Harnessing the Universal Geometry of Embeddings
- View PDF HTML (experimental) Abstract:We introduce the first method for translating text embeddings from one vector space to another without any paired data, encoders, or predefined sets of matches.
- Our unsupervised approach translates any embedding to and from a universal latent representation (i.e., a universal semantic structure conjectured by the Platonic Representation Hypothesis).
- Our translations achieve high cosine similarity across model pairs with different architectures, parameter counts, and training datasets.
Unverified
- View PDF HTML (experimental) Abstract:We introduce the first method for translating text embeddings from one vector space to another without any paired data, encoders, or predefined sets of matches.
- Our unsupervised approach translates any embedding to and from a universal latent representation (i.e., a universal semantic structure conjectured by the Platonic Representation Hypothesis).
- Our translations achieve high cosine similarity across model pairs with different architectures, parameter counts, and training datasets.
Sources: Arxiv