8. On the Theoretical Limitations of Embedding-based Retrieval Finds that single-vector dense retrievers cannot realize all possible top-k relevance combinations once queries demand sufficiently many “mix-and-match” document sets.
By
–
8. On the Theoretical Limitations of Embedding-based Retrieval Finds that single-vector dense retrievers cannot realize all possible top-k relevance combinations once queries demand sufficiently many “mix-and-match” document sets.