<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-crisislink">
    <titleInfo>
        <title>CrisisLink: Closing the Loop between Underspecified Crisis Posts and Humanitarian Coordination</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yuchen</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuze</namePart>
        <namePart type="family">Gao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bin</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jian</namePart>
        <namePart type="family">Su</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Farah</namePart>
        <namePart type="family">Benamara</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: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Pepa</namePart>
            <namePart type="family">Atanasova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gholamreza</namePart>
            <namePart type="family">Haffari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Minghan</namePart>
            <namePart type="family">Wang</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">979-8-89176-460-6</identifier>
    </relatedItem>
    <abstract>During disasters, social media becomes a critical channel for identifying urgent needs and mobilizing public and institutional response efforts. Prior crisis-informatics research has mainly focused on detecting or extracting actionable content from disaster-related posts. However, real-world humanitarian response requires structured and operationally complete records, while social media posts are often short, informal, and underspecified.\par In this work, we present CrisisLink, an LLM-based coordination system that transforms noisy crisis communications into structured crisis records. Unlike prior one-shot extraction systems, CrisisLink dynamically identifies missing operational fields and initiates clarification dialogues with users to repair incomplete records before downstream coordination. The system further grounds resources against a humanitarian taxonomy and supports partial, multi-item matching.\par Built on the CrisisNLP corpus spanning multiple disaster types, the system is evaluated through human-audited assessments, simulated dispatch workflows, and a pilot evaluation in which trained workers role-play poster replies through a live web-based response interface. Experimental results show that a single clarification round raises end-to-end Offer–Request matching accuracy from 74.0% to 88.3% (a ceiling estimate under full response)while reducing the manual triage burden on responders, demonstrating the potential of interactive LLM systems for real-world humanitarian coordination.</abstract>
    <identifier type="citekey">zhang-etal-2026-crisislink</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.205/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>3441</start>
            <end>3454</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CrisisLink: Closing the Loop between Underspecified Crisis Posts and Humanitarian Coordination
%A Zhang, Yuchen
%A Gao, Yuze
%A Chen, Bin
%A Su, Jian
%A Benamara, Farah
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F zhang-etal-2026-crisislink
%X During disasters, social media becomes a critical channel for identifying urgent needs and mobilizing public and institutional response efforts. Prior crisis-informatics research has mainly focused on detecting or extracting actionable content from disaster-related posts. However, real-world humanitarian response requires structured and operationally complete records, while social media posts are often short, informal, and underspecified.\par In this work, we present CrisisLink, an LLM-based coordination system that transforms noisy crisis communications into structured crisis records. Unlike prior one-shot extraction systems, CrisisLink dynamically identifies missing operational fields and initiates clarification dialogues with users to repair incomplete records before downstream coordination. The system further grounds resources against a humanitarian taxonomy and supports partial, multi-item matching.\par Built on the CrisisNLP corpus spanning multiple disaster types, the system is evaluated through human-audited assessments, simulated dispatch workflows, and a pilot evaluation in which trained workers role-play poster replies through a live web-based response interface. Experimental results show that a single clarification round raises end-to-end Offer–Request matching accuracy from 74.0% to 88.3% (a ceiling estimate under full response)while reducing the manual triage burden on responders, demonstrating the potential of interactive LLM systems for real-world humanitarian coordination.
%U https://aclanthology.org/2026.emnlp-industry.205/
%P 3441-3454

Markdown (Informal)

[CrisisLink: Closing the Loop between Underspecified Crisis Posts and Humanitarian Coordination](https://aclanthology.org/2026.emnlp-industry.205/) (Zhang et al., EMNLP 2026)

• CrisisLink: Closing the Loop between Underspecified Crisis Posts and Humanitarian Coordination (Zhang et al., EMNLP 2026)

ACL

• Yuchen Zhang, Yuze Gao, Bin Chen, Jian Su, and Farah Benamara. 2026. CrisisLink: Closing the Loop between Underspecified Crisis Posts and Humanitarian Coordination. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 3441–3454, Budapest, Hungary. Association for Computational Linguistics.