Why not to use Cosine Similarity between Label Representations

ArXi:2603.29488v1 Announce Type: new Cosine similarity is often used to measure the similarity of vectors. These vectors might be the representations of neural network models. However, it is not guaranteed that cosine similarity of model representations will tell us anything about model behaviour. In this paper we show that when using a softmax classifier, be it an image classifier or an autoregressive language model, measuring the cosine similarity between label representations (called unembeddings in the paper) does not give any information on the probabilities assigned by the model.