Metraipolis › archive › dc_bf301f9c847f

TCMClinicalReason-Bench: Can Language Models Reason from Pathogenesis to Prescription over Real-World Clinical Cases? — arXiv:2610.04215

Source
arXiv
Original
https://arxiv.org/abs/2610.04215
License (as archived)
CC0-1.0
Archived
2026-10-06T05:24:24.130Z
SHA-256 of the archived text
806584a7a8fce153952bc307d9f8a4c177c5caadc2a7ac0018d8af67bfa48379
Stable URL of this page
https://metraipolis.com/documento/dc_bf301f9c847f

How to cite

TCMClinicalReason-Bench: Can Language Models Reason from Pathogenesis to Prescription over Real-World Clinical Cases? — arXiv:2610.04215 — arXiv, https://arxiv.org/abs/2610.04215 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf301f9c847f (Metraipolis archive dc_bf301f9c847f, sha256 806584a7a8fce153952bc307d9f8a4c177c5caadc2a7ac0018d8af67bfa48379)
BibTeX
@misc{dcbf301f9c847f,
  title = {TCMClinicalReason-Bench: Can Language Models Reason from Pathogenesis to Prescription over Real-World Clinical Cases? — arXiv:2610.04215},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04215},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf301f9c847f; sha256 806584a7a8fce153952bc307d9f8a4c177c5caadc2a7ac0018d8af67bfa48379},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04215. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) can generate clinical narratives that are insufficiently grounded in patient-specific evidence. In traditional Chinese medicine (TCM), errors can propagate from etiology and pathogenesis through syndrome diagnosis and treatment principles to prescription generation. We developed TCMClinicalReason-Bench using 2,000 multicenter electronic health record cases to distinguish case-grounded responses from fluent but unsupported diagnostic and therapeutic conclusions. Five general-purpose and two TCM-specific LLMs were evaluated in zero-shot settings. An evidence-constrained rubric assessed seven diagnostic and therapeutic components and three cross-block relations, allowing case-supported alternatives. Qwen3.7-Plus with TCM retrieval served as the automated judge, alongside parallel blinded ratings by five senior TCM clinicians on a 600-case subset. Structural completeness was nearly saturated (99.3-100.0%), but normalized content scores ranged from 40.7% to 54.1%. The five general-purpose models averaged 50.0%, versus 41.3% for the two smaller TCM-specific models. Cross-block logic consistency ranged from 60.8% to 66.8% and correlated moderately with content across cases (Pearson's r = 0.515-0.656). Deficits were greatest in prescription generation, prescription analysis, and symptom-guided modification. In judge stress testing on 100 independent cases, perturbation detection rates across the three relations were 57%, 56%, and 31%, with contradictions detected more reliably than omissions. Separating component quality from cross-block consistency localizes failures missed by endpoint and completeness metrics and identifies where clinician oversight remains necessary.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.04215 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T05:24:05.443Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).