Metraipolis › archive › dc_802b2e950372

Dense Clinical Contrasts Enhance Medical Knowledge Updating in Large Language Models — arXiv:2608.30405

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.30405
License (as archived): CC0-1.0
Archived: 2026-10-17T07:44:39.033Z
SHA-256 of the archived text: c03fc838b04fdb42014f86e14a29582e7cd34314d397cc2e688f9ab0d4a7423c
Stable URL of this page: https://metraipolis.com/documento/dc_802b2e950372

How to cite

Dense Clinical Contrasts Enhance Medical Knowledge Updating in Large Language Models — arXiv:2608.30405 — arXiv (en), https://arxiv.org/abs/2608.30405 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_802b2e950372 (Metraipolis archive dc_802b2e950372, sha256 c03fc838b04fdb42014f86e14a29582e7cd34314d397cc2e688f9ab0d4a7423c)

BibTeX

@misc{dc802b2e950372,
  title = {Dense Clinical Contrasts Enhance Medical Knowledge Updating in Large Language Models — arXiv:2608.30405},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30405},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_802b2e950372; sha256 c03fc838b04fdb42014f86e14a29582e7cd34314d397cc2e688f9ab0d4a7423c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30405. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Medical knowledge changes continually, making large language models vulnerable to relying on outdated yet clinically plausible information. We study whether the format of supervision affects medical knowledge updating under a matched training-budget setting. We introduce SEER-Bench, a temporally anchored oncology-staging benchmark curated from the latest versioned SEER Research Data release, and render identical medical update events from NCCN oncology guidelines into four supervision formats: EMQ, MSQ, FITB, and SAQ. Across SEER-Bench and HealthBench Professional, EMQ gives the most stable external transfer and retention among same-budget SFT variants. With EMQ supervision, the updated 4B model produces competitive results on temporally anchored oncology staging, reaching 64.8% answer accuracy and 59.6% rationale accuracy on SEER-Bench. Diagnostic analyses suggest that EMQ exposes denser clinical contrast signals while preserving discriminative representations with smaller movement from the base model. These results show that medical knowledge updating depends not only on the update algorithm, but also on how knowledge is structured as supervision.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.30405 — 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 2026-10-17T07:28:26.602Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).