Conversational Assistants to support Heart Failure Patients: \\ comparing a Neurosymbolic Architecture with ChatGPT

ACL ARR 2025 February Submission7143 Authors

Abstract: Conversational assistants are becoming more and more popular, including in healthcare, partly because of the availability and capabilities of Large Language Models. There is a need for controlled, probing evaluations with real stakeholders which can highlight advantages and disadvantages of more traditional architectures and those based on generative AI. We present a within-group user study to compare two versions of a conversational assistant that allows heart failure patients to ask about salt content in food. One version of the system was developed in-house with a neurosymbolic architecture, and one is based on ChatGPT. The evaluation shows that the in-house system is more accurate, completes more tasks and is less verbose than the one based on ChatGPT; on the other hand, the one based on ChatGPT makes fewer speech errors and requires fewer clarifications to complete the task. Patients show no preference for one over the other.

Paper Type: Long

Research Area: Dialogue and Interactive Systems

Research Area Keywords: task-oriented, human-centered evaluation, user-study, healthcare applications

Contribution Types: Model analysis & interpretability, Data analysis

Languages Studied: English

Submission Number: 7143