@inproceedings{mao-yu-2024-tuning,
title = "Tuning {LLM}s with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages",
author = "Mao, Zhuoyuan and
Yu, Yen",
editor = "Ojha, Atul Kr. and
Liu, Chao-hong and
Vylomova, Ekaterina and
Pirinen, Flammie and
Abbott, Jade and
Washington, Jonathan and
Oco, Nathaniel and
Malykh, Valentin and
Logacheva, Varvara and
Zhao, Xiaobing",
booktitle = "Proceedings of the The Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.loresmt-1.1",
pages = "1--25",
abstract = "This article introduces contrastive alignment instructions (AlignInstruct) to address two challenges in machine translation (MT) on large language models (LLMs). One is the expansion of supported languages to previously unseen ones. The second relates to the lack of data in low-resource languages. Model fine-tuning through MT instructions (MTInstruct) is a straightforward approach to the first challenge. However, MTInstruct is limited by weak cross-lingual signals inherent in the second challenge. AlignInstruct emphasizes cross-lingual supervision via a cross-lingual discriminator built using statistical word alignments. Our results based on fine-tuning the BLOOMZ models (1b1, 3b, and 7b1) in up to 24 unseen languages showed that: (1) LLMs can effectively translate unseen languages using MTInstruct; (2) AlignInstruct led to consistent improvements in translation quality across 48 translation directions involving English; (3) Discriminator-based instructions outperformed their generative counterparts as cross-lingual instructions; (4) AlignInstruct improved performance in 30 zero-shot directions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mao-yu-2024-tuning">
<titleInfo>
<title>Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhuoyuan</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yen</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the The Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)</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">Chao-hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jade</namePart>
<namePart type="family">Abbott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article introduces contrastive alignment instructions (AlignInstruct) to address two challenges in machine translation (MT) on large language models (LLMs). One is the expansion of supported languages to previously unseen ones. The second relates to the lack of data in low-resource languages. Model fine-tuning through MT instructions (MTInstruct) is a straightforward approach to the first challenge. However, MTInstruct is limited by weak cross-lingual signals inherent in the second challenge. AlignInstruct emphasizes cross-lingual supervision via a cross-lingual discriminator built using statistical word alignments. Our results based on fine-tuning the BLOOMZ models (1b1, 3b, and 7b1) in up to 24 unseen languages showed that: (1) LLMs can effectively translate unseen languages using MTInstruct; (2) AlignInstruct led to consistent improvements in translation quality across 48 translation directions involving English; (3) Discriminator-based instructions outperformed their generative counterparts as cross-lingual instructions; (4) AlignInstruct improved performance in 30 zero-shot directions.</abstract>
<identifier type="citekey">mao-yu-2024-tuning</identifier>
<location>
<url>https://aclanthology.org/2024.loresmt-1.1</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>1</start>
<end>25</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages
%A Mao, Zhuoyuan
%A Yu, Yen
%Y Ojha, Atul Kr.
%Y Liu, Chao-hong
%Y Vylomova, Ekaterina
%Y Pirinen, Flammie
%Y Abbott, Jade
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Malykh, Valentin
%Y Logacheva, Varvara
%Y Zhao, Xiaobing
%S Proceedings of the The Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F mao-yu-2024-tuning
%X This article introduces contrastive alignment instructions (AlignInstruct) to address two challenges in machine translation (MT) on large language models (LLMs). One is the expansion of supported languages to previously unseen ones. The second relates to the lack of data in low-resource languages. Model fine-tuning through MT instructions (MTInstruct) is a straightforward approach to the first challenge. However, MTInstruct is limited by weak cross-lingual signals inherent in the second challenge. AlignInstruct emphasizes cross-lingual supervision via a cross-lingual discriminator built using statistical word alignments. Our results based on fine-tuning the BLOOMZ models (1b1, 3b, and 7b1) in up to 24 unseen languages showed that: (1) LLMs can effectively translate unseen languages using MTInstruct; (2) AlignInstruct led to consistent improvements in translation quality across 48 translation directions involving English; (3) Discriminator-based instructions outperformed their generative counterparts as cross-lingual instructions; (4) AlignInstruct improved performance in 30 zero-shot directions.
%U https://aclanthology.org/2024.loresmt-1.1
%P 1-25
Markdown (Informal)
[Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages](https://aclanthology.org/2024.loresmt-1.1) (Mao & Yu, LoResMT-WS 2024)
ACL