Large Language Models for Sexual, Reproductive, and Maternal Health Rights*

Abstract

This research explores the potential of Large Language Models in the context of healthcare solutions, with a specific focus on Sexual, Reproduc-tive, and Maternal Health Rights (SRMHR) Question Answering (QA) in the low-resource language, Amharic (““'Ie;;:). To construct the dataset, we first collected data from medical textbooks and guidelines authored by reputable medical institutions and organizations. U ti-lizing automatic question-and-answer generation techniques, we then generated pairs for the dataset. Sub-sequently, the dataset underwent annotation, translation, and evaluation processes, resulting in a refined collection of 2.8k Amharic datasets. We use the dataset to fine-tune the LLaMA-2-Amharic model, with test results assessed using BLEU scores and human-level evaluations, demonstrating promising outcomes. The curated Amharic SRMHRQA dataset serves as a foun- dational resource for future research. However, further enhancements are necessary to optimize its efficacy, particularly within the realm of SRMHR for low- resource languages like Amharic. Future research could involve scaling up the dataset in terms of size, quality, and domain coverage.