<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2026-evaluating">
    <titleInfo>
        <title>Evaluating the Adaptability of Large Language Models to Linguistic Variation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ziyan</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marina</namePart>
        <namePart type="family">Seghier</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alice</namePart>
        <namePart type="family">Millour</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Carlos-Emiliano</namePart>
        <namePart type="family">Gonzalez-Gallardo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jean-Yves</namePart>
        <namePart type="family">Antoine</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Large language models (LLMs) are often assumed to generalize easily across linguistic contexts, yet their ability to adapt to genre variation remains underexplored. This study examines that question through a French Named Entity Recognition (NER) task conducted on NEM.fr, a multi-genre corpus annotated with gold named entities (NEs) spanning 11 text types, from juridical and encyclopedic prose to poetry, political speech, and online discourse. We evaluate the reasoning-oriented model DeepSeek R1 across six prompting configurations (zero-, one-, and few-shot, with and without chain-of-thought reasoning), while keeping the annotation scheme, prompting format, and evaluation pipeline constant to isolate the role of genre. Performance is measured using both strict and fuzzy F1-based metrics. The results show that prompting choices have little effect once the model has learned the task format, but that genre differences strongly influence outcomes: fuzzy F1 scores range from about 0.85 in formal genres to below 0.20 in informal ones. Even under tightly controlled conditions, LLM behaviour proves highly sensitive to textual regularity and stylistic variation, highlighting genre as a key factor in assessing model robustness.</abstract>
    <identifier type="citekey">xu-etal-2026-evaluating</identifier>
    <identifier type="doi">10.63317/57bpwacmcpr2</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.183/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>2334</start>
            <end>2343</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Evaluating the Adaptability of Large Language Models to Linguistic Variation
%A Xu, Ziyan
%A Seghier, Marina
%A Millour, Alice
%A Gonzalez-Gallardo, Carlos-Emiliano
%A Antoine, Jean-Yves
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F xu-etal-2026-evaluating
%X Large language models (LLMs) are often assumed to generalize easily across linguistic contexts, yet their ability to adapt to genre variation remains underexplored. This study examines that question through a French Named Entity Recognition (NER) task conducted on NEM.fr, a multi-genre corpus annotated with gold named entities (NEs) spanning 11 text types, from juridical and encyclopedic prose to poetry, political speech, and online discourse. We evaluate the reasoning-oriented model DeepSeek R1 across six prompting configurations (zero-, one-, and few-shot, with and without chain-of-thought reasoning), while keeping the annotation scheme, prompting format, and evaluation pipeline constant to isolate the role of genre. Performance is measured using both strict and fuzzy F1-based metrics. The results show that prompting choices have little effect once the model has learned the task format, but that genre differences strongly influence outcomes: fuzzy F1 scores range from about 0.85 in formal genres to below 0.20 in informal ones. Even under tightly controlled conditions, LLM behaviour proves highly sensitive to textual regularity and stylistic variation, highlighting genre as a key factor in assessing model robustness.
%R 10.63317/57bpwacmcpr2
%U https://aclanthology.org/2026.lrec-1.183/
%U https://doi.org/10.63317/57bpwacmcpr2
%P 2334-2343

Markdown (Informal)

[Evaluating the Adaptability of Large Language Models to Linguistic Variation](https://aclanthology.org/2026.lrec-1.183/) (Xu et al., LREC 2026)

• Evaluating the Adaptability of Large Language Models to Linguistic Variation (Xu et al., LREC 2026)

ACL

• Ziyan Xu, Marina Seghier, Alice Millour, Carlos-Emiliano Gonzalez-Gallardo, and Jean-Yves Antoine. 2026. Evaluating the Adaptability of Large Language Models to Linguistic Variation. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 2334–2343, Palma de Mallorca, Spain. ELRA Language Resource Association.