MADP: Multi-Agent Deductive Planning for Enhanced Cognitive-Behavioral Mental Health Question Answer

TL;DR

The paper introduces MADP, a multi-agent deductive planning framework that models interactions among CBT elements to improve mental health question answering, resulting in a specialized LLM with better understanding and personalized responses.

Contribution

It proposes a novel multi-agent framework for MHQA that captures CBT element interactions, and constructs a new dataset to fine-tune LLMs for enhanced mental health support.

Findings

MADP outperforms baseline models in evaluations

MADP-LLM provides more personalized and context-aware responses

Extensive experiments validate the effectiveness of the proposed framework

Abstract

The Mental Health Question Answer (MHQA) task requires the seeker and supporter to complete the support process in one-turn dialogue. Given the richness of help-seeker posts, supporters must thoroughly understand the content and provide logical, comprehensive, and well-structured responses. Previous works in MHQA mostly focus on single-agent approaches based on the cognitive element of Cognitive Behavioral Therapy (CBT), but they overlook the interactions among various CBT elements, such as emotion and cognition. This limitation hinders the models' ability to thoroughly understand the distress of help-seekers. To address this, we propose a framework named Multi-Agent Deductive Planning (MADP), which is based on the interactions between the various psychological elements of CBT. This method guides Large Language Models (LLMs) to achieve a deeper understanding of the seeker's context and provide more personalized assistance based on individual circumstances. Furthermore, we construct a new dataset based on the MADP framework and use it to fine-tune LLMs, resulting in a specialized model named MADP-LLM. We conduct extensive experiments, including comparisons with multiple LLMs, human evaluations, and automatic evaluations, to validate the effectiveness of the MADP framework and MADP-LLM.