<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yoon-etal-2025-square">
    <titleInfo>
        <title>SQUARE: Unsupervised Retrieval Adaptation via Synthetic Data</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jinsung</namePart>
        <namePart type="family">Yoon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junhao</namePart>
        <namePart type="family">Zeng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sercan</namePart>
        <namePart type="given">O</namePart>
        <namePart type="family">Arik</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-335-7</identifier>
    </relatedItem>
    <abstract>Pre-trained retrieval models often face challenges in zero-shot retrieval for knowledge-based question answering, as different tasks rely on different corpora. We introduce SQUARE (Synthetic QUery-based Adaptive REtrieval), a novel method for corpus-specific unsupervised retrieval customization. SQUARE leverages LLMs to generate grounded synthetic question-answer pairs from the corpus, which are then used to fine-tune the retriever. A filtering mechanism based on the synthetic answers is employed to ensure high quality of tuning data. Extensive experiments on various datasets demonstrate superior performance of SQUARE compared to zero-shot retrieval and other customization methods, highlighting the value of corpus adaptation for effective retrieval.</abstract>
    <identifier type="citekey">yoon-etal-2025-square</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-emnlp.384</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.384/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>7283</start>
            <end>7297</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SQUARE: Unsupervised Retrieval Adaptation via Synthetic Data
%A Yoon, Jinsung
%A Zeng, Junhao
%A Arik, Sercan O.
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F yoon-etal-2025-square
%X Pre-trained retrieval models often face challenges in zero-shot retrieval for knowledge-based question answering, as different tasks rely on different corpora. We introduce SQUARE (Synthetic QUery-based Adaptive REtrieval), a novel method for corpus-specific unsupervised retrieval customization. SQUARE leverages LLMs to generate grounded synthetic question-answer pairs from the corpus, which are then used to fine-tune the retriever. A filtering mechanism based on the synthetic answers is employed to ensure high quality of tuning data. Extensive experiments on various datasets demonstrate superior performance of SQUARE compared to zero-shot retrieval and other customization methods, highlighting the value of corpus adaptation for effective retrieval.
%R 10.18653/v1/2025.findings-emnlp.384
%U https://aclanthology.org/2025.findings-emnlp.384/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.384
%P 7283-7297

Markdown (Informal)

[SQUARE: Unsupervised Retrieval Adaptation via Synthetic Data](https://aclanthology.org/2025.findings-emnlp.384/) (Yoon et al., Findings 2025)

• SQUARE: Unsupervised Retrieval Adaptation via Synthetic Data (Yoon et al., Findings 2025)

ACL

• Jinsung Yoon, Junhao Zeng, and Sercan O Arik. 2025. SQUARE: Unsupervised Retrieval Adaptation via Synthetic Data. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 7283–7297, Suzhou, China. Association for Computational Linguistics.