@inproceedings{gebremeskel-etal-2026-gccla,
title = "{GCCLA}: Graph-Conditioned Cross-Lingual Adaptation of Large Language Models Under Extreme Data Scarcity (A Case Study in {T}igrigna)",
author = "Gebremeskel, Hagos Gebremedhin and
Feng, Chong and
Abera, Asefa Mebrahtu",
editor = "Prabhakaran, Vinodkumar and
Dev, Sunipa and
Benotti, Luciana and
Hershcovich, Daniel and
Cao, Yong and
Zhou, Li and
Ma, BOlei and
Adebara, Ife",
booktitle = "Proceedings of the 4th Workshop on Cross-Cultural Considerations in {NLP} ({C}3{NLP} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.c3nlp-1.4/",
pages = "50--66",
ISBN = "979-8-89176-420-0",
abstract = "Adapting large language models (LLMs) to extremely low-resource languages remains challenging due to severe data scarcity and the lack of structured linguistic supervision. We introduce GCCLA, a graph-conditioned cross-lingual adaptation framework that integrates multilingual knowledge graphs into parameter-efficient LLM adaptation. GCCLA conditions a frozen multilingual LLM on structured semantic and typological relations encoded in a multilingual graph, providing a strong inductive bias for data-efficient transfer. We instantiate and evaluate the framework through a focused case study on English-to-Amharic-to-Tigrinya transfer, where labeled data is extremely limited. By separating knowledge representation from language modeling, GCCLA stabilizes learning and improves sample efficiency in few-shot regimes. We evaluate the approach on five tasks, sentiment analysis, named entity recognition, natural language inference, question answering, and extractive summarization, under extreme data scarcity, with as few as 0{--}1000 labeled Tigrinya examples. Experimental results show that GCCLA consistently outperforms multilingual, translation-based, and parameter-efficient baselines, achieves competitive performance with as few as 100 labeled examples, and degrades gracefully under partial graph coverage. These findings demonstrate that graph conditioning is an effective principle for data-efficient cross-lingual adaptation of LLMs advancing equitable NLP."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gebremeskel-etal-2026-gccla">
<titleInfo>
<title>GCCLA: Graph-Conditioned Cross-Lingual Adaptation of Large Language Models Under Extreme Data Scarcity (A Case Study in Tigrigna)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hagos</namePart>
<namePart type="given">Gebremedhin</namePart>
<namePart type="family">Gebremeskel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asefa</namePart>
<namePart type="given">Mebrahtu</namePart>
<namePart type="family">Abera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Cross-Cultural Considerations in NLP (C3NLP 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vinodkumar</namePart>
<namePart type="family">Prabhakaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luciana</namePart>
<namePart type="family">Benotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Hershcovich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">BOlei</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ife</namePart>
<namePart type="family">Adebara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-420-0</identifier>
</relatedItem>
<abstract>Adapting large language models (LLMs) to extremely low-resource languages remains challenging due to severe data scarcity and the lack of structured linguistic supervision. We introduce GCCLA, a graph-conditioned cross-lingual adaptation framework that integrates multilingual knowledge graphs into parameter-efficient LLM adaptation. GCCLA conditions a frozen multilingual LLM on structured semantic and typological relations encoded in a multilingual graph, providing a strong inductive bias for data-efficient transfer. We instantiate and evaluate the framework through a focused case study on English-to-Amharic-to-Tigrinya transfer, where labeled data is extremely limited. By separating knowledge representation from language modeling, GCCLA stabilizes learning and improves sample efficiency in few-shot regimes. We evaluate the approach on five tasks, sentiment analysis, named entity recognition, natural language inference, question answering, and extractive summarization, under extreme data scarcity, with as few as 0–1000 labeled Tigrinya examples. Experimental results show that GCCLA consistently outperforms multilingual, translation-based, and parameter-efficient baselines, achieves competitive performance with as few as 100 labeled examples, and degrades gracefully under partial graph coverage. These findings demonstrate that graph conditioning is an effective principle for data-efficient cross-lingual adaptation of LLMs advancing equitable NLP.</abstract>
<identifier type="citekey">gebremeskel-etal-2026-gccla</identifier>
<location>
<url>https://aclanthology.org/2026.c3nlp-1.4/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>50</start>
<end>66</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GCCLA: Graph-Conditioned Cross-Lingual Adaptation of Large Language Models Under Extreme Data Scarcity (A Case Study in Tigrigna)
%A Gebremeskel, Hagos Gebremedhin
%A Feng, Chong
%A Abera, Asefa Mebrahtu
%Y Prabhakaran, Vinodkumar
%Y Dev, Sunipa
%Y Benotti, Luciana
%Y Hershcovich, Daniel
%Y Cao, Yong
%Y Zhou, Li
%Y Ma, BOlei
%Y Adebara, Ife
%S Proceedings of the 4th Workshop on Cross-Cultural Considerations in NLP (C3NLP 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-420-0
%F gebremeskel-etal-2026-gccla
%X Adapting large language models (LLMs) to extremely low-resource languages remains challenging due to severe data scarcity and the lack of structured linguistic supervision. We introduce GCCLA, a graph-conditioned cross-lingual adaptation framework that integrates multilingual knowledge graphs into parameter-efficient LLM adaptation. GCCLA conditions a frozen multilingual LLM on structured semantic and typological relations encoded in a multilingual graph, providing a strong inductive bias for data-efficient transfer. We instantiate and evaluate the framework through a focused case study on English-to-Amharic-to-Tigrinya transfer, where labeled data is extremely limited. By separating knowledge representation from language modeling, GCCLA stabilizes learning and improves sample efficiency in few-shot regimes. We evaluate the approach on five tasks, sentiment analysis, named entity recognition, natural language inference, question answering, and extractive summarization, under extreme data scarcity, with as few as 0–1000 labeled Tigrinya examples. Experimental results show that GCCLA consistently outperforms multilingual, translation-based, and parameter-efficient baselines, achieves competitive performance with as few as 100 labeled examples, and degrades gracefully under partial graph coverage. These findings demonstrate that graph conditioning is an effective principle for data-efficient cross-lingual adaptation of LLMs advancing equitable NLP.
%U https://aclanthology.org/2026.c3nlp-1.4/
%P 50-66
Markdown (Informal)
[GCCLA: Graph-Conditioned Cross-Lingual Adaptation of Large Language Models Under Extreme Data Scarcity (A Case Study in Tigrigna)](https://aclanthology.org/2026.c3nlp-1.4/) (Gebremeskel et al., C3NLP 2026)
ACL