SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

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 whether each concept, in isolation, is decodable from a layer. Their scores therefore reflect not only reliance but also correlations in the audit dataset. We introduce Independent Canonical cONcept (ICON) decomposition, which quantifies the share of a layer's variance each conce

Read original source ↗ Open in workspace

recordType

paper

region

Global