<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-park-2026-scone">
    <titleInfo>
        <title>SCoNE : Selective Context-aware Neuron Editing for Robust Retrieval-Augmented Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chaewon</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seo</namePart>
        <namePart type="given">Yeon</namePart>
        <namePart type="family">Park</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">Junyi</namePart>
            <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>Retrieval-Augmented Generation (RAG) is highly sensitive to retrieval noise: when retrieved documents mix informative and irrelevant context, LLMs are easily distracted, leading to hallucinations. To overcome this, we propose SCoNE (Selective Context-aware Neuron Editing), a training-free model editing approach that improves retrieval noise robustness by selectively strengthening context-aware FFN neurons that are identified by both high attribution and high cross-input variability. SCoNE requires only a small number of mining samples, no fine-tuning, and no inference-time overhead. Across various knowledge-intensive question-answering benchmarks and two LLM backbones, SCoNE consistently outperforms competitive baseline methods. Our code is available at https://github.com/HYU-ARK-Lab/SCoNE.</abstract>
    <identifier type="citekey">kim-park-2026-scone</identifier>
    <identifier type="doi">10.18653/2026.emnlp-main.2126</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2126/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>48352</start>
            <end>48363</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SCoNE : Selective Context-aware Neuron Editing for Robust Retrieval-Augmented Generation
%A Kim, Chaewon
%A Park, Seo Yeon
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Junyi 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 kim-park-2026-scone
%X Retrieval-Augmented Generation (RAG) is highly sensitive to retrieval noise: when retrieved documents mix informative and irrelevant context, LLMs are easily distracted, leading to hallucinations. To overcome this, we propose SCoNE (Selective Context-aware Neuron Editing), a training-free model editing approach that improves retrieval noise robustness by selectively strengthening context-aware FFN neurons that are identified by both high attribution and high cross-input variability. SCoNE requires only a small number of mining samples, no fine-tuning, and no inference-time overhead. Across various knowledge-intensive question-answering benchmarks and two LLM backbones, SCoNE consistently outperforms competitive baseline methods. Our code is available at https://github.com/HYU-ARK-Lab/SCoNE.
%R 10.18653/2026.emnlp-main.2126
%U https://aclanthology.org/2026.emnlp-main.2126/
%U https://doi.org/10.18653/2026.emnlp-main.2126
%P 48352-48363

Markdown (Informal)

[SCoNE : Selective Context-aware Neuron Editing for Robust Retrieval-Augmented Generation](https://aclanthology.org/2026.emnlp-main.2126/) (Kim & Park, EMNLP 2026)

• SCoNE : Selective Context-aware Neuron Editing for Robust Retrieval-Augmented Generation (Kim & Park, EMNLP 2026)

ACL

• Chaewon Kim and Seo Yeon Park. 2026. SCoNE : Selective Context-aware Neuron Editing for Robust Retrieval-Augmented Generation. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 48352–48363, Budapest, Hungary. Association for Computational Linguistics.