key attributes, i.e., the psychologist's empathy and proactive guidance. We thus present WundtGPT, an empathetic and proactive mental health large language model that is acquired by fine-tuning it with instruction and real conversation between psychologists and patients. It is designed to assist psychologists in diagnosis and help patients who are reluctant to communicate face-to-face understand their psychological conditions. Its uniqueness lies in that it could not only pose purposeful questions to guide patients in detailing their symptoms but also offer warm emotional reassurance. In particular, WundtGPT incorporates Collection of Questions, Chain of Psychodiagnosis, and Empathy Constraints into a comprehensive prompt for eliciting LLMs' questions and diagnoses. Additionally, WundtGPT proposes a reward model to promote alignment with empathetic mental health professionals, which encompasses two key factors: cognitive empathy and emotional empathy. We offer a comprehensive evaluation of our proposed model. Based on these outcomes, we further conduct the manual evaluation based on proactivity, effectiveness, professionalism and coherence. We notice that WundtGPT can offer professional and effective consultation. The model is available at huggingface.

Figures (7)

• Figure 1: The comparison between real doctor-patient psychological conversation and role-playing LLMs-patient conversation. Real doctor often poses purposeful questions while LLMs do not shown the ability of question.
• Figure 2: The overview of WundtGPT is acquired by fine-tuning it with instruction and real conversation between psychologists and patients. WundtGPT proposes a reward model to promote alignment with empathetic mental health professionals, which encompasses two key factors: cognitive empathy and emotional empathy.
• Figure 3: The prompt used for instructing multi-turn active and empathy conversations (Chinese version: Appendix \ref{['sec:b']})
• Figure 4: The comparison between different hyperparameters $\beta$. The conversation on the left is alignment fine-tuned by $\beta$ equals 0.1 while the conversation on the right is alignment fine-tuned by $\beta$ equals 1e-3. The Chinese version is shown in the Appendix \ref{['sec:b']}.
• Figure 5: The sampled generated responses from WUndtGPT with analysis. We can find that the WundtGPT can offer proactive consults, empathy, suggestion and diagnosis.