Metraipolis › archive › dc_2f451fda71cd

Clinical Concept Centers in LLMs — arXiv:2610.02829

Source: arXiv
Original: https://arxiv.org/abs/2610.02829
License (as archived): CC0-1.0
Archived: 2026-10-05T22:51:35.810Z
SHA-256 of the archived text: 6bcf7c079a80e842d8fe5d198a6696b3580246e0df45174603b056a4c0f4be9f
Stable URL of this page: https://metraipolis.com/documento/dc_2f451fda71cd

How to cite

Clinical Concept Centers in LLMs — arXiv:2610.02829 — arXiv, https://arxiv.org/abs/2610.02829 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f451fda71cd (Metraipolis archive dc_2f451fda71cd, sha256 6bcf7c079a80e842d8fe5d198a6696b3580246e0df45174603b056a4c0f4be9f)

BibTeX

@misc{dc2f451fda71cd,
  title = {Clinical Concept Centers in LLMs — arXiv:2610.02829},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02829},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f451fda71cd; sha256 6bcf7c079a80e842d8fe5d198a6696b3580246e0df45174603b056a4c0f4be9f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02829. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models are increasingly used in clinical settings. However, research into the reliability and performance of these models has focused almost entirely on the language substrate, scoring what the model says. Mechanistic interpretability has found that the latent space carries a higher fidelity of representation than the text: internal representations not only encode substantially more than the output verbalizes, but the stated reasoning also systematically omits features that causally drive the answer. An evaluation of model behavior in terms of mechanistic interpretability has not been explored in clinical decision support. In this work, we extend behavioral evaluation into the latent space and ask whether clinical concepts exist as locatable, causally used representations inside open-weight LLMs. We find dedicated clinical concept centers in the latent space of all eleven open models we test. These concept centers are interpretable, firing only on their aligned clinical narratives, and meaningfully and causally drive model behavior in both constrained and open-ended settings. They are not just analytical representations, but circuits that can be utilized in clinical practice, and we explore their use from the perspective of both evaluation and performance. From the evaluation standpoint, models stay internally coherent and keep using the relevant concept centers even under adversarial role-based priming, while aligned priming improves downstream clinical performance. From a performance perspective, we simulate realistic deployment settings and find that steering models along these centers leads to meaningful downstream improvements. Finally, we conduct a blinded clinician validation and find the activation and usage of these concept centers predicts clinicians preferences.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.02829 — 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 2026-10-05T22:46:10.552Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).