Marco Simnacher

ICON Decomposition: Auditing deep neural networks for shortcuts by decomposing layer-wise representations using concepts

Deep neural networks often exploit spurious associations, a failure known as shortcut learning. Before deployment, models should be audited for reliance on a set of concepts, such as acquisition artifacts or demographics. Current methods, such as linear probes and concept activation vectors, measure reliance by asking...

ICON Decomposition : Multivariate Concept-Level Explanations of Deep Representations for Model Auditing

Embedded Conditional Independence Tests for Large Language Model Generated Text with an Application to German Parliament Speeches

Embedded CITs (eCITs), which embed X and Z and apply an existing CIT to the resulting representations and to the resulting representations, are proposed and it is shown that sufficiency weakens to mean sufficiency when the embedded test targets conditional mean independence.

ICON Decomposition: Auditing Deep Neural Networks with Multivariate Variance-based Concept-level Explanations

CON decomposition is introduced, which quantifies how much of a layer's variance each concept explains given all other concepts and the outcome, and how much none of them explains, yielding layer-comparable, calibrated scores that suppress false positives.

Interpreting Protein Language Model Embeddings via Orthogonal Projection for Protein Fitness Prediction

It is shown that PLM embeddings encode patterns correlated with biochemical properties and quantify their contribution to predicting protein fitness, and this technique is readily transferable to problem settings beyond protein fitness prediction.