{
  "abstract": "Large language models (LLMs) are increasingly used to draft medical manuscripts, yet their citations are unreliable and clinicians lack a validated way to verify them. We evaluated three frontier LLMs, Claude Opus 4.8, GPT-5.5, and Gemini 3.5 Flash, generating 270 cardiology narrative reviews with web search enabled, and verified all 8,050 references against PubMed. Problematic references accounted for 11.5% of GPT-5.5 output, 29.2% of Claude output, and 29.6% of Gemini output (P < 0.001), with no significant gradient across topics of differing publication volume (P = 0.052). Misattribution, a valid PubMed identifier that resolves to a different article, made up 77% of errors, whereas fabrication was rare (0.6%). Against an expert-adjudicated set of 270 references, an LLM-based Chain-of-Verification (CoVe) detected 60 of 62 problematic references (sensitivity 96.8%, specificity 98.6%), including every misattribution and fabrication. LLM-generated citations require identifier-level verification, and CoVe provides it at expert-level accuracy.",
  "abstract_shown": true,
  "affiliations": [
    "Seoul National University Bundang Hospital"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "name": "R. Shin"
    },
    {
      "name": "J.-M. Lee"
    },
    {
      "name": "J. Park"
    },
    {
      "name": "J.-S. Kwun"
    },
    {
      "name": "H.-W. Cho"
    },
    {
      "name": "S.-H. Kang"
    },
    {
      "affs": [
        0
      ],
      "name": "K.-H. Jeon"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0yn8hybqsk88q.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.08.31.26361806",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.08.31.26361806v1.full",
  "id": "0yn8hybqsk88q",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.08.31.26361806v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "health informatics"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7208730388",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.08.31.26361806v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-31",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0yn8hybqsk88q.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:44Z",
      "native_id": "10.64898/2026.08.31.26361806",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.08.31.26361806v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:health informatics",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Citation reliability of frontier large language models in medical writing and its automated verification",
  "title_text": "Citation reliability of frontier large language models in medical writing and its automated verification",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:44Z",
  "url": "https://research.draconitic.com/paper/0yn8hybqsk88q",
  "venue": "medRxiv",
  "versions": []
}