Do You Understand How I Feel?: Towards Verified Empathy in Therapy Chatbots
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911371947409408 |
|---|---|
| author | Dettori, Francesco Forasassi, Matteo Veronese, Lorenzo Lestingi, Livia Scotti, Vincenzo Rossi, Matteo Giovanni |
| author_facet | Dettori, Francesco Forasassi, Matteo Veronese, Lorenzo Lestingi, Livia Scotti, Vincenzo Rossi, Matteo Giovanni |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_08477 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Do You Understand How I Feel?: Towards Verified Empathy in Therapy Chatbots Dettori, Francesco Forasassi, Matteo Veronese, Lorenzo Lestingi, Livia Scotti, Vincenzo Rossi, Matteo Giovanni Computation and Language Human-Computer Interaction Software Engineering 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. |
| title | Do You Understand How I Feel?: Towards Verified Empathy in Therapy Chatbots |
| topic | Computation and Language Human-Computer Interaction Software Engineering |
| url | https://arxiv.org/abs/2601.08477 |