@inproceedings{lee-etal-2025-prom,
title = "{PROM}: Pivoted and Regulated Optimization for Multilingual Instruction Learning",
author = "Lee, Jaeseong and
Hwang, Seung-won and
Lee, Hojin and
Bak, Yunju and
Lee, Changmin",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-short.19/",
doi = "10.18653/v1/2025.naacl-short.19",
pages = "222--228",
ISBN = "979-8-89176-190-2",
abstract = "Large language models (LLMs) have become standard for natural language generation tasks, with instruction-tuning enhancing their capabilities. However, the lack of instruction-tuning datasets in languages other than English limits their application to diverse languages. To address this, researchers have adapted English-centric LLMs to other languages by appending English tuning data with its translated pair, from which we observe negative interference between the two. To resolve this, our contribution is identifying English as an internal pivot language, based on which we disentangle the roles of English and target language data in training. Specifically, we first design two roles as pivoted objectives, and also propose to regulate between the two, to better generalize for under-represented languages. Experiments across various languages demonstrate the effectiveness of our approach on multiple benchmarks. The code is publicly available for further exploration."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2025-prom">
<titleInfo>
<title>PROM: Pivoted and Regulated Optimization for Multilingual Instruction Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jaeseong</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-won</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hojin</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunju</namePart>
<namePart type="family">Bak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changmin</namePart>
<namePart type="family">Lee</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 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</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">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-190-2</identifier>
</relatedItem>
<abstract>Large language models (LLMs) have become standard for natural language generation tasks, with instruction-tuning enhancing their capabilities. However, the lack of instruction-tuning datasets in languages other than English limits their application to diverse languages. To address this, researchers have adapted English-centric LLMs to other languages by appending English tuning data with its translated pair, from which we observe negative interference between the two. To resolve this, our contribution is identifying English as an internal pivot language, based on which we disentangle the roles of English and target language data in training. Specifically, we first design two roles as pivoted objectives, and also propose to regulate between the two, to better generalize for under-represented languages. Experiments across various languages demonstrate the effectiveness of our approach on multiple benchmarks. The code is publicly available for further exploration.</abstract>
<identifier type="citekey">lee-etal-2025-prom</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-short.19</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-short.19/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>222</start>
<end>228</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PROM: Pivoted and Regulated Optimization for Multilingual Instruction Learning
%A Lee, Jaeseong
%A Hwang, Seung-won
%A Lee, Hojin
%A Bak, Yunju
%A Lee, Changmin
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-190-2
%F lee-etal-2025-prom
%X Large language models (LLMs) have become standard for natural language generation tasks, with instruction-tuning enhancing their capabilities. However, the lack of instruction-tuning datasets in languages other than English limits their application to diverse languages. To address this, researchers have adapted English-centric LLMs to other languages by appending English tuning data with its translated pair, from which we observe negative interference between the two. To resolve this, our contribution is identifying English as an internal pivot language, based on which we disentangle the roles of English and target language data in training. Specifically, we first design two roles as pivoted objectives, and also propose to regulate between the two, to better generalize for under-represented languages. Experiments across various languages demonstrate the effectiveness of our approach on multiple benchmarks. The code is publicly available for further exploration.
%R 10.18653/v1/2025.naacl-short.19
%U https://aclanthology.org/2025.naacl-short.19/
%U https://doi.org/10.18653/v1/2025.naacl-short.19
%P 222-228
Markdown (Informal)
[PROM: Pivoted and Regulated Optimization for Multilingual Instruction Learning](https://aclanthology.org/2025.naacl-short.19/) (Lee et al., NAACL 2025)
ACL
- Jaeseong Lee, Seung-won Hwang, Hojin Lee, Yunju Bak, and Changmin Lee. 2025. PROM: Pivoted and Regulated Optimization for Multilingual Instruction Learning. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 222–228, Albuquerque, New Mexico. Association for Computational Linguistics.