@inproceedings{kuo-etal-2025-mmlf,
title = "{MMLF}: Multi-query Multi-passage Late Fusion Retrieval",
author = "Kuo, Yuan-Ching and
Yu, Yi and
Chen, Chih-Ming and
Wang, Chuan-Ju",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.367/",
doi = "10.18653/v1/2025.findings-naacl.367",
pages = "6587--6598",
ISBN = "979-8-89176-195-7",
abstract = "Leveraging large language models (LLMs) for query expansion has proven highly effective across diverse tasks and languages. Yet, challenges remain in optimizing query formatting and prompting, often with less focus on handling retrieval results. In this paper, we introduce Multi-query Multi-passage Late Fusion (MMLF), a straightforward yet potent pipeline that generates sub-queries, expands them into pseudo-documents, retrieves them individually, and aggregates results using reciprocal rank fusion. Our experiments demonstrate that MMLF exhibits superior performance across five BEIR benchmark datasets, achieving an average improvement of 4{\%} and a maximum gain of up to 8{\%} in both Recall@1k and nDCG@10 compared to state of the art across BEIR information retrieval datasets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kuo-etal-2025-mmlf">
<titleInfo>
<title>MMLF: Multi-query Multi-passage Late Fusion Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuan-Ching</namePart>
<namePart type="family">Kuo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chih-Ming</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuan-Ju</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>Leveraging large language models (LLMs) for query expansion has proven highly effective across diverse tasks and languages. Yet, challenges remain in optimizing query formatting and prompting, often with less focus on handling retrieval results. In this paper, we introduce Multi-query Multi-passage Late Fusion (MMLF), a straightforward yet potent pipeline that generates sub-queries, expands them into pseudo-documents, retrieves them individually, and aggregates results using reciprocal rank fusion. Our experiments demonstrate that MMLF exhibits superior performance across five BEIR benchmark datasets, achieving an average improvement of 4% and a maximum gain of up to 8% in both Recall@1k and nDCG@10 compared to state of the art across BEIR information retrieval datasets.</abstract>
<identifier type="citekey">kuo-etal-2025-mmlf</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.367</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.367/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>6587</start>
<end>6598</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MMLF: Multi-query Multi-passage Late Fusion Retrieval
%A Kuo, Yuan-Ching
%A Yu, Yi
%A Chen, Chih-Ming
%A Wang, Chuan-Ju
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F kuo-etal-2025-mmlf
%X Leveraging large language models (LLMs) for query expansion has proven highly effective across diverse tasks and languages. Yet, challenges remain in optimizing query formatting and prompting, often with less focus on handling retrieval results. In this paper, we introduce Multi-query Multi-passage Late Fusion (MMLF), a straightforward yet potent pipeline that generates sub-queries, expands them into pseudo-documents, retrieves them individually, and aggregates results using reciprocal rank fusion. Our experiments demonstrate that MMLF exhibits superior performance across five BEIR benchmark datasets, achieving an average improvement of 4% and a maximum gain of up to 8% in both Recall@1k and nDCG@10 compared to state of the art across BEIR information retrieval datasets.
%R 10.18653/v1/2025.findings-naacl.367
%U https://aclanthology.org/2025.findings-naacl.367/
%U https://doi.org/10.18653/v1/2025.findings-naacl.367
%P 6587-6598
Markdown (Informal)
[MMLF: Multi-query Multi-passage Late Fusion Retrieval](https://aclanthology.org/2025.findings-naacl.367/) (Kuo et al., Findings 2025)
ACL
- Yuan-Ching Kuo, Yi Yu, Chih-Ming Chen, and Chuan-Ju Wang. 2025. MMLF: Multi-query Multi-passage Late Fusion Retrieval. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 6587–6598, Albuquerque, New Mexico. Association for Computational Linguistics.