<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2026-synapsehsg">
    <titleInfo>
        <title>SynapseHSG: One-Shot Hyper-Semantic Grounding for Long-Context Multimodal Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sherricane</namePart>
        <namePart type="given">Jiayu</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhijie</namePart>
        <namePart type="family">Shen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yongqiang</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaojun</namePart>
        <namePart type="family">Jing</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shuangyin</namePart>
        <namePart type="family">Li</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>Answering complex queries over long-context multimodal streams requires dynamically synthesizing asynchronous and heterogeneous evidence across extended temporal and logical spans. Existing approaches often rely on iterative Multimodal Retrieval-Augmented Generation (RAG), facing structural challenges from semantic and modality gaps as well as context bloat induced by multi-step retrieval. To address these challenges, we propose SynapseHSG, a decoupled one-shot grounding framework for long-context multimodal Question Answering. SynapseHSG introduces a hyper-semantic evidence organization method (named M2HSG) that constructs an offline graph index to align cross-modal evidence. During inference, we design a Semantic Decomposer to convert natural-language queries into graph-operable constraints. Guided by these constraints, SynapseHSG retrieves a compact query-anchored subgraph in one shot and linearizes it as structured evidence for a frozen generator. This avoids repeated LLM-driven retrieval while restricting trainable components to graph construction and query parsing. To support systematic evaluation, we introduce MM-ConfQA, a new long-context multimodal QA benchmark built from academic conference presentations. Experimental results on MM-ConfQA show that SynapseHSG improves grounded answer generation over strong multimodal and retrieval baselines, especially on dispersed-evidence questions, highlighting the value of pre-organized multimodal evidence over repeated search in raw heterogeneous contexts. We release the code and data to public.</abstract>
    <identifier type="citekey">xu-etal-2026-synapsehsg</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.206/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>4326</start>
            <end>4344</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SynapseHSG: One-Shot Hyper-Semantic Grounding for Long-Context Multimodal Question Answering
%A Xu, Sherricane Jiayu
%A Shen, Zhijie
%A Liu, Yongqiang
%A Jing, Xiaojun
%A Li, Shuangyin
%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 xu-etal-2026-synapsehsg
%X Answering complex queries over long-context multimodal streams requires dynamically synthesizing asynchronous and heterogeneous evidence across extended temporal and logical spans. Existing approaches often rely on iterative Multimodal Retrieval-Augmented Generation (RAG), facing structural challenges from semantic and modality gaps as well as context bloat induced by multi-step retrieval. To address these challenges, we propose SynapseHSG, a decoupled one-shot grounding framework for long-context multimodal Question Answering. SynapseHSG introduces a hyper-semantic evidence organization method (named M2HSG) that constructs an offline graph index to align cross-modal evidence. During inference, we design a Semantic Decomposer to convert natural-language queries into graph-operable constraints. Guided by these constraints, SynapseHSG retrieves a compact query-anchored subgraph in one shot and linearizes it as structured evidence for a frozen generator. This avoids repeated LLM-driven retrieval while restricting trainable components to graph construction and query parsing. To support systematic evaluation, we introduce MM-ConfQA, a new long-context multimodal QA benchmark built from academic conference presentations. Experimental results on MM-ConfQA show that SynapseHSG improves grounded answer generation over strong multimodal and retrieval baselines, especially on dispersed-evidence questions, highlighting the value of pre-organized multimodal evidence over repeated search in raw heterogeneous contexts. We release the code and data to public.
%U https://aclanthology.org/2026.findings-emnlp.206/
%P 4326-4344

Markdown (Informal)

[SynapseHSG: One-Shot Hyper-Semantic Grounding for Long-Context Multimodal Question Answering](https://aclanthology.org/2026.findings-emnlp.206/) (Xu et al., Findings 2026)

• SynapseHSG: One-Shot Hyper-Semantic Grounding for Long-Context Multimodal Question Answering (Xu et al., Findings 2026)

ACL

• Sherricane Jiayu Xu, Zhijie Shen, Yongqiang Liu, Xiaojun Jing, and Shuangyin Li. 2026. SynapseHSG: One-Shot Hyper-Semantic Grounding for Long-Context Multimodal Question Answering. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 4326–4344, Budapest, Hungary. Association for Computational Linguistics.