@inproceedings{louchheim-etal-2025-using,
title = "Using Encipherment to Isolate Conditions for the Successful Fine-tuning of Massively Multilingual Translation Models",
author = "Louchheim, Carter and
Sotnichenko, Denis and
Yamaguchi, Yukina and
Hopkins, Mark",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Tenth Conference on Machine Translation",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.wmt-1.14/",
pages = "241--252",
ISBN = "979-8-89176-341-8",
abstract = "When fine-tuning massively multilingual translation models for low-resource languages, practitioners often include auxiliary languages to improve performance, but factors determining successful auxiliary language selection remain unclear. This paper investigates whether syntactic similarity or lexical overlap is more important for effective multilingual fine-tuning. We use encipherment to create controlled experimental conditions that disentangle these confounded factors, generating novel languages with identical syntax but no lexical overlap, and conversely, languages that preserve lexical overlap. Through extensive NLLB-200 fine-tuning experiments across Europarl and AmericasNLP datasets, we demonstrate that lexical overlap is the dominant factor. Syntactically identical auxiliary languages provide negligible benefits ( 1.0 ChrF), while languages with significant lexical overlap provide substantial improvements ( 5.0 ChrF), with effectiveness strongly correlated to KL-divergence between token distributions (r = -0.47, p .001). Our findings provide clear guidance: when selecting auxiliary languages for multilingual fine-tuning, prioritize lexical overlap over syntactic similarity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="louchheim-etal-2025-using">
<titleInfo>
<title>Using Encipherment to Isolate Conditions for the Successful Fine-tuning of Massively Multilingual Translation Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carter</namePart>
<namePart type="family">Louchheim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Denis</namePart>
<namePart type="family">Sotnichenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yukina</namePart>
<namePart type="family">Yamaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Hopkins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-341-8</identifier>
</relatedItem>
<abstract>When fine-tuning massively multilingual translation models for low-resource languages, practitioners often include auxiliary languages to improve performance, but factors determining successful auxiliary language selection remain unclear. This paper investigates whether syntactic similarity or lexical overlap is more important for effective multilingual fine-tuning. We use encipherment to create controlled experimental conditions that disentangle these confounded factors, generating novel languages with identical syntax but no lexical overlap, and conversely, languages that preserve lexical overlap. Through extensive NLLB-200 fine-tuning experiments across Europarl and AmericasNLP datasets, we demonstrate that lexical overlap is the dominant factor. Syntactically identical auxiliary languages provide negligible benefits ( 1.0 ChrF), while languages with significant lexical overlap provide substantial improvements ( 5.0 ChrF), with effectiveness strongly correlated to KL-divergence between token distributions (r = -0.47, p .001). Our findings provide clear guidance: when selecting auxiliary languages for multilingual fine-tuning, prioritize lexical overlap over syntactic similarity.</abstract>
<identifier type="citekey">louchheim-etal-2025-using</identifier>
<location>
<url>https://aclanthology.org/2025.wmt-1.14/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>241</start>
<end>252</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Encipherment to Isolate Conditions for the Successful Fine-tuning of Massively Multilingual Translation Models
%A Louchheim, Carter
%A Sotnichenko, Denis
%A Yamaguchi, Yukina
%A Hopkins, Mark
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Tenth Conference on Machine Translation
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-341-8
%F louchheim-etal-2025-using
%X When fine-tuning massively multilingual translation models for low-resource languages, practitioners often include auxiliary languages to improve performance, but factors determining successful auxiliary language selection remain unclear. This paper investigates whether syntactic similarity or lexical overlap is more important for effective multilingual fine-tuning. We use encipherment to create controlled experimental conditions that disentangle these confounded factors, generating novel languages with identical syntax but no lexical overlap, and conversely, languages that preserve lexical overlap. Through extensive NLLB-200 fine-tuning experiments across Europarl and AmericasNLP datasets, we demonstrate that lexical overlap is the dominant factor. Syntactically identical auxiliary languages provide negligible benefits ( 1.0 ChrF), while languages with significant lexical overlap provide substantial improvements ( 5.0 ChrF), with effectiveness strongly correlated to KL-divergence between token distributions (r = -0.47, p .001). Our findings provide clear guidance: when selecting auxiliary languages for multilingual fine-tuning, prioritize lexical overlap over syntactic similarity.
%U https://aclanthology.org/2025.wmt-1.14/
%P 241-252
Markdown (Informal)
[Using Encipherment to Isolate Conditions for the Successful Fine-tuning of Massively Multilingual Translation Models](https://aclanthology.org/2025.wmt-1.14/) (Louchheim et al., WMT 2025)
ACL