<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ye-2026-aninter">
    <titleInfo>
        <title>AnInter: Anti-Interference Training for Long Context Retrieval</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lijie</namePart>
        <namePart type="family">Ye</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>Dense retrievers in Retrieval-Augmented Generation (RAG) have achieved substantial progress in semantic matching, but they remain limited in long context retrieval. In long context retrieval, target evidence often occupies only a small local span, while the remaining content acts as noise. We aim to improve long-document retrieval by enhancing retrievers’ anti-interference capability. Our contributions are threefold: (1) we construct the Anti-Interference Capability Benchmark (AICB) to evaluate retrievers’ anti-interference capability under controlled noise levels; (2) we propose anti-interference training as a short-text training path for improving long context retrieval; and (3) we train AnInter, a series of embedding models that are more robust to noisy long documents. Evaluation on LongEmbed shows that AnInter improves over its backbone by 16.4 points on average and achieves state-of-the-art performance on this challenging long context embedding benchmark. These results show that interference-aware training is a practical direction for improving long context retrieval.</abstract>
    <identifier type="citekey">ye-2026-aninter</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.214/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>4909</start>
            <end>4922</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T AnInter: Anti-Interference Training for Long Context Retrieval
%A Ye, Lijie
%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 ye-2026-aninter
%X Dense retrievers in Retrieval-Augmented Generation (RAG) have achieved substantial progress in semantic matching, but they remain limited in long context retrieval. In long context retrieval, target evidence often occupies only a small local span, while the remaining content acts as noise. We aim to improve long-document retrieval by enhancing retrievers’ anti-interference capability. Our contributions are threefold: (1) we construct the Anti-Interference Capability Benchmark (AICB) to evaluate retrievers’ anti-interference capability under controlled noise levels; (2) we propose anti-interference training as a short-text training path for improving long context retrieval; and (3) we train AnInter, a series of embedding models that are more robust to noisy long documents. Evaluation on LongEmbed shows that AnInter improves over its backbone by 16.4 points on average and achieves state-of-the-art performance on this challenging long context embedding benchmark. These results show that interference-aware training is a practical direction for improving long context retrieval.
%U https://aclanthology.org/2026.emnlp-main.214/
%P 4909-4922

Markdown (Informal)

[AnInter: Anti-Interference Training for Long Context Retrieval](https://aclanthology.org/2026.emnlp-main.214/) (Ye, EMNLP 2026)

• AnInter: Anti-Interference Training for Long Context Retrieval (Ye, EMNLP 2026)

ACL

• Lijie Ye. 2026. AnInter: Anti-Interference Training for Long Context Retrieval. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 4909–4922, Budapest, Hungary. Association for Computational Linguistics.