{
  "abstract": "Large language models (LLMs) in biomedicine face a fundamental conflict between static parameter knowledge and the dynamic nature of clinical evidence. Retrieval-Augmented Generation (RAG) addresses this by grounding generation in external data, yet it introduces new complexities in latency and architecture. This survey synthesizes the biomedical RAG landscape (2020–2025), classifying systems into naive, advanced, and modular paradigms. Beyond a technological taxonomy, we formalize the biomedical RAG trilemma, identifying the inherent trade-offs between reasoning depth, inference latency, and data privacy that constrain current clinical deployment. We analyze how recent agentic workflows enhance diagnostic reasoning but risk prohibitive latency, and how privacy constraints dictate the choice between powerful cloud-based models and local deployment. Finally, we outline the alignment gap in multimodal RAG and propose future directions for self-correcting, verifiable clinical agents.",
  "abstract_shown": true,
  "affiliations": [
    "Hunan City University, Yiyang, Hunan, China",
    "University of Geneva, Geneva, Switzerland",
    "University of Geneva",
    "Henan University, Kaifeng, Henan, China",
    "Henan University",
    "National University of Singapore, Singapore, Singapore",
    "National University of Singapore",
    "LvZhiDao Information Technology Co., Ltd, Changsha, Hunan, China",
    "LvZhiDao Information Technology Co., Ltd",
    "Hunan City University"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 9,
  "authors": [
    {
      "affs": [
        0,
        1,
        2
      ],
      "name": "Jiawei He",
      "orcid": "0000-0003-1996-3264"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Boya Zhang",
      "orcid": "0000-0002-4439-8212"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Hossein Rouhizadeh",
      "orcid": "0000-0002-6496-6766"
    },
    {
      "affs": [
        3,
        4
      ],
      "name": "Yingjian Chen",
      "orcid": "0009-0004-1359-6998"
    },
    {
      "affs": [
        5,
        6
      ],
      "name": "Rui Yang",
      "orcid": "0009-0006-0597-7197"
    },
    {
      "affs": [
        7,
        8
      ],
      "name": "Jin suo Lu",
      "orcid": "0009-0002-7681-1136"
    },
    {
      "affs": [
        0,
        9
      ],
      "name": "Xudong Chen",
      "orcid": "0000-0002-7087-4075"
    },
    {
      "affs": [
        5,
        6
      ],
      "name": "Nan Liu",
      "orcid": "0000-0003-3610-4883"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Douglas Teodoro",
      "orcid": "0000-0001-6238-4503"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dw6x0jfvr53fs.bib",
  "cited_by": 27,
  "doi": "10.1007/s10462-026-11743-y",
  "fulltext_url": null,
  "id": "dw6x0jfvr53fs",
  "issns": [
    "0269-2821",
    "1573-7462"
  ],
  "landing_url": "https://doi.org/10.1007/s10462-026-11743-y",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W4417313874",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-23",
  "publisher": "Springer Science+Business Media",
  "ris": "https://research.draconitic.com/paper/dw6x0jfvr53fs.ris",
  "sources": [
    {
      "first_seen": "2026-11-01T13:20:20Z",
      "native_id": "W4417313874",
      "source": "openalex",
      "url": "https://doi.org/10.1007/s10462-026-11743-y"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Retrieval-augmented generation in biomedicine: a survey of technologies, datasets, and clinical applications",
  "title_text": "Retrieval-augmented generation in biomedicine: a survey of technologies, datasets, and clinical applications",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T13:20:50Z",
  "url": "https://research.draconitic.com/paper/dw6x0jfvr53fs",
  "venue": "Artificial Intelligence Review",
  "versions": []
}