Enhancing AI-Driven Psychological Consultation: Layered Prompts with Large Language Models
This work addresses the shortage of qualified professionals and scalability issues in mental health support, offering a potentially scalable solution, though it appears incremental in its prompt engineering approach.
The paper tackles the problem of limited accessibility in psychological consultation by developing a layered prompting system for large language models like GPT-4, resulting in significant improvements in response quality as validated on a new dataset of consultation dialogues.
Psychological consultation is essential for improving mental health and well-being, yet challenges such as the shortage of qualified professionals and scalability issues limit its accessibility. To address these challenges, we explore the use of large language models (LLMs) like GPT-4 to augment psychological consultation services. Our approach introduces a novel layered prompting system that dynamically adapts to user input, enabling comprehensive and relevant information gathering. We also develop empathy-driven and scenario-based prompts to enhance the LLM's emotional intelligence and contextual understanding in therapeutic settings. We validated our approach through experiments using a newly collected dataset of psychological consultation dialogues, demonstrating significant improvements in response quality. The results highlight the potential of our prompt engineering techniques to enhance AI-driven psychological consultation, offering a scalable and accessible solution to meet the growing demand for mental health support.