Domain-Specific Improvement on Psychotherapy Chatbot Using Assistant

TL;DR

This paper introduces domain-specific instructions and adaptation techniques to enhance large language models' performance in psychotherapy tasks, demonstrating significant improvements over existing models through evaluation.

Contribution

It proposes psychotherapy-specific assistant instructions and adapts fine-tuning and retrieval methods to improve LLMs in psychotherapy applications.

Findings

Pre-trained LLMs with psychotherapy instructions outperform state-of-the-art baselines.

The approach improves linguistic quality of responses in psychotherapy tasks.

The method effectively aligns LLMs with domain-specific knowledge.

Abstract

Large language models (LLMs) have demonstrated impressive generalization capabilities on specific tasks with human-written instruction data. However, the limited quantity, diversity, and professional expertise of such instruction data raise concerns about the performance of LLMs in psychotherapy tasks when provided with domain-specific instructions. To address this, we firstly propose Domain-Specific Assistant Instructions based on AlexanderStreet therapy, and secondly, we use an adaption fine-tuning method and retrieval augmented generation method to improve pre-trained LLMs. Through quantitative evaluation of linguistic quality using automatic and human evaluation, we observe that pre-trained LLMs on Psychotherapy Assistant Instructions outperform state-of-the-art LLMs response baselines. Our Assistant-Instruction approach offers a half-annotation method to align pre-trained LLMs with instructions and provide pre-trained LLMs with more psychotherapy knowledge.