<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-etal-2026-r01g">
    <titleInfo>
        <title>R01G-SR: Provenance-Preserving Selection over Complementary Evidence Views for Crisis Situation Report Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yuqiu</namePart>
        <namePart type="family">Gao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuanhe</namePart>
        <namePart type="family">Tian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaofei</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhentao</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yan</namePart>
        <namePart type="family">Song</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop on Language Technologies for Crisis Preparedness and Response</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Belu</namePart>
            <namePart type="family">Ticona</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Fei</namePart>
            <namePart type="family">Xia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">William</namePart>
            <namePart type="given">D</namePart>
            <namePart type="family">Lewis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonios</namePart>
            <namePart type="family">Anastasopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hengqin, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-450-7</identifier>
    </relatedItem>
    <abstract>Crisis situation report generation organizes evolving information into structured summaries with traceable supporting evidence. Generating these reports from noisy social-media streams requires balancing evidence completeness and concentration. Unfiltered evidence retains rare observations but includes competing material and remains subject to finite prompt budgets, while filtering and compression risk discarding useful sparse evidence. In this paper, we propose R01G-SR, a provenance-preserving approach that exploits complementary evidence views through whole-report selection. The approach generates two candidate reports using the same quantized 4B generator, presenting unfiltered chronological evidence to one route and filtered, near-duplicate-compressed evidence to the other. A logistic selector uses input- and report-derived features to choose one complete candidate without merging or rewriting reports, and a separate deterministic compliance layer enforces structural and evidence-ID requirements. Nested crisis-disjoint evaluation shows aggregate improvements over both fixed routes, and the official hidden-test evaluation shows improved report quality over the submitted compressed-route fallback. Analysis reveals larger selection gains on longer inputs and later windows, while early windows account for most remaining loss relative to selecting the better available candidate. These findings support evidence-view selection as a useful component of evidence-linked crisis reporting.</abstract>
    <identifier type="citekey">gao-etal-2026-r01g</identifier>
    <location>
        <url>https://aclanthology.org/2026.lt4cpr-1.16/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>177</start>
            <end>187</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T R01G-SR: Provenance-Preserving Selection over Complementary Evidence Views for Crisis Situation Report Generation
%A Gao, Yuqiu
%A Tian, Yuanhe
%A Chen, Xiaofei
%A Yang, Zhentao
%A Song, Yan
%Y Ticona, Belu
%Y Xia, Fei
%Y Lewis, William D.
%Y Anastasopoulos, Antonios
%S Proceedings of the First Workshop on Language Technologies for Crisis Preparedness and Response
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-450-7
%F gao-etal-2026-r01g
%X Crisis situation report generation organizes evolving information into structured summaries with traceable supporting evidence. Generating these reports from noisy social-media streams requires balancing evidence completeness and concentration. Unfiltered evidence retains rare observations but includes competing material and remains subject to finite prompt budgets, while filtering and compression risk discarding useful sparse evidence. In this paper, we propose R01G-SR, a provenance-preserving approach that exploits complementary evidence views through whole-report selection. The approach generates two candidate reports using the same quantized 4B generator, presenting unfiltered chronological evidence to one route and filtered, near-duplicate-compressed evidence to the other. A logistic selector uses input- and report-derived features to choose one complete candidate without merging or rewriting reports, and a separate deterministic compliance layer enforces structural and evidence-ID requirements. Nested crisis-disjoint evaluation shows aggregate improvements over both fixed routes, and the official hidden-test evaluation shows improved report quality over the submitted compressed-route fallback. Analysis reveals larger selection gains on longer inputs and later windows, while early windows account for most remaining loss relative to selecting the better available candidate. These findings support evidence-view selection as a useful component of evidence-linked crisis reporting.
%U https://aclanthology.org/2026.lt4cpr-1.16/
%P 177-187

Markdown (Informal)

[R01G-SR: Provenance-Preserving Selection over Complementary Evidence Views for Crisis Situation Report Generation](https://aclanthology.org/2026.lt4cpr-1.16/) (Gao et al., LT4CPR 2026)

• R01G-SR: Provenance-Preserving Selection over Complementary Evidence Views for Crisis Situation Report Generation (Gao et al., LT4CPR 2026)

ACL

• Yuqiu Gao, Yuanhe Tian, Xiaofei Chen, Zhentao Yang, and Yan Song. 2026. R01G-SR: Provenance-Preserving Selection over Complementary Evidence Views for Crisis Situation Report Generation. In Proceedings of the First Workshop on Language Technologies for Crisis Preparedness and Response, pages 177–187, Hengqin, China. Association for Computational Linguistics.