5 papers · 1 filter
Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM
Vinith M. Suriyakumar, Ayush Sekhari, Lena Stempfle +5
Auditing the fine-tunes of open-weight generative models for harmful specialization has become a new governance challenge for model hosting platforms. The standard toolkit, generat…
An Investigation of Memorization Risk in Healthcare Foundation Models
Sana Tonekaboni, Lena Stempfle, Adibvafa Fallahpour +2
Foundation models trained on large-scale de-identified electronic health records (EHRs) hold promise for clinical applications. However, their capacity to memorize patient informat…
Prediction Models That Learn to Avoid Missing Values
Lena Stempfle, Anton Matsson, Newton Mwai +1
Handling missing values at test time is challenging for machine learning models, especially when aiming for both high accuracy and interpretability. Established approaches often ad…
Handling missing values in clinical machine learning: Insights from an expert study
Lena Stempfle, Arthur James, Julie Josse +2
Inherently interpretable machine learning (IML) models offer valuable support for clinical decision-making but face challenges when features contain missing values. Traditional app…
How Should We Represent History in Interpretable Models of Clinical Policies?
Anton Matsson, Lena Stempfle, Yaochen Rao +3
Modeling policies for sequential clinical decision-making based on observational data is useful for describing treatment practices, standardizing frequent patterns in treatment, an…