Toward Real-World Chinese Psychological Support Dialogues: CPsDD Dataset and a Co-Evolving Multi-Agent System

TL;DR

This paper introduces the CPsDD dataset and a multi-agent system for Chinese psychological support dialogues, leveraging limited data and expert knowledge to improve empathetic response generation and support strategies.

Contribution

It presents a novel framework combining data augmentation, expert knowledge, and multi-agent dialogue systems for Chinese psychological support, along with the new CPsDD dataset.

Findings

CADSS achieves state-of-the-art performance on support tasks

The dataset contains 68K dialogues across multiple psychological categories

The system effectively models empathetic and strategic responses

Abstract

The growing need for psychological support due to increasing pressures has exposed the scarcity of relevant datasets, particularly in non-English languages. To address this, we propose a framework that leverages limited real-world data and expert knowledge to fine-tune two large language models: Dialog Generator and Dialog Modifier. The Generator creates large-scale psychological counseling dialogues based on predefined paths, which guide system response strategies and user interactions, forming the basis for effective support. The Modifier refines these dialogues to align with real-world data quality. Through both automated and manual review, we construct the Chinese Psychological support Dialogue Dataset (CPsDD), containing 68K dialogues across 13 groups, 16 psychological problems, 13 causes, and 12 support focuses. Additionally, we introduce the Comprehensive Agent Dialogue Support System (CADSS), where a Profiler analyzes user characteristics, a Summarizer condenses dialogue history, a Planner selects strategies, and a Supporter generates empathetic responses. The experimental results of the Strategy Prediction and Emotional Support Conversation (ESC) tasks demonstrate that CADSS achieves state-of-the-art performance on both CPsDD and ESConv datasets.