@inproceedings{sakata-hirota-2026-structured,
title = "Structured Drafting and Evidence-Grounded Refinement for the {LT}4{CPR} 2026 Shared Task",
author = "Sakata, Wataru and
Hirota, Wataru",
editor = "Ticona, Belu and
Xia, Fei and
Lewis, William D. and
Anastasopoulos, Antonios",
booktitle = "Proceedings of the First Workshop on Language Technologies for Crisis Preparedness and Response",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.lt4cpr-1.13/",
pages = "141--155",
ISBN = "979-8-89176-450-7",
abstract = "Generating crisis situation reports from numerous short, redundant tweets requires both information organization and support from cited evidence. We present a system for the LT4CPR Shared Task that combines structured draft generation with bidirectional evidence-grounded refinement. Draft generation separates claim extraction, section-wise aggregation, report assembly, and summary generation. Refinement collects report-driven correction candidates and tweet-driven additions, verifies them against source tweets, and integrates accepted edits. Across all 23 cells covering two public development crises, our structured-generation configuration achieved a higher Main Score than direct generation (0.5308 vs. 0.4198). Adding bidirectional refinement slightly reduces Main Score to 0.5216 but increases the automatic NLI-based source-support metric for body bullets from 0.7925 to 0.8566. Our submission, combining both components, ranked first among the nine participating teams in the official test evaluation with a primary score of 0.682. A model-based audit of 50 randomly sampled modified body bullets judged 35 edits beneficial, eight equivalent, and seven detrimental, suggesting that bidirectional refinement improves statement quality in many edits. However, the audit and NLI disagree on individual improvements, suggesting that increases in the NLI metric should not be interpreted directly as equivalent gains in factual source support."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sakata-hirota-2026-structured">
<titleInfo>
<title>Structured Drafting and Evidence-Grounded Refinement for the LT4CPR 2026 Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wataru</namePart>
<namePart type="family">Sakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wataru</namePart>
<namePart type="family">Hirota</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>Generating crisis situation reports from numerous short, redundant tweets requires both information organization and support from cited evidence. We present a system for the LT4CPR Shared Task that combines structured draft generation with bidirectional evidence-grounded refinement. Draft generation separates claim extraction, section-wise aggregation, report assembly, and summary generation. Refinement collects report-driven correction candidates and tweet-driven additions, verifies them against source tweets, and integrates accepted edits. Across all 23 cells covering two public development crises, our structured-generation configuration achieved a higher Main Score than direct generation (0.5308 vs. 0.4198). Adding bidirectional refinement slightly reduces Main Score to 0.5216 but increases the automatic NLI-based source-support metric for body bullets from 0.7925 to 0.8566. Our submission, combining both components, ranked first among the nine participating teams in the official test evaluation with a primary score of 0.682. A model-based audit of 50 randomly sampled modified body bullets judged 35 edits beneficial, eight equivalent, and seven detrimental, suggesting that bidirectional refinement improves statement quality in many edits. However, the audit and NLI disagree on individual improvements, suggesting that increases in the NLI metric should not be interpreted directly as equivalent gains in factual source support.</abstract>
<identifier type="citekey">sakata-hirota-2026-structured</identifier>
<location>
<url>https://aclanthology.org/2026.lt4cpr-1.13/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>141</start>
<end>155</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Structured Drafting and Evidence-Grounded Refinement for the LT4CPR 2026 Shared Task
%A Sakata, Wataru
%A Hirota, Wataru
%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 sakata-hirota-2026-structured
%X Generating crisis situation reports from numerous short, redundant tweets requires both information organization and support from cited evidence. We present a system for the LT4CPR Shared Task that combines structured draft generation with bidirectional evidence-grounded refinement. Draft generation separates claim extraction, section-wise aggregation, report assembly, and summary generation. Refinement collects report-driven correction candidates and tweet-driven additions, verifies them against source tweets, and integrates accepted edits. Across all 23 cells covering two public development crises, our structured-generation configuration achieved a higher Main Score than direct generation (0.5308 vs. 0.4198). Adding bidirectional refinement slightly reduces Main Score to 0.5216 but increases the automatic NLI-based source-support metric for body bullets from 0.7925 to 0.8566. Our submission, combining both components, ranked first among the nine participating teams in the official test evaluation with a primary score of 0.682. A model-based audit of 50 randomly sampled modified body bullets judged 35 edits beneficial, eight equivalent, and seven detrimental, suggesting that bidirectional refinement improves statement quality in many edits. However, the audit and NLI disagree on individual improvements, suggesting that increases in the NLI metric should not be interpreted directly as equivalent gains in factual source support.
%U https://aclanthology.org/2026.lt4cpr-1.13/
%P 141-155
Markdown (Informal)
[Structured Drafting and Evidence-Grounded Refinement for the LT4CPR 2026 Shared Task](https://aclanthology.org/2026.lt4cpr-1.13/) (Sakata & Hirota, LT4CPR 2026)
ACL