<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dejean-clinchant-2026-efficient">
    <titleInfo>
        <title>Efficient Listwise Reranking with Compressed Document Representations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hervé</namePart>
        <namePart type="family">Déjean</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stéphane</namePart>
        <namePart type="family">Clinchant</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>Reranking, the second stage of modern retrieval pipelines, is computationally expensive when performed by Large Language Models (LLMs). Existing efficiency-oriented approaches either rely on smaller models or restrict input length, both at the cost of effectiveness. Inspired by recent advances in soft document compression for retrieval-augmented generation (RAG), we introduce **RRK**, an efficient and effective listwise reranker that operates directly on multi-token compressed document representations rather than raw text. Trained via simple distillation from a strong teacher, RRK combines rich compressed representations with listwise reranking to deliver a highly efficient yet competitive system: despite its 7B-parameter backbone, it runs 5-20 faster than smaller rerankers (0.6-4B parameters) while matching or outperforming them in effectiveness. The advantage widens further on long-document benchmarks, where input compression yields the largest speedups.</abstract>
    <identifier type="citekey">dejean-clinchant-2026-efficient</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1336/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>30474</start>
            <end>30485</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Efficient Listwise Reranking with Compressed Document Representations
%A Déjean, Hervé
%A Clinchant, Stéphane
%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 dejean-clinchant-2026-efficient
%X Reranking, the second stage of modern retrieval pipelines, is computationally expensive when performed by Large Language Models (LLMs). Existing efficiency-oriented approaches either rely on smaller models or restrict input length, both at the cost of effectiveness. Inspired by recent advances in soft document compression for retrieval-augmented generation (RAG), we introduce **RRK**, an efficient and effective listwise reranker that operates directly on multi-token compressed document representations rather than raw text. Trained via simple distillation from a strong teacher, RRK combines rich compressed representations with listwise reranking to deliver a highly efficient yet competitive system: despite its 7B-parameter backbone, it runs 5-20 faster than smaller rerankers (0.6-4B parameters) while matching or outperforming them in effectiveness. The advantage widens further on long-document benchmarks, where input compression yields the largest speedups.
%U https://aclanthology.org/2026.emnlp-main.1336/
%P 30474-30485

Markdown (Informal)

[Efficient Listwise Reranking with Compressed Document Representations](https://aclanthology.org/2026.emnlp-main.1336/) (Déjean & Clinchant, EMNLP 2026)

• Efficient Listwise Reranking with Compressed Document Representations (Déjean & Clinchant, EMNLP 2026)

ACL

• Hervé Déjean and Stéphane Clinchant. 2026. Efficient Listwise Reranking with Compressed Document Representations. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 30474–30485, Budapest, Hungary. Association for Computational Linguistics.