Conversational Topic Recommendation in Counseling and Psychotherapy with Decision Transformer and Large Language Models

TL;DR

This paper introduces a decision transformer-based approach for recommending conversation topics in mental health counseling, leveraging offline reinforcement learning and large language models to improve dialogue support systems.

Contribution

It presents a novel decision transformer architecture for topic recommendation and a method to fine-tune LLMs using model outputs as synthetic labels.

Findings

Decision transformer outperforms baseline RL methods.

Synthetic labels improve LLM fine-tuning for topic recommendation.

Implementation with LLaMA-2 7B shows mixed but promising results.

Abstract

Given the increasing demand for mental health assistance, artificial intelligence (AI), particularly large language models (LLMs), may be valuable for integration into automated clinical support systems. In this work, we leverage a decision transformer architecture for topic recommendation in counseling conversations between patients and mental health professionals. The architecture is utilized for offline reinforcement learning, and we extract states (dialogue turn embeddings), actions (conversation topics), and rewards (scores measuring the alignment between patient and therapist) from previous turns within a conversation to train a decision transformer model. We demonstrate an improvement over baseline reinforcement learning methods, and propose a novel system of utilizing our model's output as synthetic labels for fine-tuning a large language model for the same task. Although our implementation based on LLaMA-2 7B has mixed results, future work can undoubtedly build on the design.