Do You Understand How I Feel?: Towards Verified Empathy in Therapy Chatbots
This addresses the need for systematic empathy verification in mental health chatbots, which is an incremental step in improving therapeutic support tools.
The paper tackles the problem of ensuring empathy in therapy chatbots by proposing a framework that combines natural language processing and formal verification, with preliminary results showing the model captures therapy dynamics well and strategies improve empathy satisfaction probabilities.
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.