@inproceedings{liu-niehues-2025-conditions,
title = "Conditions for Catastrophic Forgetting in Multilingual Translation",
author = "Liu, Danni and
Niehues, Jan",
editor = "Adelani, David Ifeoluwa and
Arnett, Catherine and
Ataman, Duygu and
Chang, Tyler A. and
Gonen, Hila and
Raja, Rahul and
Schmidt, Fabian and
Stap, David and
Wang, Jiayi",
booktitle = "Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)",
month = nov,
year = "2025",
address = "Suzhuo, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.mrl-main.23/",
pages = "347--359",
ISBN = "979-8-89176-345-6",
abstract = "Fine-tuning multilingual foundation models on specific languages often induces catastrophic forgetting, degrading performance on languages unseen in fine-tuning. While this phenomenon is widely-documented, the literature presents fragmented results about when forgetting occurs. To address this ambiguity, we conduct a systematic empirical study using machine translation as a testbed to identify the conditions that trigger catastrophic forgetting in multilingual fine-tuning. Through controlled experiments across different model architectures, data scales, and fine-tuning approaches, we reveal that the relative scale between model and data size is a primary determinant of forgetting. Moreover, we demonstrate that a model{'}s instruction-following ability is more critical for retaining multilingual knowledge than its architecture. Contrary to assumptions, parameter-efficient fine-tuning offers no clear advantage over full fine-tuning in mitigating forgetting. Lastly, we show that cross-lingual alignment can mitigate forgetting while also facilitating positive transfer to unseen target languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-niehues-2025-conditions">
<titleInfo>
<title>Conditions for Catastrophic Forgetting in Multilingual Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danni</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Niehues</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 5th Workshop on Multilingual Representation Learning (MRL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duygu</namePart>
<namePart type="family">Ataman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hila</namePart>
<namePart type="family">Gonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Raja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabian</namePart>
<namePart type="family">Schmidt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Stap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhuo, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-345-6</identifier>
</relatedItem>
<abstract>Fine-tuning multilingual foundation models on specific languages often induces catastrophic forgetting, degrading performance on languages unseen in fine-tuning. While this phenomenon is widely-documented, the literature presents fragmented results about when forgetting occurs. To address this ambiguity, we conduct a systematic empirical study using machine translation as a testbed to identify the conditions that trigger catastrophic forgetting in multilingual fine-tuning. Through controlled experiments across different model architectures, data scales, and fine-tuning approaches, we reveal that the relative scale between model and data size is a primary determinant of forgetting. Moreover, we demonstrate that a model’s instruction-following ability is more critical for retaining multilingual knowledge than its architecture. Contrary to assumptions, parameter-efficient fine-tuning offers no clear advantage over full fine-tuning in mitigating forgetting. Lastly, we show that cross-lingual alignment can mitigate forgetting while also facilitating positive transfer to unseen target languages.</abstract>
<identifier type="citekey">liu-niehues-2025-conditions</identifier>
<location>
<url>https://aclanthology.org/2025.mrl-main.23/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>347</start>
<end>359</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Conditions for Catastrophic Forgetting in Multilingual Translation
%A Liu, Danni
%A Niehues, Jan
%Y Adelani, David Ifeoluwa
%Y Arnett, Catherine
%Y Ataman, Duygu
%Y Chang, Tyler A.
%Y Gonen, Hila
%Y Raja, Rahul
%Y Schmidt, Fabian
%Y Stap, David
%Y Wang, Jiayi
%S Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhuo, China
%@ 979-8-89176-345-6
%F liu-niehues-2025-conditions
%X Fine-tuning multilingual foundation models on specific languages often induces catastrophic forgetting, degrading performance on languages unseen in fine-tuning. While this phenomenon is widely-documented, the literature presents fragmented results about when forgetting occurs. To address this ambiguity, we conduct a systematic empirical study using machine translation as a testbed to identify the conditions that trigger catastrophic forgetting in multilingual fine-tuning. Through controlled experiments across different model architectures, data scales, and fine-tuning approaches, we reveal that the relative scale between model and data size is a primary determinant of forgetting. Moreover, we demonstrate that a model’s instruction-following ability is more critical for retaining multilingual knowledge than its architecture. Contrary to assumptions, parameter-efficient fine-tuning offers no clear advantage over full fine-tuning in mitigating forgetting. Lastly, we show that cross-lingual alignment can mitigate forgetting while also facilitating positive transfer to unseen target languages.
%U https://aclanthology.org/2025.mrl-main.23/
%P 347-359
Markdown (Informal)
[Conditions for Catastrophic Forgetting in Multilingual Translation](https://aclanthology.org/2025.mrl-main.23/) (Liu & Niehues, MRL 2025)
ACL