A Chatbot Powered by Large Language Models for Home-Based ADRD Support
Year: 2026
Type: conference-paper
Abstract: Alzheimer’s disease and related dementias (ADRD) remain highly prevalent and are among the leading causes of death in the United States. Providing effective care for individuals with ADRD presents significant challenges, particularly for caregivers who require accessible and reliable support resources. Recent advances in large language models (LLMs) offer promising opportunities to deliver personalized, conversational assistance. This study presents the development of a web-based LLM-powered chatbot designed to support home-based ADRD care by providing clear, context-aware information. The system integrates modern web technologies with LLaMA-based models to generate responses tailored to user needs. Our preliminary results show that the LLaMA 3.1 model achieves performance comparable to that of the LLaMA 3.3 model. However, the LLaMA 3.1 model requires fewer resources, enabling potential deployment in future mobile applications.
Authors: Ansh Khurana, Xiao Luo
Institutions: Montgomery High School, Southern Methodist University
Language: English
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W7202299112