@inproceedings{devine-2024-tagengo,
title = "Tagengo: A Multilingual Chat Dataset",
author = "Devine, Peter",
editor = {S{\"a}lev{\"a}, Jonne and
Owodunni, Abraham},
booktitle = "Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.mrl-1.6",
pages = "106--113",
abstract = "Open source large language models (LLMs) have shown great improvements in recent times. However, many of these models are focused solely on popular spoken languages. We present a high quality dataset of more than 70k prompt-response pairs in 74 languages which consist of human generated prompts and synthetic responses. We use this dataset to train a state-of-the-art open source English LLM to chat multilingually.We evaluate our model on MT-Bench chat benchmarks in 6 languages, finding that our multilingual model outperforms previous state-of-the-art open source LLMs across each language. We further find that training on more multilingual data is beneficial to the performance in a chosen target language (Japanese) compared to simply training on only data in that language.These results indicate the necessity of training on large amounts of high quality multilingual data to make a more accessible LLM.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="devine-2024-tagengo">
<titleInfo>
<title>Tagengo: A Multilingual Chat Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Devine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonne</namePart>
<namePart type="family">Sälevä</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abraham</namePart>
<namePart type="family">Owodunni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Open source large language models (LLMs) have shown great improvements in recent times. However, many of these models are focused solely on popular spoken languages. We present a high quality dataset of more than 70k prompt-response pairs in 74 languages which consist of human generated prompts and synthetic responses. We use this dataset to train a state-of-the-art open source English LLM to chat multilingually.We evaluate our model on MT-Bench chat benchmarks in 6 languages, finding that our multilingual model outperforms previous state-of-the-art open source LLMs across each language. We further find that training on more multilingual data is beneficial to the performance in a chosen target language (Japanese) compared to simply training on only data in that language.These results indicate the necessity of training on large amounts of high quality multilingual data to make a more accessible LLM.</abstract>
<identifier type="citekey">devine-2024-tagengo</identifier>
<location>
<url>https://aclanthology.org/2024.mrl-1.6</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>106</start>
<end>113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tagengo: A Multilingual Chat Dataset
%A Devine, Peter
%Y Sälevä, Jonne
%Y Owodunni, Abraham
%S Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F devine-2024-tagengo
%X Open source large language models (LLMs) have shown great improvements in recent times. However, many of these models are focused solely on popular spoken languages. We present a high quality dataset of more than 70k prompt-response pairs in 74 languages which consist of human generated prompts and synthetic responses. We use this dataset to train a state-of-the-art open source English LLM to chat multilingually.We evaluate our model on MT-Bench chat benchmarks in 6 languages, finding that our multilingual model outperforms previous state-of-the-art open source LLMs across each language. We further find that training on more multilingual data is beneficial to the performance in a chosen target language (Japanese) compared to simply training on only data in that language.These results indicate the necessity of training on large amounts of high quality multilingual data to make a more accessible LLM.
%U https://aclanthology.org/2024.mrl-1.6
%P 106-113
Markdown (Informal)
[Tagengo: A Multilingual Chat Dataset](https://aclanthology.org/2024.mrl-1.6) (Devine, MRL 2024)
ACL
- Peter Devine. 2024. Tagengo: A Multilingual Chat Dataset. In Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024), pages 106–113, Miami, Florida, USA. Association for Computational Linguistics.