ChatCounselor: A Large Language Models for Mental Health Support

June M. Liu, Donghao Li, He Cao, Tianhe Ren, Zeyi Liao +1 more
9/27/2023
cs.CL

No official code found. Best implementation: EmoCareAI/ChatPsychiatrist (164 stars, Apache-2.0, last commit 2024-03-12).

Abstract

This paper presents ChatCounselor, a large language model (LLM) solution designed to provide mental health support. Unlike generic chatbots, ChatCounselor is distinguished by its foundation in real conversations between consulting clients and professional psychologists, enabling it to possess specialized knowledge and counseling skills in the field of psychology. The training dataset, Psych8k, was constructed from 260 in-depth interviews, each spanning an hour. To assess the quality of counseling responses, the counseling Bench was devised. Leveraging GPT-4 and meticulously crafted prompts based on seven metrics of psychological counseling assessment, the model underwent evaluation using a set of real-world counseling questions. Impressively, ChatCounselor surpasses existing open-source models in the counseling Bench and approaches the performance level of ChatGPT, showcasing the remarkable enhancement in model capability attained through high-quality domain-specific data.

View on arXivView PDF

Code Implementations(1)

Apache-2.0

An AI-chat bot transforming counseling with personalized support and expert assistance.

16433Shell, PythonApr 25, 20232 years agoApache-2.0

Similar Papers

Cite this paper

@article{liu2023chatcounselor,
  title  = {ChatCounselor: A Large Language Models for Mental Health Support},
  author = {June M. Liu and Donghao Li and He Cao and Tianhe Ren and Zeyi Liao and Jiamin Wu},
  year   = {2023},
  eprint = {2309.15461},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2309.15461v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.15461.svg)](https://codeofpaper.com/paper/2309.15461)

Discussion