@inproceedings{singh-etal-2026-splade,
title = "{SPLADE}-{COVER}: Coverage-Aware Representations for Learned Sparse Retrieval",
author = "Singh, Siddharth AK and
Yang, Eugene and
Lawrie, Dawn and
Adriaanse, Trevor and
Yates, Andrew",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2695/",
pages = "61302--61312",
ISBN = "979-8-89176-459-0",
abstract = "Long-form retrieval tasks such as report generation, multi-document summarization, and retrieval-augmented generation require systems to surface evidence covering multiple aspects (subtopics) of a complex query. Existing approaches to information coverage typically fall into two families: (1) methods such as Maximum Marginal Relevance (MMR) that rerank initial retrievals using document-similarity heuristics, and (2) expansion-based methods that invoke large language models at query time to produce subqueries, pseudo-answers, or expanded keywords. We propose SPLADE-COVER, a learned sparse retrieval model whose expansion mechanism is trained to be coverage-aware. SPLADE-COVER inherits the SPLADE-v3 architecture but is trained with an objective that distills multi-aspect subquery supervision into a single sparse representation, requiring no language-model invocation or reranking at query time. On benchmarks with nugget-level judgments, SPLADE-COVER often improves over its base model as measured by both information coverage metrics and relevance metrics, at a fraction of the query-time cost of generation-based methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-etal-2026-splade">
<titleInfo>
<title>SPLADE-COVER: Coverage-Aware Representations for Learned Sparse Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="given">AK</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugene</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawn</namePart>
<namePart type="family">Lawrie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Adriaanse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Yates</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Long-form retrieval tasks such as report generation, multi-document summarization, and retrieval-augmented generation require systems to surface evidence covering multiple aspects (subtopics) of a complex query. Existing approaches to information coverage typically fall into two families: (1) methods such as Maximum Marginal Relevance (MMR) that rerank initial retrievals using document-similarity heuristics, and (2) expansion-based methods that invoke large language models at query time to produce subqueries, pseudo-answers, or expanded keywords. We propose SPLADE-COVER, a learned sparse retrieval model whose expansion mechanism is trained to be coverage-aware. SPLADE-COVER inherits the SPLADE-v3 architecture but is trained with an objective that distills multi-aspect subquery supervision into a single sparse representation, requiring no language-model invocation or reranking at query time. On benchmarks with nugget-level judgments, SPLADE-COVER often improves over its base model as measured by both information coverage metrics and relevance metrics, at a fraction of the query-time cost of generation-based methods.</abstract>
<identifier type="citekey">singh-etal-2026-splade</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2695/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>61302</start>
<end>61312</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SPLADE-COVER: Coverage-Aware Representations for Learned Sparse Retrieval
%A Singh, Siddharth AK
%A Yang, Eugene
%A Lawrie, Dawn
%A Adriaanse, Trevor
%A Yates, Andrew
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F singh-etal-2026-splade
%X Long-form retrieval tasks such as report generation, multi-document summarization, and retrieval-augmented generation require systems to surface evidence covering multiple aspects (subtopics) of a complex query. Existing approaches to information coverage typically fall into two families: (1) methods such as Maximum Marginal Relevance (MMR) that rerank initial retrievals using document-similarity heuristics, and (2) expansion-based methods that invoke large language models at query time to produce subqueries, pseudo-answers, or expanded keywords. We propose SPLADE-COVER, a learned sparse retrieval model whose expansion mechanism is trained to be coverage-aware. SPLADE-COVER inherits the SPLADE-v3 architecture but is trained with an objective that distills multi-aspect subquery supervision into a single sparse representation, requiring no language-model invocation or reranking at query time. On benchmarks with nugget-level judgments, SPLADE-COVER often improves over its base model as measured by both information coverage metrics and relevance metrics, at a fraction of the query-time cost of generation-based methods.
%U https://aclanthology.org/2026.emnlp-main.2695/
%P 61302-61312
Markdown (Informal)
[SPLADE-COVER: Coverage-Aware Representations for Learned Sparse Retrieval](https://aclanthology.org/2026.emnlp-main.2695/) (Singh et al., EMNLP 2026)
ACL