@inproceedings{do-bloem-2026-well,
title = "How Well Do Large Language Models Reason in Under-Resourced Languages? Evidence from {V}ietnamese",
author = "Do, Tuan Anh and
Bloem, Jelke",
editor = "Ojha, Atul Kr. and
Sakti, Sakriani and
Soria, Claudia and
Melero, Maite and
McCrae, John P. and
Lignos, Constantine and
Liu, Chao-Hong and
Claramunt, German Rigau and
Rehm, Georg",
booktitle = "Proceedings of the {SIGUL} 2026 Joint Workshop with {ELE}, {EURALI}, and {DCLRL}: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages",
month = may,
year = "2026",
address = "Palma, Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.sigul-1.1/",
doi = "10.63317/2a43bkurpywk",
pages = "1--18",
abstract = "Despite advancements in Large Language Models, reasoning benchmarks remain centered on high-resource languages, leaving languages like Vietnamese under-evaluated. In this study, we aim to address this gap by evaluating four models: PhoGPT (native), Vistral and VBD-Llama (adapted), and Llama-2 (English-centric), on commonsense reasoning and arithmetic reasoning. As Vietnamese benchmarks for these tasks are lacking, we adapt two analogy datasets from English to Vietnamese and construct two sequence datasets, ensuring a range of structural complexity and difficulty levels. We evaluate diverse prompting strategies, including Chain-of-Thought, role-playing guidance, cross-lingual prompting, and few-shot learning. Our results reveal a baseline proficiency in analogical and arithmetic reasoning among the models, with Vistral and Llama-2 outperforming other models in multiple tasks. The effects of Chain-of-Thought and contextual guidance are limited in Vietnamese, while cross-lingual prompting and few-shot learning show promising performance improvements. The findings underscore the feasibility of adapting benchmarks to less-resourced languages and provide insights into strengths and weaknesses in the performance of Vietnamese LLMs, suggesting directions for model improvements."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="do-bloem-2026-well">
<titleInfo>
<title>How Well Do Large Language Models Reason in Under-Resourced Languages? Evidence from Vietnamese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tuan</namePart>
<namePart type="given">Anh</namePart>
<namePart type="family">Do</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jelke</namePart>
<namePart type="family">Bloem</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 SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="given">Rigau</namePart>
<namePart type="family">Claramunt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</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 Large Language Models, reasoning benchmarks remain centered on high-resource languages, leaving languages like Vietnamese under-evaluated. In this study, we aim to address this gap by evaluating four models: PhoGPT (native), Vistral and VBD-Llama (adapted), and Llama-2 (English-centric), on commonsense reasoning and arithmetic reasoning. As Vietnamese benchmarks for these tasks are lacking, we adapt two analogy datasets from English to Vietnamese and construct two sequence datasets, ensuring a range of structural complexity and difficulty levels. We evaluate diverse prompting strategies, including Chain-of-Thought, role-playing guidance, cross-lingual prompting, and few-shot learning. Our results reveal a baseline proficiency in analogical and arithmetic reasoning among the models, with Vistral and Llama-2 outperforming other models in multiple tasks. The effects of Chain-of-Thought and contextual guidance are limited in Vietnamese, while cross-lingual prompting and few-shot learning show promising performance improvements. The findings underscore the feasibility of adapting benchmarks to less-resourced languages and provide insights into strengths and weaknesses in the performance of Vietnamese LLMs, suggesting directions for model improvements.</abstract>
<identifier type="citekey">do-bloem-2026-well</identifier>
<identifier type="doi">10.63317/2a43bkurpywk</identifier>
<location>
<url>https://aclanthology.org/2026.sigul-1.1/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1</start>
<end>18</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Well Do Large Language Models Reason in Under-Resourced Languages? Evidence from Vietnamese
%A Do, Tuan Anh
%A Bloem, Jelke
%Y Ojha, Atul Kr.
%Y Sakti, Sakriani
%Y Soria, Claudia
%Y Melero, Maite
%Y McCrae, John P.
%Y Lignos, Constantine
%Y Liu, Chao-Hong
%Y Claramunt, German Rigau
%Y Rehm, Georg
%S Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca, Spain
%F do-bloem-2026-well
%X Despite advancements in Large Language Models, reasoning benchmarks remain centered on high-resource languages, leaving languages like Vietnamese under-evaluated. In this study, we aim to address this gap by evaluating four models: PhoGPT (native), Vistral and VBD-Llama (adapted), and Llama-2 (English-centric), on commonsense reasoning and arithmetic reasoning. As Vietnamese benchmarks for these tasks are lacking, we adapt two analogy datasets from English to Vietnamese and construct two sequence datasets, ensuring a range of structural complexity and difficulty levels. We evaluate diverse prompting strategies, including Chain-of-Thought, role-playing guidance, cross-lingual prompting, and few-shot learning. Our results reveal a baseline proficiency in analogical and arithmetic reasoning among the models, with Vistral and Llama-2 outperforming other models in multiple tasks. The effects of Chain-of-Thought and contextual guidance are limited in Vietnamese, while cross-lingual prompting and few-shot learning show promising performance improvements. The findings underscore the feasibility of adapting benchmarks to less-resourced languages and provide insights into strengths and weaknesses in the performance of Vietnamese LLMs, suggesting directions for model improvements.
%R 10.63317/2a43bkurpywk
%U https://aclanthology.org/2026.sigul-1.1/
%U https://doi.org/10.63317/2a43bkurpywk
%P 1-18
Markdown (Informal)
[How Well Do Large Language Models Reason in Under-Resourced Languages? Evidence from Vietnamese](https://aclanthology.org/2026.sigul-1.1/) (Do & Bloem, SIGUL-EURALI-DCLRL 2026)
ACL