<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-triage">
    <titleInfo>
        <title>TRIAGE: Label-Free Hateful Video Detection with Boundary Mapping and Resolution</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Junyi</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qian</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jing</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yi</namePart>
        <namePart type="family">Zhang</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>Hateful video detection is essential for maintaining safe and trustworthy online platforms. Current state-of-the-art methods are predominantly trained in a supervised manner, which incurs substantial annotation costs as online video content continues to grow rapidly. Although recent label-free approaches have shown promising progress, they still suffer from an effectiveness–efficiency trade-off, lagging behind supervised methods while requiring considerable computational resources. To address this limitation, we propose TRIAGE, a coarse-to-fine label-free detection framework that first localizes a boundary region and then progressively refines the cases within it. The framework introduces two core designs. The Boundary Mapper uses a lightweight MLLM to efficiently localize a boundary region, finalizing cases outside this region while retaining ambiguous hard cases for further reasoning. The Adaptive Boundary Resolver then queries diverse stronger MLLMs sequentially, resolves cases within the boundary region through Bayesian sequential updates, and terminates once sufficient evidence is accumulated. Across four public datasets, improves accuracy over the best label-free/few-shot baseline by 2.5–8.7 points, reduces parameter-weighted inference cost by at least 2.0, and outperforms the best supervised baseline on three datasets. Code is available at https://github.com/JunyiChen-ai/TRIAGE.</abstract>
    <identifier type="citekey">chen-etal-2026-triage</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1696/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>38600</start>
            <end>38621</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TRIAGE: Label-Free Hateful Video Detection with Boundary Mapping and Resolution
%A Chen, Junyi
%A Liu, Qian
%A Sun, Jing
%A Zhang, Yi
%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 chen-etal-2026-triage
%X Hateful video detection is essential for maintaining safe and trustworthy online platforms. Current state-of-the-art methods are predominantly trained in a supervised manner, which incurs substantial annotation costs as online video content continues to grow rapidly. Although recent label-free approaches have shown promising progress, they still suffer from an effectiveness–efficiency trade-off, lagging behind supervised methods while requiring considerable computational resources. To address this limitation, we propose TRIAGE, a coarse-to-fine label-free detection framework that first localizes a boundary region and then progressively refines the cases within it. The framework introduces two core designs. The Boundary Mapper uses a lightweight MLLM to efficiently localize a boundary region, finalizing cases outside this region while retaining ambiguous hard cases for further reasoning. The Adaptive Boundary Resolver then queries diverse stronger MLLMs sequentially, resolves cases within the boundary region through Bayesian sequential updates, and terminates once sufficient evidence is accumulated. Across four public datasets, improves accuracy over the best label-free/few-shot baseline by 2.5–8.7 points, reduces parameter-weighted inference cost by at least 2.0, and outperforms the best supervised baseline on three datasets. Code is available at https://github.com/JunyiChen-ai/TRIAGE.
%U https://aclanthology.org/2026.emnlp-main.1696/
%P 38600-38621

Markdown (Informal)

[TRIAGE: Label-Free Hateful Video Detection with Boundary Mapping and Resolution](https://aclanthology.org/2026.emnlp-main.1696/) (Chen et al., EMNLP 2026)

• TRIAGE: Label-Free Hateful Video Detection with Boundary Mapping and Resolution (Chen et al., EMNLP 2026)

ACL

• Junyi Chen, Qian Liu, Jing Sun, and Yi Zhang. 2026. TRIAGE: Label-Free Hateful Video Detection with Boundary Mapping and Resolution. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 38600–38621, Budapest, Hungary. Association for Computational Linguistics.