{
  "abstract": "Language models and agents are increasingly used in biomedicine, but current benchmarks reward correct answers even when the underlying reasoning is flawed. Here we introduce Karenina, an open-source framework that turns expert knowledge into multi-dimensional evaluations of questions, conversations and autonomous agents. Illustrated in Question-Answer pairs, multi-turn conversations and autonomous data-analysis, these dimensions together moves evaluation beyond scoring, enabling trustworthy decision-making with AI in biomedicine.",
  "abstract_shown": true,
  "affiliations": [
    "European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Hinxton, UK;Open Targets, European Molecular Biology Laboratory, Hinxton, U"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 11,
  "authors": [
    {
      "name": "F. Carli"
    },
    {
      "name": "P. Rusina"
    },
    {
      "name": "L. Ai"
    },
    {
      "name": "L. Kuechenhoff"
    },
    {
      "name": "P. K. P. To"
    },
    {
      "name": "E. M. McDonagh"
    },
    {
      "name": "S. Lobentanzer"
    },
    {
      "name": "F. Petroni"
    },
    {
      "name": "A. Dugourd"
    },
    {
      "name": "D. Ochoa"
    },
    {
      "affs": [
        0
      ],
      "name": "J. Saez-Rodriguez"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/e5ps2q05pgz67.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.01.748513",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.01.748513v1.full",
  "id": "e5ps2q05pgz67",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.01.748513v1",
  "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": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7208814027",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.01.748513v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/e5ps2q05pgz67.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:35Z",
      "native_id": "10.64898/2026.09.01.748513",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.01.748513v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Turning Domain Expertise into Multi-Dimensional Evaluation of Biomedical AI with Karenina",
  "title_text": "Turning Domain Expertise into Multi-Dimensional Evaluation of Biomedical AI with Karenina",
  "type": "preprint",
  "updated_at": "2026-10-30T12:19:35Z",
  "url": "https://research.draconitic.com/paper/e5ps2q05pgz67",
  "venue": "bioRxiv",
  "versions": []
}