WARP: An Efficient Engine for Multi-Vector Retrieval

2025-01-29 · Jan Luca Scheerer, Matei Zaharia, Christopher Potts, Gustavo Alonso, Omar Khattab

Multi-vector retrieval methods such as ColBERT and its recent variant, the ConteXtualized Token Retriever (XTR), offer high accuracy but face efficiency challenges at scale. To address this, we present WARP, a retrieval engine that substantially improves the efficiency of retrievers trained with the XTR objective through three key innovations: (1) WARP$_\text{SELECT}$ for dynamic similarity imputation; (2) implicit decompression, avoiding costly vector reconstruction during retrieval; and (3) a two-stage reduction process for efficient score aggregation. Combined with highly-optimized C++ kernels, our system reduces end-to-end latency compared to XTR's reference implementation by 41x, and achieves a 3x speedup over the ColBERTv2/PLAID engine, while preserving retrieval quality.

📄 PDF Abstract BibTeX arXiv:2501.17788

Code (0)

등록된 구현이 없습니다.

Tasks

Imputation Retrieval

Improving Warped Planar Object Detection Network For Automatic License Plate Recognition

2022-12-14 · Nguyen Dinh Tra, Nguyen Cong Tri, Phan Duy Hung

This paper aims to improve the Warping Planer Object Detection Network (WPOD-Net) using feature engineering to increase accuracy. What problems are solved using the Warping Object Detection Network using feature engineer…

Feature Engineering License Plate Recognition object-detection Object Detection

RAG Playground: A Framework for Systematic Evaluation of Retrieval Strategies and Prompt Engineering in RAG Systems

2024-12-16 · Ioannis Papadimitriou, Ilias Gialampoukidis, Stefanos Vrochidis, Ioannis 외

We present RAG Playground, an open-source framework for systematic evaluation of Retrieval-Augmented Generation (RAG) systems. The framework implements and compares three retrieval approaches: naive vector search, rerank…

Prompt Engineering RAG Reranking Retrieval+1

Designing Interfaces for Multimodal Vector Search Applications

2024-09-18 · Owen Pendrigh Elliott, Tom Hamer, Jesse Clark

Multimodal vector search offers a new paradigm for information retrieval by exposing numerous pieces of functionality which are not possible in traditional lexical search engines. While multimodal vector search can be tr…

Information Retrieval Retrieval

SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes

2023-02-13 · Minghan Li, Sheng-Chieh Lin, Xueguang Ma, Jimmy Lin

This paper introduces Sparsified Late Interaction for Multi-vector (SLIM) retrieval with inverted indexes. Multi-vector retrieval methods have demonstrated their effectiveness on various retrieval datasets, and among the…

Information Retrieval Retrieval

Bridging Dual Knowledge Graphs for Multi-Hop Question Answering in Construction Safety

2025-07-18 · Yuxin Zhang, Xi Wang, Mo Hu, Zhenyu Zhang arxiv

Information retrieval and question answering from safety regulations are essential for automated construction compliance checking but are hindered by the linguistic and structural complexity of regulatory text. Many quer…

Multi-hop Question Answering Information Retrieval Knowledge Graphs