@inproceedings{chang-etal-2026-goldfish,
title = "Goldfish: Monolingual Language Models for 350 Languages",
author = "Chang, Tyler A. and
Arnett, Catherine and
Tu, Zhuowen and
Bergen, Benjamin",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.300/",
doi = "10.63317/5ceec3hhv4d5",
pages = "3750--3781",
abstract = "For many low-resource languages, the only available language models are large multilingual models trained on many languages simultaneously. Despite state-of-the-art performance on reasoning tasks, we find that these models still struggle with basic grammatical text generation in many languages. First, large multilingual models perform worse than bigrams for many languages (e.g. 24{\%} of languages in XGLM 4.5B; 43{\%} in BLOOM 7.1B) using FLORES perplexity as an evaluation metric. Second, when we train small monolingual models with only 125M parameters on 1GB or less data for 350 languages, these small models outperform large multilingual models both in perplexity and on a massively multilingual grammaticality benchmark. To facilitate future work on low-resource language modeling, we release Goldfish, a suite of over 1,000 small monolingual language models trained comparably for 350 languages. These models represent the first publicly-available monolingual language models for 215 of the languages included."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chang-etal-2026-goldfish">
<titleInfo>
<title>Goldfish: Monolingual Language Models for 350 Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuowen</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Bergen</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>For many low-resource languages, the only available language models are large multilingual models trained on many languages simultaneously. Despite state-of-the-art performance on reasoning tasks, we find that these models still struggle with basic grammatical text generation in many languages. First, large multilingual models perform worse than bigrams for many languages (e.g. 24% of languages in XGLM 4.5B; 43% in BLOOM 7.1B) using FLORES perplexity as an evaluation metric. Second, when we train small monolingual models with only 125M parameters on 1GB or less data for 350 languages, these small models outperform large multilingual models both in perplexity and on a massively multilingual grammaticality benchmark. To facilitate future work on low-resource language modeling, we release Goldfish, a suite of over 1,000 small monolingual language models trained comparably for 350 languages. These models represent the first publicly-available monolingual language models for 215 of the languages included.</abstract>
<identifier type="citekey">chang-etal-2026-goldfish</identifier>
<identifier type="doi">10.63317/5ceec3hhv4d5</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.300/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>3750</start>
<end>3781</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Goldfish: Monolingual Language Models for 350 Languages
%A Chang, Tyler A.
%A Arnett, Catherine
%A Tu, Zhuowen
%A Bergen, Benjamin
%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 chang-etal-2026-goldfish
%X For many low-resource languages, the only available language models are large multilingual models trained on many languages simultaneously. Despite state-of-the-art performance on reasoning tasks, we find that these models still struggle with basic grammatical text generation in many languages. First, large multilingual models perform worse than bigrams for many languages (e.g. 24% of languages in XGLM 4.5B; 43% in BLOOM 7.1B) using FLORES perplexity as an evaluation metric. Second, when we train small monolingual models with only 125M parameters on 1GB or less data for 350 languages, these small models outperform large multilingual models both in perplexity and on a massively multilingual grammaticality benchmark. To facilitate future work on low-resource language modeling, we release Goldfish, a suite of over 1,000 small monolingual language models trained comparably for 350 languages. These models represent the first publicly-available monolingual language models for 215 of the languages included.
%R 10.63317/5ceec3hhv4d5
%U https://aclanthology.org/2026.lrec-1.300/
%U https://doi.org/10.63317/5ceec3hhv4d5
%P 3750-3781
Markdown (Informal)
[Goldfish: Monolingual Language Models for 350 Languages](https://aclanthology.org/2026.lrec-1.300/) (Chang et al., LREC 2026)
ACL
- Tyler A. Chang, Catherine Arnett, Zhuowen Tu, and Benjamin Bergen. 2026. Goldfish: Monolingual Language Models for 350 Languages. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 3750–3781, Palma de Mallorca, Spain. ELRA Language Resource Association.