Tag
This paper proposes a framework to analyze how linguistic relations are linearly encoded in language model embeddings, revealing differences across models like GloVe, RoBERTa, and ModernBERT and relation types.
This paper introduces KODA (Kernel Optimization for Discrepancy Analysis), a kernel-based framework for comparing and aligning vision-language model representations by identifying sample subsets that are clustered differently across models like CLIP, SigLIP, and BLIP. The method uses contrastive embedding clustering and randomized low-dimensional approximations to scale to large datasets while providing interpretable structural differences between representations.