5 papers
Embedded Conditional Independence Tests for Large Language Model Generated Text with an Application to German Parliament Speeches
Marco Simnacher, Georg Keilbar, Benjamin König +2
Conditional independence tests (CITs) test for conditional dependence between two random objects and given a third random object . Existing CITs have limited applicabili…
ICON decomposition: Multivariate concept auditing reveals shortcuts that neural networks rely on
Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer +7
Deep neural networks often exploit spurious associations, a failure known as shortcut learning. Before deployment, models should therefore be audited for reliance on concepts such…
Interpreting Protein Language Model Embeddings via Orthogonal Projection for Protein Fitness Prediction
Paulo Yanez Sarmiento, Pia Francesca Rissom, Manuel Pfeuffer +6
Recently, there has been a growing adoption of protein language models (PLMs) in biomedical science. Their embeddings provide a rich numerical representation of protein sequences w…
Counterfactual Explanations for Deep Two-Sample Testing
Wei-Cheng Lai, Marco Simnacher, Christoph Lippert
Two-sample testing is a fundamental tool for detecting distributional differences across scientific domains, but classical tests (including kernel-based tests) can be ineffective o…
Deep Nonparametric Conditional Independence Tests for Images
Marco Simnacher, Xiangnan Xu, Hani Park +2
Conditional independence tests (CITs) test for conditional dependence between random variables. As existing CITs are limited in their applicability to complex, high-dimensional var…