SARHAchat: An LLM-Based Chatbot for Sexual and Reproductive Health Counseling

TL;DR

This paper tackles safety and reliability gaps in SRH AI chatbots by introducing SARHAchat, an LLM-based SRH counseling assistant. It combines a bi-level memory architecture, structured reasoning, and thought-injection prompting with Retrieval-Augmented Generation to ground recommendations in current guidelines. In evaluations against a naive prompting baseline, SARHAchat achieves markedly higher medical safety (98.22% vs 85.21%), reduces omissions and contraindicated recommendations, and attains superior conversational quality (98.82% satisfactory vs 89.35%). The results indicate SARHAchat can streamline pre-clinical SRH care and holds promise for clinical deployment, with a public demo available.

Abstract

While Artificial Intelligence (AI) shows promise in healthcare applications, existing conversational systems often falter in complex and sensitive medical domains such as Sexual and Reproductive Health (SRH). These systems frequently struggle with hallucination and lack the specialized knowledge required, particularly for sensitive SRH topics. Furthermore, current AI approaches in healthcare tend to prioritize diagnostic capabilities over comprehensive patient care and education. Addressing these gaps, this work at the UNC School of Nursing introduces SARHAchat, a proof-of-concept Large Language Model (LLM)-based chatbot. SARHAchat is designed as a reliable, user-centered system integrating medical expertise with empathetic communication to enhance SRH care delivery. Our evaluation demonstrates SARHAchat's ability to provide accurate and contextually appropriate contraceptive counseling while maintaining a natural conversational flow. The demo is available at https://sarhachat.com/}{https://sarhachat.com/.

Figures (1)

• Figure 1: Overview of the SARHAchat conversation logic and system components.