<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gutierrez-etal-2025-fsts">
    <titleInfo>
        <title>FSTs vs ICL: Generalisation in LLMs for an under-resourced language</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ximena</namePart>
        <namePart type="family">Gutierrez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mikel</namePart>
        <namePart type="given">Segura</namePart>
        <namePart type="family">Elizalde</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Victor</namePart>
        <namePart type="family">Mijangos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-335-7</identifier>
    </relatedItem>
    <abstract>LLMs have been widely adopted to tackle many traditional NLP tasks. Their effectiveness remains uncertain in scenarios where pre-trained models have limited prior knowledge of a language. In this work, we examine LLMs’ generalization in under-resourced settings through the task of orthographic normalization across Otomi language variants. We develop two approaches: a rule-based method using a finite-state transducer (FST) and an in-context learning (ICL) method that provides the model with string transduction examples. We compare the performance of FSTs and neural approaches in low-resource scenarios, providing insights into their potential and limitations. Our results show that while FSTs outperform LLMs in zero-shot settings, ICL enables LLMs to surpass FSTs, stressing the importance of combining linguistic expertise with machine learning in current approaches for low-resource scenarios.</abstract>
    <identifier type="citekey">gutierrez-etal-2025-fsts</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.867/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>15998</start>
            <end>16006</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T FSTs vs ICL: Generalisation in LLMs for an under-resourced language
%A Gutierrez, Ximena
%A Elizalde, Mikel Segura
%A Mijangos, Victor
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F gutierrez-etal-2025-fsts
%X LLMs have been widely adopted to tackle many traditional NLP tasks. Their effectiveness remains uncertain in scenarios where pre-trained models have limited prior knowledge of a language. In this work, we examine LLMs’ generalization in under-resourced settings through the task of orthographic normalization across Otomi language variants. We develop two approaches: a rule-based method using a finite-state transducer (FST) and an in-context learning (ICL) method that provides the model with string transduction examples. We compare the performance of FSTs and neural approaches in low-resource scenarios, providing insights into their potential and limitations. Our results show that while FSTs outperform LLMs in zero-shot settings, ICL enables LLMs to surpass FSTs, stressing the importance of combining linguistic expertise with machine learning in current approaches for low-resource scenarios.
%U https://aclanthology.org/2025.findings-emnlp.867/
%P 15998-16006

Markdown (Informal)

[FSTs vs ICL: Generalisation in LLMs for an under-resourced language](https://aclanthology.org/2025.findings-emnlp.867/) (Gutierrez et al., Findings 2025)

• FSTs vs ICL: Generalisation in LLMs for an under-resourced language (Gutierrez et al., Findings 2025)

ACL

• Ximena Gutierrez, Mikel Segura Elizalde, and Victor Mijangos. 2025. FSTs vs ICL: Generalisation in LLMs for an under-resourced language. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 15998–16006, Suzhou, China. Association for Computational Linguistics.