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.
@article{arxiv.2502.10374,
title = {Robustness tests for biomedical foundation models should tailor to specifications},
author = {R. Patrick Xian and Noah R. Baker and Tom David and Qiming Cui and A. Jay Holmgren and Stefan Bauer and Madhumita Sushil and Reza Abbasi-Asl},
journal= {arXiv preprint arXiv:2502.10374},
year = {2025}
}
Comments
17 pages, accepted version with SI, repo at https://github.com/RealPolitiX/bfm-robust