Embeddings & Vector SearchOrion Weller, Michael Boratko et al. (Google DeepMind, Johns Hopkins)Google DeepMind
On the Theoretical Limitations of Embedding-Based Retrieval published
On the Theoretical Limitations of Embedding-Based Retrieval published — shows in theory and experiments that the embedding dimension limits the number of top-k document subsets that can be returned. On the LIMIT dataset, SOTA models fail even on very simple queries
Why it matters
A rebuttal showing that the limits of single-vector retrieval are fundamental, dimensional limits that more data or bigger models cannot fix. A theoretical basis for a return to multi-vector, sparse and hybrid retrieval
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2508.21038Added in Week 35, 2026 · See that week