Discovering Intersectional Bias via Directional Alignment in Face Recognition Embeddings

ArXi:2510.15520v2 Announce Type: replace-cross Modern face recognition models embed identities on a unit hypersphere, where identity variation forms tight clusters. Conversely, shared semantic attributes can often be effectively approximated as linear directions in the latent space. Existing bias evaluation methods rely on predefined attribute labels, synthetic counterfactuals, or proximity-based clustering, all of which fail to capture intersectional subpopulations that emerge along latent directions. We.