@inproceedings{bhojani-etal-2026-biorag,
    title = "{B}io{RAG}: A Systematic Ablation Study of Retrieval Strategies for Biomedical Question Answering",
    author = "Bhojani, Krushil  and
      Waghmare, Mayank  and
      Nandyala, Hima Bindu",
    editor = "Demner-Fushman, Dina  and
      Ananiadou, Sophia  and
      Roberts, Kirk  and
      Tsujii, Junichi",
    booktitle = "{B}io{NLP} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.bionlp-1.10/",
    pages = "104--114",
    ISBN = "979-8-89176-434-7",
    abstract = "Retrieval strategy selection is a critical but understudied design decision in biomedical RAG systems. Existing evaluations rely on lexical metrics that miss answer grounding, or require proprietary infrastructure that limits reproducibility. We present BioRAG, a head-to-head ablation of seven retrieval strategies on BioASQ-13b, evaluated using four RAGAs metrics with a locally deployed judge at zero monetary cost. Hybrid BM25 plus dense retrieval with Reciprocal Rank Fusion achieves faithfulness of 0.534 and context recall of 0.507, improvements of 50{\%} and 85{\%} over naive dense retrieval, confirmed across three random seed re-samples. HyDE improves faithfulness by 14{\%} but reduces context precision by 52{\%}, a tradeoff not previously documented on BioASQ. No single strategy dominates all four metrics, indicating that strategy selection must be application-driven. Sensitivity analysis across k in {\{}3,5,10{\}} confirms ranking stability. A domain mismatch diagnostic confirms 2{\%} corpus coverage failure. The full pipeline runs on consumer hardware without paid APIs, directly addressing BioNLP 2026{'}s emphasis on reproducibility and evaluation frameworks for health-related applications."
}