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

2026-01-13

AI Summary

This work addresses the lack of systematic modeling and verification mechanisms for empathy in existing psychotherapeutic chatbots. It proposes the first verifiable empathetic dialogue framework that integrates natural language processing with formal verification: leveraging a Transformer-based architecture to extract dialogue features, it constructs a stochastic hybrid automaton to formally characterize empathetic properties. For the first time, statistical model checking and strategy synthesis techniques are introduced to enable automated verification and guidance of empathetic behaviors. Preliminary experiments demonstrate that the framework faithfully reconstructs the dynamics of therapeutic dialogues, and the generated tailored strategies significantly increase the probability of satisfying empathetic requirements.

Technology Category

• Natural Language Processing: Safety and Robustness
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

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.

Problem

• empathy
• therapy chatbots
• formal verification
• conversational agents
• mental health

Innovation

• empathy verification
• therapy chatbots
• stochastic hybrid automaton
• statistical model checking
• strategy synthesis