@inproceedings{sitaram-etal-2023-everything,
title = "Everything you need to know about Multilingual {LLM}s: Towards fair, performant and reliable models for languages of the world",
author = "Sitaram, Sunayana and
Choudhury, Monojit and
Patra, Barun and
Chaudhary, Vishrav and
Ahuja, Kabir and
Bali, Kalika",
editor = "Chen, Yun-Nung (Vivian) and
Margot, Margot and
Reddy, Siva",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 6: Tutorial Abstracts)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-tutorials.3",
doi = "10.18653/v1/2023.acl-tutorials.3",
pages = "21--26",
abstract = "This tutorial will describe various aspects of scaling up language technologies to many of the world{'}s languages by describing the latest research in Massively Multilingual Language Models (MMLMs). We will cover topics such as data collection, training and fine-tuning of models, Responsible AI issues such as fairness, bias and toxicity, linguistic diversity and evaluation in the context of MMLMs, specifically focusing on issues in non-English and low-resource languages. Further, we will also talk about some of the real-world challenges in deploying these models in language communities in the field. With the performance of MMLMs improving in the zero-shot setting for many languages, it is now becoming feasible to use them for building language technologies in many languages of the world, and this tutorial will provide the computational linguistics community with unique insights from the latest research in multilingual models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sitaram-etal-2023-everything">
<titleInfo>
<title>Everything you need to know about Multilingual LLMs: Towards fair, performant and reliable models for languages of the world</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monojit</namePart>
<namePart type="family">Choudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barun</namePart>
<namePart type="family">Patra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishrav</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kabir</namePart>
<namePart type="family">Ahuja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 6: Tutorial Abstracts)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="given">(Vivian)</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Margot</namePart>
<namePart type="family">Margot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siva</namePart>
<namePart type="family">Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This tutorial will describe various aspects of scaling up language technologies to many of the world’s languages by describing the latest research in Massively Multilingual Language Models (MMLMs). We will cover topics such as data collection, training and fine-tuning of models, Responsible AI issues such as fairness, bias and toxicity, linguistic diversity and evaluation in the context of MMLMs, specifically focusing on issues in non-English and low-resource languages. Further, we will also talk about some of the real-world challenges in deploying these models in language communities in the field. With the performance of MMLMs improving in the zero-shot setting for many languages, it is now becoming feasible to use them for building language technologies in many languages of the world, and this tutorial will provide the computational linguistics community with unique insights from the latest research in multilingual models.</abstract>
<identifier type="citekey">sitaram-etal-2023-everything</identifier>
<identifier type="doi">10.18653/v1/2023.acl-tutorials.3</identifier>
<location>
<url>https://aclanthology.org/2023.acl-tutorials.3</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>21</start>
<end>26</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Everything you need to know about Multilingual LLMs: Towards fair, performant and reliable models for languages of the world
%A Sitaram, Sunayana
%A Choudhury, Monojit
%A Patra, Barun
%A Chaudhary, Vishrav
%A Ahuja, Kabir
%A Bali, Kalika
%Y Chen, Yun-Nung (Vivian)
%Y Margot, Margot
%Y Reddy, Siva
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 6: Tutorial Abstracts)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F sitaram-etal-2023-everything
%X This tutorial will describe various aspects of scaling up language technologies to many of the world’s languages by describing the latest research in Massively Multilingual Language Models (MMLMs). We will cover topics such as data collection, training and fine-tuning of models, Responsible AI issues such as fairness, bias and toxicity, linguistic diversity and evaluation in the context of MMLMs, specifically focusing on issues in non-English and low-resource languages. Further, we will also talk about some of the real-world challenges in deploying these models in language communities in the field. With the performance of MMLMs improving in the zero-shot setting for many languages, it is now becoming feasible to use them for building language technologies in many languages of the world, and this tutorial will provide the computational linguistics community with unique insights from the latest research in multilingual models.
%R 10.18653/v1/2023.acl-tutorials.3
%U https://aclanthology.org/2023.acl-tutorials.3
%U https://doi.org/10.18653/v1/2023.acl-tutorials.3
%P 21-26
Markdown (Informal)
[Everything you need to know about Multilingual LLMs: Towards fair, performant and reliable models for languages of the world](https://aclanthology.org/2023.acl-tutorials.3) (Sitaram et al., ACL 2023)
ACL