<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dela-cruz-etal-2026-errors">
    <titleInfo>
        <title>From Errors to Precision: A Taxonomy-Guided Approach for LLM Flood Cause Extraction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jane</namePart>
        <namePart type="given">Arleth</namePart>
        <namePart type="family">dela Cruz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Iris</namePart>
        <namePart type="family">Hendrickx</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Martha</namePart>
        <namePart type="family">Larson</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 11th Workshop on Natural User-generated Text</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">JinYeong</namePart>
            <namePart type="family">Bak</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rob</namePart>
            <namePart type="family">van der Goot</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hyeju</namePart>
            <namePart type="family">Jang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Weerayut</namePart>
            <namePart type="family">Buaphet</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ramponi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Wei</namePart>
            <namePart type="family">Xu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ritter</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">979-8-89176-470-5</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) offer disaster risk management (DRM) practitioners a promising “plug-and-play” solution for information extraction on online media data. However, they can struggle with the strict precision required for identifying semantically and structurally complex disaster causes. We evaluated how off-the shelf LLMs extract causal information from flood-related texts and found a strong recall bias. To diagnose these errors, our primary contribution is a comprehensive, human-annotated qualitative error taxonomy using inductive and deductive coding. We identified specific linguistic traps, i.e., impact descriptions, background context, and subjective opinions, trigger over-extraction, indicating models have a patterned failure. As an exploratory second step, we apply this taxonomy to design an ablation study of prompt-based interventions using definitions and exclusions. Our results show that our approach successfully shifts models along the precision–recall trade-off, i.e., curbing over-extraction, improving precision and domain-specific F0.5-score for recall-biased models. We demonstrate that by leveraging qualitative error analysis, domain experts can not only characterize and refine off-the-shelf LLMs, but also navigate the tradeoffs of prompting.</abstract>
    <identifier type="citekey">dela-cruz-etal-2026-errors</identifier>
    <location>
        <url>https://aclanthology.org/2026.wnut-1.8/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>101</start>
            <end>116</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T From Errors to Precision: A Taxonomy-Guided Approach for LLM Flood Cause Extraction
%A dela Cruz, Jane Arleth
%A Hendrickx, Iris
%A Larson, Martha
%Y Bak, JinYeong
%Y van der Goot, Rob
%Y Jang, Hyeju
%Y Buaphet, Weerayut
%Y Ramponi, Alan
%Y Xu, Wei
%Y Ritter, Alan
%S Proceedings of the 11th Workshop on Natural User-generated Text
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-470-5
%F dela-cruz-etal-2026-errors
%X Large language models (LLMs) offer disaster risk management (DRM) practitioners a promising “plug-and-play” solution for information extraction on online media data. However, they can struggle with the strict precision required for identifying semantically and structurally complex disaster causes. We evaluated how off-the shelf LLMs extract causal information from flood-related texts and found a strong recall bias. To diagnose these errors, our primary contribution is a comprehensive, human-annotated qualitative error taxonomy using inductive and deductive coding. We identified specific linguistic traps, i.e., impact descriptions, background context, and subjective opinions, trigger over-extraction, indicating models have a patterned failure. As an exploratory second step, we apply this taxonomy to design an ablation study of prompt-based interventions using definitions and exclusions. Our results show that our approach successfully shifts models along the precision–recall trade-off, i.e., curbing over-extraction, improving precision and domain-specific F0.5-score for recall-biased models. We demonstrate that by leveraging qualitative error analysis, domain experts can not only characterize and refine off-the-shelf LLMs, but also navigate the tradeoffs of prompting.
%U https://aclanthology.org/2026.wnut-1.8/
%P 101-116

Markdown (Informal)

[From Errors to Precision: A Taxonomy-Guided Approach for LLM Flood Cause Extraction](https://aclanthology.org/2026.wnut-1.8/) (dela Cruz et al., WNUT 2026)

• From Errors to Precision: A Taxonomy-Guided Approach for LLM Flood Cause Extraction (dela Cruz et al., WNUT 2026)

ACL

• Jane Arleth dela Cruz, Iris Hendrickx, and Martha Larson. 2026. From Errors to Precision: A Taxonomy-Guided Approach for LLM Flood Cause Extraction. In Proceedings of the 11th Workshop on Natural User-generated Text, pages 101–116, Budapest, Hungary. Association for Computational Linguistics.