{"ID":2861255,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.01612","arxiv_id":"2510.01612","title":"RAG-BioQA: A Retrieval-Augmented Generation Framework for Long-Form Biomedical Question Answering","abstract":"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.","short_abstract":"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 ge...","url_abs":"https://arxiv.org/abs/2510.01612","url_pdf":"https://arxiv.org/pdf/2510.01612v3","authors":"[\"Lovely Yeswanth Panchumarthi\",\"Sumalatha Saleti\",\"Sai Prasad Gudari\",\"Atharva Negi\",\"Praveen Raj Budime\",\"Harsit Upadhya\"]","published":"2025-10-02T02:49:09Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"RAG\",\"LoRA\"]","has_code":false}