@inproceedings{park-etal-2025-scv,
title = "{SCV}: Light and Effective Multi-Vector Retrieval with Sequence Compressive Vectors",
author = "Park, Cheoneum and
Jeong, Seohyeong and
Kim, Minsang and
Lim, KyungTae and
Lee, Yong-Hun",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven and
Darwish, Kareem and
Agarwal, Apoorv",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics: Industry Track",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-industry.63/",
pages = "760--770",
abstract = "Recent advances in language models (LMs) has driven progress in information retrieval (IR), effectively extracting semantically relevant information. However, they face challenges in balancing computational costs with deeper query-document interactions. To tackle this, we present two mechanisms: 1) a light and effective multi-vector retrieval with sequence compression vectors, dubbed SCV and 2) coarse-to-fine vector search. The strengths of SCV stems from its application of span compressive vectors for scoring. By employing a non-linear operation to examine every token in the document, we abstract these into a span-level representation. These vectors effectively reduce the document`s dimensional representation, enabling the model to engage comprehensively with tokens across the entire collection of documents, rather than the subset retrieved by Approximate Nearest Neighbor. Therefore, our framework performs a coarse single vector search during the inference stage and conducts a fine-grained multi-vector search end-to-end. This approach effectively reduces the cost required for search. We empirically show that SCV achieves the fastest latency compared to other state-of-the-art models and can obtain competitive performance on both in-domain and out-of-domain benchmark datasets."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2025-scv">
<titleInfo>
<title>SCV: Light and Effective Multi-Vector Retrieval with Sequence Compressive Vectors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cheoneum</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seohyeong</namePart>
<namePart type="family">Jeong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minsang</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">KyungTae</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong-Hun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Apoorv</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in language models (LMs) has driven progress in information retrieval (IR), effectively extracting semantically relevant information. However, they face challenges in balancing computational costs with deeper query-document interactions. To tackle this, we present two mechanisms: 1) a light and effective multi-vector retrieval with sequence compression vectors, dubbed SCV and 2) coarse-to-fine vector search. The strengths of SCV stems from its application of span compressive vectors for scoring. By employing a non-linear operation to examine every token in the document, we abstract these into a span-level representation. These vectors effectively reduce the document‘s dimensional representation, enabling the model to engage comprehensively with tokens across the entire collection of documents, rather than the subset retrieved by Approximate Nearest Neighbor. Therefore, our framework performs a coarse single vector search during the inference stage and conducts a fine-grained multi-vector search end-to-end. This approach effectively reduces the cost required for search. We empirically show that SCV achieves the fastest latency compared to other state-of-the-art models and can obtain competitive performance on both in-domain and out-of-domain benchmark datasets.</abstract>
<identifier type="citekey">park-etal-2025-scv</identifier>
<location>
<url>https://aclanthology.org/2025.coling-industry.63/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>760</start>
<end>770</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SCV: Light and Effective Multi-Vector Retrieval with Sequence Compressive Vectors
%A Park, Cheoneum
%A Jeong, Seohyeong
%A Kim, Minsang
%A Lim, KyungTae
%A Lee, Yong-Hun
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%Y Darwish, Kareem
%Y Agarwal, Apoorv
%S Proceedings of the 31st International Conference on Computational Linguistics: Industry Track
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F park-etal-2025-scv
%X Recent advances in language models (LMs) has driven progress in information retrieval (IR), effectively extracting semantically relevant information. However, they face challenges in balancing computational costs with deeper query-document interactions. To tackle this, we present two mechanisms: 1) a light and effective multi-vector retrieval with sequence compression vectors, dubbed SCV and 2) coarse-to-fine vector search. The strengths of SCV stems from its application of span compressive vectors for scoring. By employing a non-linear operation to examine every token in the document, we abstract these into a span-level representation. These vectors effectively reduce the document‘s dimensional representation, enabling the model to engage comprehensively with tokens across the entire collection of documents, rather than the subset retrieved by Approximate Nearest Neighbor. Therefore, our framework performs a coarse single vector search during the inference stage and conducts a fine-grained multi-vector search end-to-end. This approach effectively reduces the cost required for search. We empirically show that SCV achieves the fastest latency compared to other state-of-the-art models and can obtain competitive performance on both in-domain and out-of-domain benchmark datasets.
%U https://aclanthology.org/2025.coling-industry.63/
%P 760-770
Markdown (Informal)
[SCV: Light and Effective Multi-Vector Retrieval with Sequence Compressive Vectors](https://aclanthology.org/2025.coling-industry.63/) (Park et al., COLING 2025)
ACL