<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vast-etal-2026-mice">
    <titleInfo>
        <title>MICE: Minimal Interaction Cross-Encoders for efficient Re-ranking</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mathias</namePart>
        <namePart type="family">Vast</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Victor</namePart>
        <namePart type="family">Morand</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Josiane</namePart>
        <namePart type="family">Mothe</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Benjamin</namePart>
        <namePart type="family">Piwowarski</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>In Information Retrieval (IR), cross-encoders deliver state-of-the-art ranking effectiveness but have a high inference cost, limiting their use to second-stage re-rankers. Prior work has addressed this bottleneck from two largely separate directions: accelerating cross-encoder inference through attention sparsification, or improving first-stage retrieval effectiveness to alleviate the need of a re-ranker, using more complex models, e.g. late-interactions. In this work, we bridge these two directions through an in-depth analysis of cross-encoder internal mechanisms. By identifying and removing superfluous interactions, we derive MICE (Minimal Interaction Cross-Encoders), a new cross-encoder architecture that retains effectiveness while reducing computational overhead. Extensive evaluations show MICE retains most of the performances of its cross-encoder counterparts in-domain and matches or even exceeds it in out-of-domain, while reducing FLOPs down to 2.5 times.</abstract>
    <identifier type="citekey">vast-etal-2026-mice</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1736/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>39612</start>
            <end>39628</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MICE: Minimal Interaction Cross-Encoders for efficient Re-ranking
%A Vast, Mathias
%A Morand, Victor
%A Mothe, Josiane
%A Piwowarski, Benjamin
%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 vast-etal-2026-mice
%X In Information Retrieval (IR), cross-encoders deliver state-of-the-art ranking effectiveness but have a high inference cost, limiting their use to second-stage re-rankers. Prior work has addressed this bottleneck from two largely separate directions: accelerating cross-encoder inference through attention sparsification, or improving first-stage retrieval effectiveness to alleviate the need of a re-ranker, using more complex models, e.g. late-interactions. In this work, we bridge these two directions through an in-depth analysis of cross-encoder internal mechanisms. By identifying and removing superfluous interactions, we derive MICE (Minimal Interaction Cross-Encoders), a new cross-encoder architecture that retains effectiveness while reducing computational overhead. Extensive evaluations show MICE retains most of the performances of its cross-encoder counterparts in-domain and matches or even exceeds it in out-of-domain, while reducing FLOPs down to 2.5 times.
%U https://aclanthology.org/2026.emnlp-main.1736/
%P 39612-39628

Markdown (Informal)

[MICE: Minimal Interaction Cross-Encoders for efficient Re-ranking](https://aclanthology.org/2026.emnlp-main.1736/) (Vast et al., EMNLP 2026)

• MICE: Minimal Interaction Cross-Encoders for efficient Re-ranking (Vast et al., EMNLP 2026)

ACL

• Mathias Vast, Victor Morand, Josiane Mothe, and Benjamin Piwowarski. 2026. MICE: Minimal Interaction Cross-Encoders for efficient Re-ranking. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 39612–39628, Budapest, Hungary. Association for Computational Linguistics.