@inproceedings{klimaszewski-etal-2025-train,
title = "No Train but Gain: Language Arithmetic for training-free Language Adapters enhancement",
author = "Klimaszewski, Mateusz and
Andruszkiewicz, Piotr and
Birch, Alexandra",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.737/",
pages = "11121--11134",
abstract = "Modular deep learning is the state-of-the-art solution for lifting the curse of multilinguality, preventing the impact of negative interference and enabling cross-lingual performance in Multilingual Pre-trained Language Models. However, a trade-off of this approach is the reduction in positive transfer learning from closely related languages. In response, we introduce a novel method called language arithmetic, which enables training-free post-processing to address this limitation. Extending the task arithmetic framework, we apply learning via addition to the language adapters, transitioning the framework from a multi-task to a multilingual setup. The effectiveness of the proposed solution is demonstrated on three downstream tasks in a MAD-X-based set of cross-lingual schemes, acting as a post-processing procedure. Language arithmetic consistently improves the baselines with significant gains, especially in the most challenging case of zero-shot application. Our code and models are available at https://github.com/mklimasz/language-arithmetic."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="klimaszewski-etal-2025-train">
<titleInfo>
<title>No Train but Gain: Language Arithmetic for training-free Language Adapters enhancement</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mateusz</namePart>
<namePart type="family">Klimaszewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Andruszkiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Modular deep learning is the state-of-the-art solution for lifting the curse of multilinguality, preventing the impact of negative interference and enabling cross-lingual performance in Multilingual Pre-trained Language Models. However, a trade-off of this approach is the reduction in positive transfer learning from closely related languages. In response, we introduce a novel method called language arithmetic, which enables training-free post-processing to address this limitation. Extending the task arithmetic framework, we apply learning via addition to the language adapters, transitioning the framework from a multi-task to a multilingual setup. The effectiveness of the proposed solution is demonstrated on three downstream tasks in a MAD-X-based set of cross-lingual schemes, acting as a post-processing procedure. Language arithmetic consistently improves the baselines with significant gains, especially in the most challenging case of zero-shot application. Our code and models are available at https://github.com/mklimasz/language-arithmetic.</abstract>
<identifier type="citekey">klimaszewski-etal-2025-train</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.737/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>11121</start>
<end>11134</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T No Train but Gain: Language Arithmetic for training-free Language Adapters enhancement
%A Klimaszewski, Mateusz
%A Andruszkiewicz, Piotr
%A Birch, Alexandra
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F klimaszewski-etal-2025-train
%X Modular deep learning is the state-of-the-art solution for lifting the curse of multilinguality, preventing the impact of negative interference and enabling cross-lingual performance in Multilingual Pre-trained Language Models. However, a trade-off of this approach is the reduction in positive transfer learning from closely related languages. In response, we introduce a novel method called language arithmetic, which enables training-free post-processing to address this limitation. Extending the task arithmetic framework, we apply learning via addition to the language adapters, transitioning the framework from a multi-task to a multilingual setup. The effectiveness of the proposed solution is demonstrated on three downstream tasks in a MAD-X-based set of cross-lingual schemes, acting as a post-processing procedure. Language arithmetic consistently improves the baselines with significant gains, especially in the most challenging case of zero-shot application. Our code and models are available at https://github.com/mklimasz/language-arithmetic.
%U https://aclanthology.org/2025.coling-main.737/
%P 11121-11134
Markdown (Informal)
[No Train but Gain: Language Arithmetic for training-free Language Adapters enhancement](https://aclanthology.org/2025.coling-main.737/) (Klimaszewski et al., COLING 2025)
ACL