@inproceedings{fernandez-etal-2026-extracting,
title = "Extracting information on public water shortages using news media and {LLM}s: a pilot study in {S}weden",
author = "Fernandez, Jeanne and
Zahra, Shorouq and
Brito, Mariana Madruga de and
M{\r{a}}rd, Johanna",
editor = "Schimanski, Tobias and
Usmanova, Aida and
Morio, Gaku and
Ni, Jingwei and
Dutia, Kalyan and
Vaghefi, Seyed Saeid and
Stammbach, Dominik and
Leippold, Markus",
booktitle = "Proceedings of the 3rd Workshop on Natural Language Processing Meets Climate Change ({C}limate{NLP} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.climatenlp-1.7/",
pages = "99--115",
ISBN = "979-8-89176-465-1",
abstract = "Slow-onset events such as droughts lack a clearly defined onset, and systematic databases do not capture their impacts at fine scales. News reports can help fill this gap by providing information on how drought-driven water shortages affect communities and how authorities respond. Yet, extracting structured information from text remains challenging. Here, we use news articles and official public communications on water-saving recommendations and water-use restrictions in Sweden as a case study to benchmark LLMs for drought-related information extraction. We compare the proprietary GPT-5 series against three large open-access models (Llama3.3, Deepseek, and GPT-OSS) in extracting variables such as the date, location, and causes of water-saving measures. Using prompt engineering, structured outputs, and minimal post-processing, we evaluate performance using a test set of 210 manually annotated articles. The GPT-5 model series outperforms all open-access models across all variables. We find that, without task-specific fine-tuning, open-source models are sometimes outperformed by a keyword-based baseline, suggesting that general-purpose capabilities alone are insufficient for reliably extracting structured data. These findings underscore the challenges of monitoring water-shortage risks based on texts, particularly when extracting complex variables."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fernandez-etal-2026-extracting">
<titleInfo>
<title>Extracting information on public water shortages using news media and LLMs: a pilot study in Sweden</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jeanne</namePart>
<namePart type="family">Fernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shorouq</namePart>
<namePart type="family">Zahra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="given">Madruga</namePart>
<namePart type="given">de</namePart>
<namePart type="family">Brito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Mård</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 3rd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tobias</namePart>
<namePart type="family">Schimanski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Usmanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaku</namePart>
<namePart type="family">Morio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingwei</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalyan</namePart>
<namePart type="family">Dutia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seyed</namePart>
<namePart type="given">Saeid</namePart>
<namePart type="family">Vaghefi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="family">Stammbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Leippold</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">979-8-89176-465-1</identifier>
</relatedItem>
<abstract>Slow-onset events such as droughts lack a clearly defined onset, and systematic databases do not capture their impacts at fine scales. News reports can help fill this gap by providing information on how drought-driven water shortages affect communities and how authorities respond. Yet, extracting structured information from text remains challenging. Here, we use news articles and official public communications on water-saving recommendations and water-use restrictions in Sweden as a case study to benchmark LLMs for drought-related information extraction. We compare the proprietary GPT-5 series against three large open-access models (Llama3.3, Deepseek, and GPT-OSS) in extracting variables such as the date, location, and causes of water-saving measures. Using prompt engineering, structured outputs, and minimal post-processing, we evaluate performance using a test set of 210 manually annotated articles. The GPT-5 model series outperforms all open-access models across all variables. We find that, without task-specific fine-tuning, open-source models are sometimes outperformed by a keyword-based baseline, suggesting that general-purpose capabilities alone are insufficient for reliably extracting structured data. These findings underscore the challenges of monitoring water-shortage risks based on texts, particularly when extracting complex variables.</abstract>
<identifier type="citekey">fernandez-etal-2026-extracting</identifier>
<location>
<url>https://aclanthology.org/2026.climatenlp-1.7/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>99</start>
<end>115</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extracting information on public water shortages using news media and LLMs: a pilot study in Sweden
%A Fernandez, Jeanne
%A Zahra, Shorouq
%A Brito, Mariana Madruga de
%A Mård, Johanna
%Y Schimanski, Tobias
%Y Usmanova, Aida
%Y Morio, Gaku
%Y Ni, Jingwei
%Y Dutia, Kalyan
%Y Vaghefi, Seyed Saeid
%Y Stammbach, Dominik
%Y Leippold, Markus
%S Proceedings of the 3rd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-465-1
%F fernandez-etal-2026-extracting
%X Slow-onset events such as droughts lack a clearly defined onset, and systematic databases do not capture their impacts at fine scales. News reports can help fill this gap by providing information on how drought-driven water shortages affect communities and how authorities respond. Yet, extracting structured information from text remains challenging. Here, we use news articles and official public communications on water-saving recommendations and water-use restrictions in Sweden as a case study to benchmark LLMs for drought-related information extraction. We compare the proprietary GPT-5 series against three large open-access models (Llama3.3, Deepseek, and GPT-OSS) in extracting variables such as the date, location, and causes of water-saving measures. Using prompt engineering, structured outputs, and minimal post-processing, we evaluate performance using a test set of 210 manually annotated articles. The GPT-5 model series outperforms all open-access models across all variables. We find that, without task-specific fine-tuning, open-source models are sometimes outperformed by a keyword-based baseline, suggesting that general-purpose capabilities alone are insufficient for reliably extracting structured data. These findings underscore the challenges of monitoring water-shortage risks based on texts, particularly when extracting complex variables.
%U https://aclanthology.org/2026.climatenlp-1.7/
%P 99-115
Markdown (Informal)
[Extracting information on public water shortages using news media and LLMs: a pilot study in Sweden](https://aclanthology.org/2026.climatenlp-1.7/) (Fernandez et al., ClimateNLP 2026)
ACL