Dynamic Strategy Chain: Dynamic Zero-Shot CoT for Long Mental Health Support Generation

TL;DR

This paper introduces a zero-shot Dynamic Strategy Chain prompting method that enhances long mental health support text generation by tailoring responses with personalized counseling strategies, outperforming traditional CoT prompting.

Contribution

The paper proposes a novel zero-shot DSC prompting approach that dynamically generates personalized mental health strategies to improve LLM responses in counseling tasks.

Findings

Zero-shot DSC prompting produces more human-like responses.

It outperforms CoT prompting in automatic and manual evaluations.

The method effectively tailors responses to individual help-seekers.

Abstract

Long counseling Text Generation for Mental health support (LTGM), an innovative and challenging task, aims to provide help-seekers with mental health support through a comprehensive and more acceptable response. The combination of chain-of-thought (CoT) prompting and Large Language Models (LLMs) is employed and get the SOTA performance on various NLP tasks, especially on text generation tasks. Zero-shot CoT prompting is one of the most common methods in CoT prompting. However, in the LTGM task, Zero-shot CoT prompting can not simulate a counselor or provide personalized strategies without effective mental health counseling strategy prompts. To tackle this challenge, we propose a zero-shot Dynamic Strategy Chain (DSC) prompting method. Firstly, we utilize GPT2 to learn the responses written by mental health counselors and dynamically generate mental health counseling strategies tailored to the help-seekers' needs. Secondly, the Zero-shot DSC prompting is constructed according to mental health counseling strategies and the help-seekers' post. Finally, the Zero-shot DSC prompting is employed to guide LLMs in generating more human-like responses for the help-seekers. Both automatic and manual evaluations demonstrate that Zero-shot DSC prompting can deliver more human-like responses than CoT prompting methods on LTGM tasks.