The rapidly growth of biomedical literature creates challenges acquiring specific medical information. Current biomedical question-answering systems primarily focus on short-form answers, failing to provide comprehensive explanations necessary for clinical decision-making. We present RAG-BioQA, a retrieval-augmented generation framework for long-form biomedical question answering. Our system integrates BioBERT embeddings with FAISS indexing for retrieval and a LoRA fine-tuned FLAN-T5 model for answer generation. We train on 181k QA pairs from PubMedQA, MedDialog, and MedQuAD, and evaluate on a held-out PubMedQA test set. We compare four retrieval strategies: dense retrieval (FAISS), BM25, ColBERT, and MonoT5. Our results show that domain-adapted dense retrieval outperforms zero-shot neural re-rankers, with the best configuration achieving 0.24 BLEU-1 and 0.29 ROUGE-1. Fine-tuning improves BERTScore by 81\% over the base model. We release our framework to support reproducible biomedical QA research.
@article{arxiv.2510.01612,
title = {RAG-BioQA: A Retrieval-Augmented Generation Framework for Long-Form Biomedical Question Answering},
author = {Lovely Yeswanth Panchumarthi and Sumalatha Saleti and Sai Prasad Gudari and Atharva Negi and Praveen Raj Budime and Harsit Upadhya},
journal= {arXiv preprint arXiv:2510.01612},
year = {2026}
}