@inproceedings{daoud-2026-storylines,
title = "Storylines, Not Snapshots: Error-Driven Prompting for Crisis Situation Reports at {LT}4{CPR} 2026",
author = "Daoud, Youcef",
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-1.12/",
pages = "134--140",
ISBN = "979-8-89176-450-7",
abstract = "We describe our system for the LT4CPR 2026 shared task on automatic situation report generation, where a structured report must be produced from a single stream of crisis-related posts. Each stream is processed independently with one request to an open-weight large language model, gpt-oss-120b, whose zero-shot prompt restricts subsection labels to the official vocabulary; a deterministic step assembles the report schema. We designed the prompt from an error analysis of the 140 training streams, which showed that the untuned model{'}s reports were mostly correct but incomplete: they held about a third as many bullets as the references, cited about 1.7 posts per bullet against 4.4, and never produced several subsections. Asking instead for one consolidated bullet per storyline, citing every supporting post, raised the official primary score of our submission from 0.611 to 0.650 on the test set, third of nine teams. Replacing the model with nemotron-3-super under the original prompt lowered the score to 0.534, a larger effect than the prompt revision. We also report a negative result: giving the model a typed tracker of the figures stated in the posts did not increase the figures it reported, although the tracker held nearly twice as many reference figures as the model stated"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="daoud-2026-storylines">
<titleInfo>
<title>Storylines, Not Snapshots: Error-Driven Prompting for Crisis Situation Reports at LT4CPR 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Youcef</namePart>
<namePart type="family">Daoud</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>We describe our system for the LT4CPR 2026 shared task on automatic situation report generation, where a structured report must be produced from a single stream of crisis-related posts. Each stream is processed independently with one request to an open-weight large language model, gpt-oss-120b, whose zero-shot prompt restricts subsection labels to the official vocabulary; a deterministic step assembles the report schema. We designed the prompt from an error analysis of the 140 training streams, which showed that the untuned model’s reports were mostly correct but incomplete: they held about a third as many bullets as the references, cited about 1.7 posts per bullet against 4.4, and never produced several subsections. Asking instead for one consolidated bullet per storyline, citing every supporting post, raised the official primary score of our submission from 0.611 to 0.650 on the test set, third of nine teams. Replacing the model with nemotron-3-super under the original prompt lowered the score to 0.534, a larger effect than the prompt revision. We also report a negative result: giving the model a typed tracker of the figures stated in the posts did not increase the figures it reported, although the tracker held nearly twice as many reference figures as the model stated</abstract>
<identifier type="citekey">daoud-2026-storylines</identifier>
<location>
<url>https://aclanthology.org/2026.lt4cpr-1.12/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>134</start>
<end>140</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Storylines, Not Snapshots: Error-Driven Prompting for Crisis Situation Reports at LT4CPR 2026
%A Daoud, Youcef
%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 daoud-2026-storylines
%X We describe our system for the LT4CPR 2026 shared task on automatic situation report generation, where a structured report must be produced from a single stream of crisis-related posts. Each stream is processed independently with one request to an open-weight large language model, gpt-oss-120b, whose zero-shot prompt restricts subsection labels to the official vocabulary; a deterministic step assembles the report schema. We designed the prompt from an error analysis of the 140 training streams, which showed that the untuned model’s reports were mostly correct but incomplete: they held about a third as many bullets as the references, cited about 1.7 posts per bullet against 4.4, and never produced several subsections. Asking instead for one consolidated bullet per storyline, citing every supporting post, raised the official primary score of our submission from 0.611 to 0.650 on the test set, third of nine teams. Replacing the model with nemotron-3-super under the original prompt lowered the score to 0.534, a larger effect than the prompt revision. We also report a negative result: giving the model a typed tracker of the figures stated in the posts did not increase the figures it reported, although the tracker held nearly twice as many reference figures as the model stated
%U https://aclanthology.org/2026.lt4cpr-1.12/
%P 134-140
Markdown (Informal)
[Storylines, Not Snapshots: Error-Driven Prompting for Crisis Situation Reports at LT4CPR 2026](https://aclanthology.org/2026.lt4cpr-1.12/) (Daoud, LT4CPR 2026)
ACL