@inproceedings{sushko-etal-2025-skipclm,
title = "{S}kip{CLM}: Enhancing Crosslingual Alignment of Decoder Transformer Models via Contrastive Learning and Skip Connection",
author = "Sushko, Nikita and
Panchenko, Alexander and
Tutubalina, Elena",
editor = "Ebrahimi, Abteen and
Haider, Samar and
Liu, Emmy and
Haider, Sammar and
Leonor Pacheco, Maria and
Wein, Shira",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = apr,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-srw.50/",
doi = "10.18653/v1/2025.naacl-srw.50",
pages = "517--528",
ISBN = "979-8-89176-192-6",
abstract = "This paper proposes SkipCLM, a novel method for improving multilingual machine translation in Decoder Transformers. We augment contrastive learning for cross-lingual alignment with a trainable skip connection to preserve information crucial for accurate target language generation. Experiments with XGLM-564M on the Flores-101 benchmark demonstrate improved performance, particularly for en-de and en-zh direction translations, compared to direct sequence-to-sequence training and existing contrastive learning methods. Code is available at: https://github.com/s-nlp/skipclm."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sushko-etal-2025-skipclm">
<titleInfo>
<title>SkipCLM: Enhancing Crosslingual Alignment of Decoder Transformer Models via Contrastive Learning and Skip Connection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikita</namePart>
<namePart type="family">Sushko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Panchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Tutubalina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abteen</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sammar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Leonor Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shira</namePart>
<namePart type="family">Wein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-192-6</identifier>
</relatedItem>
<abstract>This paper proposes SkipCLM, a novel method for improving multilingual machine translation in Decoder Transformers. We augment contrastive learning for cross-lingual alignment with a trainable skip connection to preserve information crucial for accurate target language generation. Experiments with XGLM-564M on the Flores-101 benchmark demonstrate improved performance, particularly for en-de and en-zh direction translations, compared to direct sequence-to-sequence training and existing contrastive learning methods. Code is available at: https://github.com/s-nlp/skipclm.</abstract>
<identifier type="citekey">sushko-etal-2025-skipclm</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-srw.50</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-srw.50/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>517</start>
<end>528</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SkipCLM: Enhancing Crosslingual Alignment of Decoder Transformer Models via Contrastive Learning and Skip Connection
%A Sushko, Nikita
%A Panchenko, Alexander
%A Tutubalina, Elena
%Y Ebrahimi, Abteen
%Y Haider, Samar
%Y Liu, Emmy
%Y Haider, Sammar
%Y Leonor Pacheco, Maria
%Y Wein, Shira
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-192-6
%F sushko-etal-2025-skipclm
%X This paper proposes SkipCLM, a novel method for improving multilingual machine translation in Decoder Transformers. We augment contrastive learning for cross-lingual alignment with a trainable skip connection to preserve information crucial for accurate target language generation. Experiments with XGLM-564M on the Flores-101 benchmark demonstrate improved performance, particularly for en-de and en-zh direction translations, compared to direct sequence-to-sequence training and existing contrastive learning methods. Code is available at: https://github.com/s-nlp/skipclm.
%R 10.18653/v1/2025.naacl-srw.50
%U https://aclanthology.org/2025.naacl-srw.50/
%U https://doi.org/10.18653/v1/2025.naacl-srw.50
%P 517-528
Markdown (Informal)
[SkipCLM: Enhancing Crosslingual Alignment of Decoder Transformer Models via Contrastive Learning and Skip Connection](https://aclanthology.org/2025.naacl-srw.50/) (Sushko et al., NAACL 2025)
ACL