Late-interaction (multi-vector) models represent documents using a set of token-level vectors, providing a middle ground between cross-encoders and dense encoders in terms of quality and cost of embedding. However, compared to the latter, the indices are costly to store and score. Pooling and pruning based compression...
Graphs are a standard representation for data in the social sciences, cybersecurity, computer infrastructure, bioinformatics, and more. Typical real-world graphs are sparse, meaning the average degree is small (in the tens, while the number of vertices is more than millions). When graph data is collected from a source,...
This work introduces EigenLI, a spectral approximation framework that compresses late-interaction representations via document-specific low-dimensional subspaces and consistently outperforms comparable single-vector surrogates such as MUVERA.
S. Archish, Sabyasachi Basu, Ankit Garg et al.· 1 citation
This work provides the first explicit family of query and document sets, together with their relevance matrices, for which single-vector embeddings that rank all relevant documents above irrelevant ones require exponential size, whereas polynomial-size multi-vector embeddings suffice.
Mihir Agarwal, Viraj Agrawal, Sabyasachi Basu et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.