@inproceedings{rey-garcia-2026-comparative,
title = "A Comparative Study of Multilingual Fine-tuning and Prompting for Automatic Text Readability Classification in {G}alician",
author = "Rey, Sandra Rodr{\'i}guez and
Garcia, Marcos",
editor = "Shardlow, Matthew and
Fran{\c{c}}ois, Thomas and
Amaro, Raquel and
Baptista, Jorge and
Cardon, R{\'e}mi and
Ribeiro, Eug{\'e}nio and
Saggion, Horacio and
Stodden, Regina and
Todirascu, Amalia and
Wilkens, Rodrigo",
booktitle = "Proceedings of the Joint Workshop on Readability and Text Simplification ({READI}x{TSAR}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.readi-1.8/",
doi = "10.63317/4tnwhe3r9579",
pages = "101--120",
abstract = "Despite advancements in automatic readability assessment, low-resource languages such as Galician remain under-explored. This study addresses this gap by presenting a comparative study of readability assessment techniques in Galician, including fine-tuning of encoder models as well as prompting strategies using large generative models. Due to the scarcity of native Galician resources, neural machine translation was employed to generate synthetic Galician data. The analysis begins with BERT-based monolingual models trained on the synthetic data. For multilingual models, the impact of using original versus translated data was compared in order to assess the effects of translation-based augmentation. Finally, several LLMs were evaluated using zero-shot and few-shot prompting methods. The results indicate that generative models are not yet competitive with encoder models tuned for text classification in Galician, and that data generated through machine translation improves the performance of monolingual models but has little effect on multilingual models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rey-garcia-2026-comparative">
<titleInfo>
<title>A Comparative Study of Multilingual Fine-tuning and Prompting for Automatic Text Readability Classification in Galician</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="given">Rodríguez</namePart>
<namePart type="family">Rey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Garcia</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 Joint Workshop on Readability and Text Simplification (READIxTSAR) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">François</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Amaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Baptista</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rémi</namePart>
<namePart type="family">Cardon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugénio</namePart>
<namePart type="family">Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Stodden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amalia</namePart>
<namePart type="family">Todirascu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodrigo</namePart>
<namePart type="family">Wilkens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite advancements in automatic readability assessment, low-resource languages such as Galician remain under-explored. This study addresses this gap by presenting a comparative study of readability assessment techniques in Galician, including fine-tuning of encoder models as well as prompting strategies using large generative models. Due to the scarcity of native Galician resources, neural machine translation was employed to generate synthetic Galician data. The analysis begins with BERT-based monolingual models trained on the synthetic data. For multilingual models, the impact of using original versus translated data was compared in order to assess the effects of translation-based augmentation. Finally, several LLMs were evaluated using zero-shot and few-shot prompting methods. The results indicate that generative models are not yet competitive with encoder models tuned for text classification in Galician, and that data generated through machine translation improves the performance of monolingual models but has little effect on multilingual models.</abstract>
<identifier type="citekey">rey-garcia-2026-comparative</identifier>
<identifier type="doi">10.63317/4tnwhe3r9579</identifier>
<location>
<url>https://aclanthology.org/2026.readi-1.8/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>101</start>
<end>120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Comparative Study of Multilingual Fine-tuning and Prompting for Automatic Text Readability Classification in Galician
%A Rey, Sandra Rodríguez
%A Garcia, Marcos
%Y Shardlow, Matthew
%Y François, Thomas
%Y Amaro, Raquel
%Y Baptista, Jorge
%Y Cardon, Rémi
%Y Ribeiro, Eugénio
%Y Saggion, Horacio
%Y Stodden, Regina
%Y Todirascu, Amalia
%Y Wilkens, Rodrigo
%S Proceedings of the Joint Workshop on Readability and Text Simplification (READIxTSAR) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F rey-garcia-2026-comparative
%X Despite advancements in automatic readability assessment, low-resource languages such as Galician remain under-explored. This study addresses this gap by presenting a comparative study of readability assessment techniques in Galician, including fine-tuning of encoder models as well as prompting strategies using large generative models. Due to the scarcity of native Galician resources, neural machine translation was employed to generate synthetic Galician data. The analysis begins with BERT-based monolingual models trained on the synthetic data. For multilingual models, the impact of using original versus translated data was compared in order to assess the effects of translation-based augmentation. Finally, several LLMs were evaluated using zero-shot and few-shot prompting methods. The results indicate that generative models are not yet competitive with encoder models tuned for text classification in Galician, and that data generated through machine translation improves the performance of monolingual models but has little effect on multilingual models.
%R 10.63317/4tnwhe3r9579
%U https://aclanthology.org/2026.readi-1.8/
%U https://doi.org/10.63317/4tnwhe3r9579
%P 101-120
Markdown (Informal)
[A Comparative Study of Multilingual Fine-tuning and Prompting for Automatic Text Readability Classification in Galician](https://aclanthology.org/2026.readi-1.8/) (Rey & Garcia, READI-TSAR 2026)
ACL