<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choi-etal-2026-duoprag">
    <titleInfo>
        <title>DuoPRAG: Rank-Disentangled and Gated Knowledge-Reasoning Fusion</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nakhyeon</namePart>
        <namePart type="family">Choi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cheoneum</namePart>
        <namePart type="family">Park</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seung-Hoon</namePart>
        <namePart type="family">Na</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>We rethink parametric retrieval-augmented generation with DuoPRAG, which integrates knowledge and reasoning capabilities through rank-disentangled and gated Low-Rank Adaptation (LoRA) composition. Existing parametric RAG methods encode document knowledge into LoRA parameters while leaving reasoning to be supplied through lexical chain-of-thought (CoT) prompting. This introduces three failure modes in outputs and contradicts the prompt-independent inference that parametric RAG aims to achieve. DuoPRAG parameterizes knowledge and reasoning into disentangled LoRA adapters, fused through a learnable mask and rank-specific gates. We achieve state-of-the-art performance on multi-hop QA benchmarks, outperforming the strongest parametric RAG baseline while preserving the parametric inference framework. Our results demonstrate that jointly parameterizing knowledge and reasoning is a natural and effective extension of the parametric RAG paradigm. Our code is available at https://github.com/naknak-choi/DuoPRAG.</abstract>
    <identifier type="citekey">choi-etal-2026-duoprag</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.413/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>9465</start>
            <end>9489</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DuoPRAG: Rank-Disentangled and Gated Knowledge-Reasoning Fusion
%A Choi, Nakhyeon
%A Park, Cheoneum
%A Na, Seung-Hoon
%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 choi-etal-2026-duoprag
%X We rethink parametric retrieval-augmented generation with DuoPRAG, which integrates knowledge and reasoning capabilities through rank-disentangled and gated Low-Rank Adaptation (LoRA) composition. Existing parametric RAG methods encode document knowledge into LoRA parameters while leaving reasoning to be supplied through lexical chain-of-thought (CoT) prompting. This introduces three failure modes in outputs and contradicts the prompt-independent inference that parametric RAG aims to achieve. DuoPRAG parameterizes knowledge and reasoning into disentangled LoRA adapters, fused through a learnable mask and rank-specific gates. We achieve state-of-the-art performance on multi-hop QA benchmarks, outperforming the strongest parametric RAG baseline while preserving the parametric inference framework. Our results demonstrate that jointly parameterizing knowledge and reasoning is a natural and effective extension of the parametric RAG paradigm. Our code is available at https://github.com/naknak-choi/DuoPRAG.
%U https://aclanthology.org/2026.emnlp-main.413/
%P 9465-9489

Markdown (Informal)

[DuoPRAG: Rank-Disentangled and Gated Knowledge-Reasoning Fusion](https://aclanthology.org/2026.emnlp-main.413/) (Choi et al., EMNLP 2026)

• DuoPRAG: Rank-Disentangled and Gated Knowledge-Reasoning Fusion (Choi et al., EMNLP 2026)

ACL

• Nakhyeon Choi, Cheoneum Park, and Seung-Hoon Na. 2026. DuoPRAG: Rank-Disentangled and Gated Knowledge-Reasoning Fusion. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 9465–9489, Budapest, Hungary. Association for Computational Linguistics.