{
  "abstract": "Introduction: Traditional Chinese Medicine (TCM) tongue diagnosis requires reconstruction of multiple visual signs across tongue morphology, body color, coating texture, and coating color. We developed TongueBench as a prompt-controlled, ontology-constrained evaluation protocol for application programming interface (API)-accessed large multimodal models (LMMs), without task-specific training.\n\nMethods: Nine LMMs were evaluated on 2,694 tongue images with 22 expert-adjudicated labels under direct prompting (DP), knowledge-guided prompting (KGP), and knowledge-guided reflective prompting (KGRP). For the primary LMM-versus-supervised comparison, archived LMM predictions were matched to the same 270 test images used by three supervised baselines. Sensitivity analyses assessed a fixed label order, training-only frequencies, and no conflict removal. Raw-output auditing distinguished model-generated ontology violations from their removal by deterministic post-processing.\n\nResults: Across the nine evaluated models, KGRP increased mean Micro-F1 from 47.57% to 48.51%, Macro-F1 from 32.41% to 33.60%, and sample-level Jaccard from 34.45% to 35.32%, while reducing Hamming loss from 26.39% to 25.54%. Model-level changes were heterogeneous. Image-level bootstrap intervals described the fixed nine-model mean contrast under an unverified image-independence assumption. Supervised models had better observed aggregate scores on the matched split, but patient-level separation could not be established. Sensitivity analyses retained the direction of the mean KGRP-versus-DP changes.\n\nDiscussion: TongueBench characterizes modest prompt-associated changes, parsing failures, repeated-output variation, and incomplete label-set reconstruction. These observations do not establish general prompt superiority, patient-level generalizability, or clinical utility.",
  "abstract_shown": true,
  "affiliations": [
    "Institute of TCM Diagnostics, Hunan University of Chinese Medicine, Changsha, Hunan, China",
    "Provincial Key Laboratory of TCM Diagnostics, Hunan University of Chinese Medicine, Changsha, Hunan, China",
    "School of Software Engineering, Sun Yat-sen University, Zhuhai, China",
    "Department of Computer Science, Cornell University, Ithaca, NY, United States",
    "Academy of Chinese Medical Sciences, Hunan University of Chinese Medicine, Changsha, Hunan, China"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Yihan Meng"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Nuan Cui"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Jingxin Yao"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Shufeng Kong"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Pei Liu"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Zengbo Zhang"
    },
    {
      "affs": [
        4
      ],
      "name": "Hao Liang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/c07k26bctyttb.bib",
  "cited_by": 0,
  "doi": "10.3389/frai.2026.1943004",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13731349/",
  "id": "c07k26bctyttb",
  "issns": [
    "2624-8212"
  ],
  "landing_url": "https://doi.org/10.3389/frai.2026.1943004",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Original Research"
    ],
    [
      "openalex",
      "2707|Traditional Chinese Medicine Studies"
    ]
  ],
  "openalex": "W7223104955",
  "pdf_url": "https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2026.1943004/pdf",
  "pmcid": "PMC13731349",
  "pmid": "42984981",
  "published": "2026-10-21",
  "publisher": "Frontiers Media SA",
  "ris": "https://research.draconitic.com/paper/c07k26bctyttb.ris",
  "sources": [
    {
      "first_seen": "2026-11-08T12:21:33Z",
      "native_id": "PMC13731349",
      "source": "pmc",
      "url": "https://doi.org/10.3389/frai.2026.1943004"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2707|Traditional Chinese Medicine Studies",
      "subfield": "general"
    }
  ],
  "title": "TongueBench: performance of prompt-engineered large multimodal models in Traditional Chinese Medicine tongue diagnosis",
  "title_text": "TongueBench: performance of prompt-engineered large multimodal models in Traditional Chinese Medicine tongue diagnosis",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T12:21:33Z",
  "url": "https://research.draconitic.com/paper/c07k26bctyttb",
  "venue": "Frontiers in Artificial Intelligence",
  "versions": []
}