SOURCE-LINKED INTELLIGENCE

Matryoshka Hash Representations for Model-Aware Compact Semantic Retrieval

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Retrieval-augmented generation (RAG) depends on dense retrieval: each document is stored as a learned vector, and a query is answered by finding its nearest neighbors in that vector space. Keeping one full-precision vector per document is the dominant index cost at corpus scale, so retrieval systems replace each vector with a short code of a few bytes---a step called quantization. Standard quantizers such as product quantization (PQ) pick the code that reconstructs the original vector most closely. A single code is even more useful if it serves several byte budgets at once: when its short pref

Read original source ↗ Open in workspace

recordType

paper

region

Global