<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jung-wang-2026-uncertainty">
    <titleInfo>
        <title>Uncertainty-Aware Hybrid Retrieval for Long-Document RAG</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hoin</namePart>
        <namePart type="family">Jung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaoqian</namePart>
        <namePart type="family">Wang</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>Retrieval-augmented generation (RAG) depends critically on the quality and granularity of retrieved evidence. Large retrieval units preserve context but often introduce irrelevant content, which can dilute answer-bearing evidence and worsen long context utilization. Fine-grained units are more compact, but they may be difficult to retrieve reliably because short chunks can lack semantic, lexical, or bridging cues needed to match the query. We propose **Uncertainty-aware Multi-Granularity RAG (UMG-RAG)**, a training-free hybrid retrieval framework that adapts retrieval across chunk granularities based on query-specific reliability estimates. Instead of training a new retriever or modifying the generator, UMG-RAG uses existing dense and sparse retrievers as complementary experts across multiple chunk granularities. For each query, it converts each expert-granularity score list into an evidence distribution, estimates reliability from distribution entropy, and fuses candidates according to query-specific semantic, lexical, and granularity confidence. We further introduce **UMGP-RAG**, a parent promotion variant that uses fine-grained hits to locate relevant evidence while returning broader non-redundant parent chunks for local coherence. Experiments on question answering benchmarks show that uncertainty-aware fusion and parent promotion improve generation quality in a training-free, plug-and-play retrieval pipeline.</abstract>
    <identifier type="citekey">jung-wang-2026-uncertainty</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2104/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>47893</start>
            <end>47911</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Uncertainty-Aware Hybrid Retrieval for Long-Document RAG
%A Jung, Hoin
%A Wang, Xiaoqian
%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 jung-wang-2026-uncertainty
%X Retrieval-augmented generation (RAG) depends critically on the quality and granularity of retrieved evidence. Large retrieval units preserve context but often introduce irrelevant content, which can dilute answer-bearing evidence and worsen long context utilization. Fine-grained units are more compact, but they may be difficult to retrieve reliably because short chunks can lack semantic, lexical, or bridging cues needed to match the query. We propose **Uncertainty-aware Multi-Granularity RAG (UMG-RAG)**, a training-free hybrid retrieval framework that adapts retrieval across chunk granularities based on query-specific reliability estimates. Instead of training a new retriever or modifying the generator, UMG-RAG uses existing dense and sparse retrievers as complementary experts across multiple chunk granularities. For each query, it converts each expert-granularity score list into an evidence distribution, estimates reliability from distribution entropy, and fuses candidates according to query-specific semantic, lexical, and granularity confidence. We further introduce **UMGP-RAG**, a parent promotion variant that uses fine-grained hits to locate relevant evidence while returning broader non-redundant parent chunks for local coherence. Experiments on question answering benchmarks show that uncertainty-aware fusion and parent promotion improve generation quality in a training-free, plug-and-play retrieval pipeline.
%U https://aclanthology.org/2026.emnlp-main.2104/
%P 47893-47911

Markdown (Informal)

[Uncertainty-Aware Hybrid Retrieval for Long-Document RAG](https://aclanthology.org/2026.emnlp-main.2104/) (Jung & Wang, EMNLP 2026)

• Uncertainty-Aware Hybrid Retrieval for Long-Document RAG (Jung & Wang, EMNLP 2026)

ACL

• Hoin Jung and Xiaoqian Wang. 2026. Uncertainty-Aware Hybrid Retrieval for Long-Document RAG. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 47893–47911, Budapest, Hungary. Association for Computational Linguistics.