<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="corallo-papotti-2026-parallel">
    <titleInfo>
        <title>Parallel Context-of-Experts Decoding for Retrieval Augmented Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Giulio</namePart>
        <namePart type="family">Corallo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Paolo</namePart>
        <namePart type="family">Papotti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-395-1</identifier>
    </relatedItem>
    <abstract>Retrieval Augmented Generation faces a trade-off: concatenating documents in a long prompt enables multi-document reasoning but creates prefill bottlenecks, while encoding document KV caches separately offers speed but breaks cross-document interaction. We propose Parallel Context-of-Experts Decoding (PCED), a training-free framework that shifts evidence aggregation from the attention mechanism to the decoding. PCED treats retrieved documents as isolated “experts”, synchronizing their predictions via a retrieval-aware extension of context-aware decoding. This approach recovers cross-document reasoning capabilities without constructing a shared attention across documents.</abstract>
    <identifier type="citekey">corallo-papotti-2026-parallel</identifier>
    <identifier type="doi">10.18653/v1/2026.findings-acl.1635</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.1635/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>32666</start>
            <end>32676</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Parallel Context-of-Experts Decoding for Retrieval Augmented Generation
%A Corallo, Giulio
%A Papotti, Paolo
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F corallo-papotti-2026-parallel
%X Retrieval Augmented Generation faces a trade-off: concatenating documents in a long prompt enables multi-document reasoning but creates prefill bottlenecks, while encoding document KV caches separately offers speed but breaks cross-document interaction. We propose Parallel Context-of-Experts Decoding (PCED), a training-free framework that shifts evidence aggregation from the attention mechanism to the decoding. PCED treats retrieved documents as isolated “experts”, synchronizing their predictions via a retrieval-aware extension of context-aware decoding. This approach recovers cross-document reasoning capabilities without constructing a shared attention across documents.
%R 10.18653/v1/2026.findings-acl.1635
%U https://aclanthology.org/2026.findings-acl.1635/
%U https://doi.org/10.18653/v1/2026.findings-acl.1635
%P 32666-32676

Markdown (Informal)

[Parallel Context-of-Experts Decoding for Retrieval Augmented Generation](https://aclanthology.org/2026.findings-acl.1635/) (Corallo & Papotti, Findings 2026)

• Parallel Context-of-Experts Decoding for Retrieval Augmented Generation (Corallo & Papotti, Findings 2026)

ACL

• Giulio Corallo and Paolo Papotti. 2026. Parallel Context-of-Experts Decoding for Retrieval Augmented Generation. In Findings of the Association for Computational Linguistics: ACL 2026, pages 32666–32676, San Diego, California, United States. Association for Computational Linguistics.