<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oh-kim-2026-repair">
    <titleInfo>
        <title>REPAIR: Resolving Long-Tail Confusion in Scientific Retrievers via Fact-Verified Iterative Refinement</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yerim</namePart>
        <namePart type="family">Oh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gunhee</namePart>
        <namePart type="family">Kim</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>Precise retrieval of scientific information is fundamentally constrained by long-tailed concepts and high fact-sensitivity of scientific corpora. These challenges often limit the effectiveness of dense retrievers and hallucination-prone LLM augmentation. To address this, we present REPAIR, a self-evolving data augmentation framework for scientific dense retrievers. REPAIR iteratively synthesizes training data to address knowledge gaps by cycling through diagnosis of long-tail concepts, API-guided evidence expansion, and differentiation via hard negative mining. This process effectively grounds retrieval in factual reality to resolve fine-grained distinctions. Extensive experiments demonstrate that REPAIR significantly outperforms 19 strong baselines on nine materials science and biomedical benchmarks. Our work highlights that diagnosing and factually augmenting data to long-tail deficits is essential for robust scientific retrieval.</abstract>
    <identifier type="citekey">oh-kim-2026-repair</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1204/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>27543</start>
            <end>27572</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T REPAIR: Resolving Long-Tail Confusion in Scientific Retrievers via Fact-Verified Iterative Refinement
%A Oh, Yerim
%A Kim, Gunhee
%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 oh-kim-2026-repair
%X Precise retrieval of scientific information is fundamentally constrained by long-tailed concepts and high fact-sensitivity of scientific corpora. These challenges often limit the effectiveness of dense retrievers and hallucination-prone LLM augmentation. To address this, we present REPAIR, a self-evolving data augmentation framework for scientific dense retrievers. REPAIR iteratively synthesizes training data to address knowledge gaps by cycling through diagnosis of long-tail concepts, API-guided evidence expansion, and differentiation via hard negative mining. This process effectively grounds retrieval in factual reality to resolve fine-grained distinctions. Extensive experiments demonstrate that REPAIR significantly outperforms 19 strong baselines on nine materials science and biomedical benchmarks. Our work highlights that diagnosing and factually augmenting data to long-tail deficits is essential for robust scientific retrieval.
%U https://aclanthology.org/2026.emnlp-main.1204/
%P 27543-27572

Markdown (Informal)

[REPAIR: Resolving Long-Tail Confusion in Scientific Retrievers via Fact-Verified Iterative Refinement](https://aclanthology.org/2026.emnlp-main.1204/) (Oh & Kim, EMNLP 2026)

• REPAIR: Resolving Long-Tail Confusion in Scientific Retrievers via Fact-Verified Iterative Refinement (Oh & Kim, EMNLP 2026)

ACL

• Yerim Oh and Gunhee Kim. 2026. REPAIR: Resolving Long-Tail Confusion in Scientific Retrievers via Fact-Verified Iterative Refinement. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 27543–27572, Budapest, Hungary. Association for Computational Linguistics.