The Emotional Spectrum of LLMs: Leveraging Empathy and Emotion-Based Markers for Mental Health Support

TL;DR

This paper introduces RACLETTE, an empathetic conversational AI system that builds emotional profiles for users, aiding mental health assessment and support through explainable emotional markers and improved emotional understanding.

Contribution

The work presents a novel conversational system with superior emotional accuracy and a method to use emotional profiles as interpretable markers for mental health screening.

Findings

RACLETTE outperforms benchmarks in emotional understanding and empathetic response generation.

Emotional profiles can be used for preliminary mental health screening.

The system offers explainable emotional markers for mental health assessment.

Abstract

The increasing demand for mental health services has highlighted the need for innovative solutions, particularly in the realm of psychological conversational AI, where the availability of sensitive data is scarce. In this work, we explored the development of a system tailored for mental health support with a novel approach to psychological assessment based on explainable emotional profiles in combination with empathetic conversational models, offering a promising tool for augmenting traditional care, particularly where immediate expertise is unavailable. Our work can be divided into two main parts, intrinsecaly connected to each other. First, we present RACLETTE, a conversational system that demonstrates superior emotional accuracy compared to state-of-the-art benchmarks in both understanding users' emotional states and generating empathetic responses during conversations, while progressively building an emotional profile of the user through their interactions. Second, we show how the emotional profiles of a user can be used as interpretable markers for mental health assessment. These profiles can be compared with characteristic emotional patterns associated with different mental disorders, providing a novel approach to preliminary screening and support.