paper-with-me

Papers

Efficient Constant-Space Multi-Vector Retrieval

2025-04-02 · Sean MacAvaney, Antonio Mallia, Nicola Tonellotto

Multi-vector retrieval methods, exemplified by the ColBERT architecture, have shown substantial promise for retrieval by providing strong trade-offs in terms of retrieval latency and effectiveness. However, they come at a high cost in terms of storage since a (potentially compressed) vector needs to be stored for every token in the input collection. To overcome this issue, we propose encoding documents to a fixed number of vectors, which are no longer necessarily tied to the input tokens. Beyond reducing the storage costs, our approach has the advantage that document representations become of a fixed size on disk, allowing for better OS paging management. Through experiments using the MSMARCO passage corpus and BEIR with the ColBERT-v2 architecture, a representative multi-vector ranking model architecture, we find that passages can be effectively encoded into a fixed number of vectors while retaining most of the original effectiveness.

📄 PDF Abstract BibTeX arXiv:2504.01818

Code (1)

pisa-engine/constbert 공식 구현

Tasks

ManagementRetrieval

Similar Papers 제목 키워드 기반

Recursive Binding on a Budget: Subspace Carving in Order-p Tensor Memories

2026-06-09 · Travis Pence, Daisuke Yamada, Vikas Singh arxiv

Tensor Product Representations provide the structural fidelity required for symbolic reasoning in models but suffer from exponential dimensionality growth when encoding deep recursive structures. Conversely, Vector Symbo…

LEMUR: Learned Multi-Vector Retrieval

2026-01-29 · Elias Jääsaari, Ville Hyvönen, Teemu Roos arxiv

Multi-vector representations generated by late interaction models, such as ColBERT, enable superior retrieval quality compared to single-vector representations in information retrieval applications. In multi-vector retri…

Information Retrieval

Multi-Vector Index Compression in Any Modality

2026-02-24 · Hanxiang Qin, Alexander Martin, Rohan Jha, Chunsheng Zuo 외 arxiv

We study efficient multi-vector retrieval for late interaction in any modality. Late interaction has emerged as a dominant paradigm for information retrieval in text, images, visual documents, and videos, but its computa…

Information Retrieval

Generative Multi-hop Retrieval

2022-04-27 · Hyunji Lee, Sohee Yang, Hanseok Oh, Minjoon Seo

A common practice for text retrieval is to use an encoder to map the documents and the query to a common vector space and perform a nearest neighbor search (NNS); multi-hop retrieval also often adopts the same paradigm, …

DecoderGPURetrievalText Retrieval

Beyond Nearest Neighbors: Semantic Compression and Graph-Augmented Retrieval for Enhanced Vector Search

2025-07-25 · Rahul Raja, Arpita Vats arxiv

Vector databases typically rely on approximate nearest neighbor (ANN) search to retrieve the top-k closest vectors to a query in embedding space. While effective, this approach often yields semantically redundant results…

Semantic Retrieval