Do You Understand How I Feel?: Towards Verified Empathy in Therapy Chatbots

TL;DR

This paper proposes a framework combining NLP and formal verification to develop therapy chatbots with verified empathy, ensuring they meet empathy requirements through model checking and strategy synthesis.

Contribution

It introduces a novel integration of Transformer-based dialogue analysis with formal models for verifying and guiding empathetic behavior in therapy chatbots.

Findings

Formal model accurately captures therapy session dynamics

Ad-hoc strategies increase empathy satisfaction probability

Framework enables systematic verification of empathy in chatbots

Abstract

Conversational agents are increasingly used as support tools along mental therapeutic pathways with significant societal impacts. In particular, empathy is a key non-functional requirement in therapeutic contexts, yet current chatbot development practices provide no systematic means to specify or verify it. This paper envisions a framework integrating natural language processing and formal verification to deliver empathetic therapy chatbots. A Transformer-based model extracts dialogue features, which are then translated into a Stochastic Hybrid Automaton model of dyadic therapy sessions. Empathy-related properties can then be verified through Statistical Model Checking, while strategy synthesis provides guidance for shaping agent behavior. Preliminary results show that the formal model captures therapy dynamics with good fidelity and that ad-hoc strategies improve the probability of satisfying empathy requirements.