Efficient Multi-Vector Dense Retrieval Using Optimized Bit Vectors and Product Quantization
This paper introduces EMVB, a novel framework for efficient query processing in multi-vector dense retrieval. EMVB employs a highly efficient pre-filtering step using optimized bit vectors, a column-wise SIMD reduction for candidate passage retrieval, and a late interaction mechanism that combines product quantization with per-document term filtering to significantly improve the efficiency of multi-vector dense retrieval systems.