<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hwang-etal-2026-atom">
    <titleInfo>
        <title>Atom-RAG: Atomic Fact-Centric Retrieval for Multi-Hop Reasoning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Seok</namePart>
        <namePart type="given">Jun</namePart>
        <namePart type="family">Hwang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Soohyeong</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">JungHyoun</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jeonghyeon</namePart>
        <namePart type="family">Park</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yong</namePart>
        <namePart type="given">Suk</namePart>
        <namePart type="family">Choi</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Retrieval-Augmented Generation (RAG) en- hances large language models with ex- ternal knowledge but often suffers from query–evidence mismatch due to inappropriate retrieval granularity. Chunk-level retrieval can introduce substantial noise, while graph-based retrieval may suffer from overly fine-grained or densely connected structures that hinder effec- tive multi-hop reasoning. To address this issue, we propose Atom-RAG, a retrieval-augmented framework based on atomic fact–centric knowl- edge representation and granularity-aligned re- trieval. Atom-RAG represents documents as collections of atomic facts and aligns retrieval with the fine-grained information needs of com- plex queries. By decomposing queries into fact-level subqueries, the framework retrieves and aggregates evidence in a manner aligned with the information requirements of multi-hop reasoning, producing a compact and evidence- aligned context for generation. Experiments on benchmarks covering different reasoning depths show that Atom-RAG consistently out- performs strong iterative and graph-based RAG baselines, achieving improved multi-hop QA performance and stronger evidence retrieval. These results highlight the importance of align- ing the granularity of queries and retrieval units for reliable multi-hop reasoning within a unified retrieval pipeline. Code and data are available at https://github.com/cody628/ AtomRAG.</abstract>
    <identifier type="citekey">hwang-etal-2026-atom</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.2323</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.2323/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>49872</start>
            <end>49890</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Atom-RAG: Atomic Fact-Centric Retrieval for Multi-Hop Reasoning
%A Hwang, Seok Jun
%A Kim, Soohyeong
%A Kim, JungHyoun
%A Park, Jeonghyeon
%A Choi, Yong Suk
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F hwang-etal-2026-atom
%X Retrieval-Augmented Generation (RAG) en- hances large language models with ex- ternal knowledge but often suffers from query–evidence mismatch due to inappropriate retrieval granularity. Chunk-level retrieval can introduce substantial noise, while graph-based retrieval may suffer from overly fine-grained or densely connected structures that hinder effec- tive multi-hop reasoning. To address this issue, we propose Atom-RAG, a retrieval-augmented framework based on atomic fact–centric knowl- edge representation and granularity-aligned re- trieval. Atom-RAG represents documents as collections of atomic facts and aligns retrieval with the fine-grained information needs of com- plex queries. By decomposing queries into fact-level subqueries, the framework retrieves and aggregates evidence in a manner aligned with the information requirements of multi-hop reasoning, producing a compact and evidence- aligned context for generation. Experiments on benchmarks covering different reasoning depths show that Atom-RAG consistently out- performs strong iterative and graph-based RAG baselines, achieving improved multi-hop QA performance and stronger evidence retrieval. These results highlight the importance of align- ing the granularity of queries and retrieval units for reliable multi-hop reasoning within a unified retrieval pipeline. Code and data are available at https://github.com/cody628/ AtomRAG.
%R 10.18653/2026.findings-emnlp.2323
%U https://aclanthology.org/2026.findings-emnlp.2323/
%U https://doi.org/10.18653/2026.findings-emnlp.2323
%P 49872-49890

Markdown (Informal)

[Atom-RAG: Atomic Fact-Centric Retrieval for Multi-Hop Reasoning](https://aclanthology.org/2026.findings-emnlp.2323/) (Hwang et al., Findings 2026)

• Atom-RAG: Atomic Fact-Centric Retrieval for Multi-Hop Reasoning (Hwang et al., Findings 2026)

ACL

• Seok Jun Hwang, Soohyeong Kim, JungHyoun Kim, Jeonghyeon Park, and Yong Suk Choi. 2026. Atom-RAG: Atomic Fact-Centric Retrieval for Multi-Hop Reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 49872–49890, Budapest, Hungary. Association for Computational Linguistics.