PuSH - Publikationsserver des Helmholtz Zentrums München

Xian, R.P.* ; Baker, N.R.* ; David, T.* ; Cui, Q.H.* ; Holmgren, A.J.* ; Bauer, S. ; Sushil, M.* ; Abbasi-Asl, R.*

Robustness tests for biomedical foundation models should tailor to specifications.

NPJ Digit. Med. 8:557 (2025)
Verlagsversion Forschungsdaten DOI PMC
Open Access Gold
Creative Commons Lizenzvertrag
The rise of biomedical foundation models creates new hurdles in model testing and authorization, given their broad capabilities and susceptibility to complex distribution shifts. We suggest tailoring robustness tests according to task-dependent priorities and propose to integrate granular notions of robustness in a predefined specification to guide implementation. Our approach facilitates the standardization of robustness assessments in the model lifecycle and connects abstract AI regulatory frameworks with concrete testing procedures.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Fachkommentar, Meinungsartikel
ISSN (print) / ISBN 2398-6352
e-ISSN 2398-6352
Zeitschrift NPJ digital medicine
Quellenangaben Band: 8, Heft: 1, Seiten: , Artikelnummer: 557 Supplement: ,
Verlag Nature Publishing Group
Verlagsort Heidelberger Platz 3, Berlin, 14197, Germany
Begutachtungsstatus Peer reviewed
Institut(e) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Förderungen National Cancer Institute of the National Institutes of Health
Weill Neurohub