RAG-BioQA: A Retrieval-Augmented Generation Framework for Long-Form Biomedical Question Answering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Panchumarthi, Lovely Yeswanth, Saleti, Sumalatha, Gudari, Sai Prasad, Negi, Atharva, Budime, Praveen Raj, Upadhya, Harsit
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915702737207296
author Panchumarthi, Lovely Yeswanth
Saleti, Sumalatha
Gudari, Sai Prasad
Negi, Atharva
Budime, Praveen Raj
Upadhya, Harsit
author_facet Panchumarthi, Lovely Yeswanth
Saleti, Sumalatha
Gudari, Sai Prasad
Negi, Atharva
Budime, Praveen Raj
Upadhya, Harsit
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_01612
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RAG-BioQA: A Retrieval-Augmented Generation Framework for Long-Form Biomedical Question Answering
Panchumarthi, Lovely Yeswanth
Saleti, Sumalatha
Gudari, Sai Prasad
Negi, Atharva
Budime, Praveen Raj
Upadhya, Harsit
Computation and Language
Artificial Intelligence
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.
title RAG-BioQA: A Retrieval-Augmented Generation Framework for Long-Form Biomedical Question Answering
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.01612