Scaling Responsible Medical Text Retrieval Across Silos: Evaluating Small Language Models with Retrieval-Augmented Generation
Abstract
This study evaluates small language models with FAISS and Dynamic Top-k for diabetes-focused medical text retrieval, with all-mpnet-base-v2 performing best and FAISS (FAISS Facebook AI Similarity Search) maintaining sub-2 ms latency even at tenfold scale. Dynamic Top-k improved precision and nDCG (Normalized Discounted Cumulative Gain), showing that lightweight SLM-RAG (Small Language Model-Retrieval Augmented Generation) pipelines can approach larger-model accuracy while remaining highly scalable for cloud-based EMR (Electronic Medical Record) environments.
Fields of Study & Subjects
Topic Modeling
Biomedical Text Mining and Ontologies
Health Literacy and Information Accessibility
Publication details
- Journal / source
- Studies in health technology and informatics
- Publisher
- IOS Press
- Volume
- 334
- Pages
- 150–151
- Publication date
- 12 February 2026
- Language
- EN
- Document type
- Book chapter