GICDM: Mitigating Hubness for Reliable Distance-Based Generative Model Evaluation

ArXi:2602.16449v2 Announce Type: replace-cross Generative model evaluation commonly relies on high-dimensional embedding spaces to compute distances between samples. We show that dataset representations in these spaces are affected by the hubness phenomenon, which distorts nearest-neighbor relationships and biases distance-based metrics. Building on the classical Iterative Contextual Dissimilarity Measure (ICDM), we