The Brittle Compass: Navigating LLM Prompt Sensitivity in Slovak Migration Media Discourse

Jaroslav Kopčan; Samuel Harvan; Marek Šuppa

The Brittle Compass: Navigating LLM Prompt Sensitivity in Slovak Migration Media Discourse

Jaroslav Kopčan, Samuel Harvan, Marek Suppa

Correct Metadata for

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

In this work, we present a case study that explores various tasks centered around the topic of migration in Slovak, a low-resource language, such as topic relevance and geographical relevance classification, and migration source/destination location term extraction. Our results demonstrate that native (Slovak)prompts yield a modest, task-dependent gain, while large models show significant robustness to prompt variations compared to their smaller counterparts. Analysis reveals that instructions(system or task) emerge as the most critical prompt component, more so than the examples sections, with task-specific performance benefits being more pronounced than overall language effects.

Anthology ID:: 2025.lowresnlp-1.10
Volume:: Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages
Month:: September
Year:: 2025
Address:: Varna, Bulgaria
Editors:: Ernesto Luis Estevanell-Valladares, Alicia Picazo-Izquierdo, Tharindu Ranasinghe, Besik Mikaberidze, Simon Ostermann, Daniil Gurgurov, Philipp Mueller, Claudia Borg, Marián Šimko
Venues:: LowResNLP | WS
SIG:
Publisher:: INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:: 88–101
Language:
URL:: https://aclanthology.org/2025.lowresnlp-1.10/
DOI:
Bibkey:
Cite (ACL):: Jaroslav Kopčan, Samuel Harvan, and Marek Suppa. 2025. The Brittle Compass: Navigating LLM Prompt Sensitivity in Slovak Migration Media Discourse. In Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages, pages 88–101, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):: The Brittle Compass: Navigating LLM Prompt Sensitivity in Slovak Migration Media Discourse (Kopčan et al., LowResNLP 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.lowresnlp-1.10.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{kopcan-etal-2025-brittle,
    title = "The Brittle Compass: Navigating {LLM} Prompt Sensitivity in {S}lovak Migration Media Discourse",
    author = "Kop{\v{c}}an, Jaroslav  and
      Harvan, Samuel  and
      Suppa, Marek",
    editor = "Estevanell-Valladares, Ernesto Luis  and
      Picazo-Izquierdo, Alicia  and
      Ranasinghe, Tharindu  and
      Mikaberidze, Besik  and
      Ostermann, Simon  and
      Gurgurov, Daniil  and
      Mueller, Philipp  and
      Borg, Claudia  and
      {\v{S}}imko, Mari{\'a}n",
    booktitle = "Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages",
    month = sep,
    year = "2025",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd., Shoumen, Bulgaria",
    url = "https://aclanthology.org/2025.lowresnlp-1.10/",
    pages = "88--101",
    abstract = "In this work, we present a case study that explores various tasks centered around the topic of migration in Slovak, a low-resource language, such as topic relevance and geographical relevance classification, and migration source/destination location term extraction. Our results demonstrate that native (Slovak)prompts yield a modest, task-dependent gain, while large models show significant robustness to prompt variations compared to their smaller counterparts. Analysis reveals that instructions(system or task) emerge as the most critical prompt component, more so than the examples sections, with task-specific performance benefits being more pronounced than overall language effects."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kopcan-etal-2025-brittle">
    <titleInfo>
        <title>The Brittle Compass: Navigating LLM Prompt Sensitivity in Slovak Migration Media Discourse</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jaroslav</namePart>
        <namePart type="family">Kopčan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Samuel</namePart>
        <namePart type="family">Harvan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marek</namePart>
        <namePart type="family">Suppa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ernesto</namePart>
            <namePart type="given">Luis</namePart>
            <namePart type="family">Estevanell-Valladares</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alicia</namePart>
            <namePart type="family">Picazo-Izquierdo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tharindu</namePart>
            <namePart type="family">Ranasinghe</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Besik</namePart>
            <namePart type="family">Mikaberidze</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Ostermann</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Daniil</namePart>
            <namePart type="family">Gurgurov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Philipp</namePart>
            <namePart type="family">Mueller</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Claudia</namePart>
            <namePart type="family">Borg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marián</namePart>
            <namePart type="family">Šimko</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this work, we present a case study that explores various tasks centered around the topic of migration in Slovak, a low-resource language, such as topic relevance and geographical relevance classification, and migration source/destination location term extraction. Our results demonstrate that native (Slovak)prompts yield a modest, task-dependent gain, while large models show significant robustness to prompt variations compared to their smaller counterparts. Analysis reveals that instructions(system or task) emerge as the most critical prompt component, more so than the examples sections, with task-specific performance benefits being more pronounced than overall language effects.</abstract>
    <identifier type="citekey">kopcan-etal-2025-brittle</identifier>
    <location>
        <url>https://aclanthology.org/2025.lowresnlp-1.10/</url>
    </location>
    <part>
        <date>2025-09</date>
        <extent unit="page">
            <start>88</start>
            <end>101</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T The Brittle Compass: Navigating LLM Prompt Sensitivity in Slovak Migration Media Discourse
%A Kopčan, Jaroslav
%A Harvan, Samuel
%A Suppa, Marek
%Y Estevanell-Valladares, Ernesto Luis
%Y Picazo-Izquierdo, Alicia
%Y Ranasinghe, Tharindu
%Y Mikaberidze, Besik
%Y Ostermann, Simon
%Y Gurgurov, Daniil
%Y Mueller, Philipp
%Y Borg, Claudia
%Y Šimko, Marián
%S Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F kopcan-etal-2025-brittle
%X In this work, we present a case study that explores various tasks centered around the topic of migration in Slovak, a low-resource language, such as topic relevance and geographical relevance classification, and migration source/destination location term extraction. Our results demonstrate that native (Slovak)prompts yield a modest, task-dependent gain, while large models show significant robustness to prompt variations compared to their smaller counterparts. Analysis reveals that instructions(system or task) emerge as the most critical prompt component, more so than the examples sections, with task-specific performance benefits being more pronounced than overall language effects.
%U https://aclanthology.org/2025.lowresnlp-1.10/
%P 88-101

Download as File

Markdown (Informal)

[The Brittle Compass: Navigating LLM Prompt Sensitivity in Slovak Migration Media Discourse](https://aclanthology.org/2025.lowresnlp-1.10/) (Kopčan et al., LowResNLP 2025)

The Brittle Compass: Navigating LLM Prompt Sensitivity in Slovak Migration Media Discourse (Kopčan et al., LowResNLP 2025)

ACL

Jaroslav Kopčan, Samuel Harvan, and Marek Suppa. 2025. The Brittle Compass: Navigating LLM Prompt Sensitivity in Slovak Migration Media Discourse. In Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages, pages 88–101, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.