AsthmaBot: Multi-modal, Multi-Lingual Retrieval Augmented Generation For Asthma Patient Support

TL;DR

AsthmaBot is a multilingual, multi-modal retrieval-augmented system designed to support asthma patients by providing accurate, accessible information through an interactive interface, addressing limitations of existing language models.

Contribution

The paper introduces AsthmaBot, a novel retrieval-augmented generation system that integrates multi-modal data and supports multiple languages for asthma patient assistance.

Findings

AsthmaBot effectively answers asthma-related FAQs with improved accuracy.

It incorporates text, images, and videos to enhance user engagement.

The system is accessible online for public use.

Abstract

Asthma rates have risen globally, driven by environmental and lifestyle factors. Access to immediate medical care is limited, particularly in developing countries, necessitating automated support systems. Large Language Models like ChatGPT (Chat Generative Pre-trained Transformer) and Gemini have advanced natural language processing in general and question answering in particular, however, they are prone to producing factually incorrect responses (i.e. hallucinations). Retrieval-augmented generation systems, integrating curated documents, can improve large language models' performance and reduce the incidence of hallucination. We introduce AsthmaBot, a multi-lingual, multi-modal retrieval-augmented generation system for asthma support. Evaluation of an asthma-related frequently asked questions dataset shows AsthmaBot's efficacy. AsthmaBot has an added interactive and intuitive interface that integrates different data modalities (text, images, videos) to make it accessible to the larger public. AsthmaBot is available online via \url{asthmabot.datanets.org}.