<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2026-metabench">
    <titleInfo>
        <title>MetaBench: Benchmarking Two-Stage Reranking and Top-N Screening for Meta-Analyses</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yining</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Keke</namePart>
        <namePart type="family">Tang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Meilian</namePart>
        <namePart type="family">Chen</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>Meta-analyses are central to evidence-based medicine, but their production remains slow because reviewers must search PubMed and screen large candidate sets under PICOS eligibility constraints. We introduce MetaBench, a large-scale benchmark for early-stage PubMed title/abstract citation screening in meta-analysis study selection, formulated as a two-stage reranking and Top-N screening problem with effort-aware evaluation. MetaBench contains 7,801 PubMed meta-analyses, 120,930 PMID-linked included studies, and reproducible candidate pools with 4.2M unique title/abstract records constructed from replayed PubMed strategies or expert-validated training-only reconstructions. To improve evaluation fidelity, we introduce a coverage-based tiering protocol and reserve Tier 1 (1,297 topics) as a high-integrity test set. MetaBench evaluates candidate reranking with Recall/nDCG and Effort@R/NormEffort@R, and budgeted Top-N screening with sensitivity, specificity, precision, and F-scores. The main benchmark intentionally focuses on scalable title/abstract screening rather than full-text eligibility adjudication; PMCID metadata supports an auxiliary full-text track on an OA-constrained subset. Experiments show that MetaBench supervision improves dense reranking, reduces screening effort, and strengthens LLM-based inclusion decisions. An anonymized codebase and dataset sample are included with this ARR submission; the full dataset and codebase will be publicly released upon acceptance.</abstract>
    <identifier type="citekey">huang-etal-2026-metabench</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1179/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>27010</start>
            <end>27050</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MetaBench: Benchmarking Two-Stage Reranking and Top-N Screening for Meta-Analyses
%A Huang, Yining
%A Tang, Keke
%A Chen, Meilian
%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 huang-etal-2026-metabench
%X Meta-analyses are central to evidence-based medicine, but their production remains slow because reviewers must search PubMed and screen large candidate sets under PICOS eligibility constraints. We introduce MetaBench, a large-scale benchmark for early-stage PubMed title/abstract citation screening in meta-analysis study selection, formulated as a two-stage reranking and Top-N screening problem with effort-aware evaluation. MetaBench contains 7,801 PubMed meta-analyses, 120,930 PMID-linked included studies, and reproducible candidate pools with 4.2M unique title/abstract records constructed from replayed PubMed strategies or expert-validated training-only reconstructions. To improve evaluation fidelity, we introduce a coverage-based tiering protocol and reserve Tier 1 (1,297 topics) as a high-integrity test set. MetaBench evaluates candidate reranking with Recall/nDCG and Effort@R/NormEffort@R, and budgeted Top-N screening with sensitivity, specificity, precision, and F-scores. The main benchmark intentionally focuses on scalable title/abstract screening rather than full-text eligibility adjudication; PMCID metadata supports an auxiliary full-text track on an OA-constrained subset. Experiments show that MetaBench supervision improves dense reranking, reduces screening effort, and strengthens LLM-based inclusion decisions. An anonymized codebase and dataset sample are included with this ARR submission; the full dataset and codebase will be publicly released upon acceptance.
%U https://aclanthology.org/2026.emnlp-main.1179/
%P 27010-27050

Markdown (Informal)

[MetaBench: Benchmarking Two-Stage Reranking and Top-N Screening for Meta-Analyses](https://aclanthology.org/2026.emnlp-main.1179/) (Huang et al., EMNLP 2026)

• MetaBench: Benchmarking Two-Stage Reranking and Top-N Screening for Meta-Analyses (Huang et al., EMNLP 2026)

ACL

• Yining Huang, Keke Tang, and Meilian Chen. 2026. MetaBench: Benchmarking Two-Stage Reranking and Top-N Screening for Meta-Analyses. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 27010–27050, Budapest, Hungary. Association for Computational Linguistics.