CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling

TL;DR

This paper introduces CPsyCoun, a framework that reconstructs and evaluates multi-turn Chinese psychological counseling dialogues using report data, addressing the lack of professional knowledge and automatic assessment methods.

Contribution

It presents a novel two-phase approach for dialogue reconstruction and a comprehensive benchmark for automatic evaluation in Chinese psychological counseling.

Findings

Effective dialogue reconstruction demonstrated by experimental results.

Benchmark facilitates automatic evaluation of multi-turn psychological consultations.

Open-source datasets and models support future research.

Abstract

Using large language models (LLMs) to assist psychological counseling is a significant but challenging task at present. Attempts have been made on improving empathetic conversations or acting as effective assistants in the treatment with LLMs. However, the existing datasets lack consulting knowledge, resulting in LLMs lacking professional consulting competence. Moreover, how to automatically evaluate multi-turn dialogues within the counseling process remains an understudied area. To bridge the gap, we propose CPsyCoun, a report-based multi-turn dialogue reconstruction and evaluation framework for Chinese psychological counseling. To fully exploit psychological counseling reports, a two-phase approach is devised to construct high-quality dialogues while a comprehensive evaluation benchmark is developed for the effective automatic evaluation of multi-turn psychological consultations. Competitive experimental results demonstrate the effectiveness of our proposed framework in psychological counseling. We open-source the datasets and model for future research at https://github.com/CAS-SIAT-XinHai/CPsyCoun