@inproceedings{antero-etal-2025-diploma,
title = "{DIPL}om{A}: Efficient Adaptation of Instructed {LLM}s to Low-Resource Languages via Post-Training Delta Merging",
author = "Antero, Ixak Sarasua and
Corral, Ander and
Saralegi, Xabier",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.1355/",
pages = "24898--24912",
ISBN = "979-8-89176-335-7",
abstract = "This paper investigates how open-weight instruction-tuned large language models (LLMs) can be efficiently adapted to low-resource languages without requiring costly large-scale post-training. We introduce DIPLomA (Decoupled Instruction-Preserving Language Adaptation), a lightweight delta-based transfer strategy that provides a practical and effective solution for this scenario. DIPLomA decouples language adaptation from post-training alignment by first continually pretraining a foundational LLM on a modest amount of monolingual target-language data while anchoring on English replay, and then injecting instruction-following capabilities via delta-based weight merging from the instructed counterpart of the base LLM. We evaluate DIPLomA on Basque and validate its generality on Welsh and Swahili, demonstrating consistent and substantial gains in instruction-following, linguistic proficiency, and safety. Compared to strong baselines, our method achieves average relative improvements of 50 points in Basque, 63 in Welsh, and 51 in Swahili, while preserving the original model{'}s multilingual performance. These results highlight DIPLomA as an effective, resource-efficient strategy for bringing high-quality instruction alignment to underrepresented languages at scale."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="antero-etal-2025-diploma">
<titleInfo>
<title>DIPLomA: Efficient Adaptation of Instructed LLMs to Low-Resource Languages via Post-Training Delta Merging</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ixak</namePart>
<namePart type="given">Sarasua</namePart>
<namePart type="family">Antero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ander</namePart>
<namePart type="family">Corral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xabier</namePart>
<namePart type="family">Saralegi</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>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</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">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>This paper investigates how open-weight instruction-tuned large language models (LLMs) can be efficiently adapted to low-resource languages without requiring costly large-scale post-training. We introduce DIPLomA (Decoupled Instruction-Preserving Language Adaptation), a lightweight delta-based transfer strategy that provides a practical and effective solution for this scenario. DIPLomA decouples language adaptation from post-training alignment by first continually pretraining a foundational LLM on a modest amount of monolingual target-language data while anchoring on English replay, and then injecting instruction-following capabilities via delta-based weight merging from the instructed counterpart of the base LLM. We evaluate DIPLomA on Basque and validate its generality on Welsh and Swahili, demonstrating consistent and substantial gains in instruction-following, linguistic proficiency, and safety. Compared to strong baselines, our method achieves average relative improvements of 50 points in Basque, 63 in Welsh, and 51 in Swahili, while preserving the original model’s multilingual performance. These results highlight DIPLomA as an effective, resource-efficient strategy for bringing high-quality instruction alignment to underrepresented languages at scale.</abstract>
<identifier type="citekey">antero-etal-2025-diploma</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.1355/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>24898</start>
<end>24912</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DIPLomA: Efficient Adaptation of Instructed LLMs to Low-Resource Languages via Post-Training Delta Merging
%A Antero, Ixak Sarasua
%A Corral, Ander
%A Saralegi, Xabier
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F antero-etal-2025-diploma
%X This paper investigates how open-weight instruction-tuned large language models (LLMs) can be efficiently adapted to low-resource languages without requiring costly large-scale post-training. We introduce DIPLomA (Decoupled Instruction-Preserving Language Adaptation), a lightweight delta-based transfer strategy that provides a practical and effective solution for this scenario. DIPLomA decouples language adaptation from post-training alignment by first continually pretraining a foundational LLM on a modest amount of monolingual target-language data while anchoring on English replay, and then injecting instruction-following capabilities via delta-based weight merging from the instructed counterpart of the base LLM. We evaluate DIPLomA on Basque and validate its generality on Welsh and Swahili, demonstrating consistent and substantial gains in instruction-following, linguistic proficiency, and safety. Compared to strong baselines, our method achieves average relative improvements of 50 points in Basque, 63 in Welsh, and 51 in Swahili, while preserving the original model’s multilingual performance. These results highlight DIPLomA as an effective, resource-efficient strategy for bringing high-quality instruction alignment to underrepresented languages at scale.
%U https://aclanthology.org/2025.findings-emnlp.1355/
%P 24898-24912
Markdown (Informal)
[DIPLomA: Efficient Adaptation of Instructed LLMs to Low-Resource Languages via Post-Training Delta Merging](https://aclanthology.org/2025.findings-emnlp.1355/) (Antero et al., Findings 2025)
ACL