@inproceedings{lin-etal-2025-xampler,
title = "{XAMPLER}: Learning to Retrieve Cross-Lingual In-Context Examples",
author = "Lin, Peiqin and
Martins, Andre and
Schuetze, Hinrich",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.221/",
doi = "10.18653/v1/2025.findings-naacl.221",
pages = "3968--3977",
ISBN = "979-8-89176-195-7",
abstract = "Recent studies indicate that leveraging off-the-shelf or fine-tuned retrievers, capable of retrieving relevant in-context examples tailored to the input query, enhances few-shot in-context learning of English. However, adapting these methods to other languages, especially low-resource ones, poses challenges due to the scarcity of cross-lingual retrievers and annotated data. Thus, we introduce XAMPLER: Cross-Lingual Example Retrieval, a method tailored to tackle the challenge of cross-lingual in-context learning using only annotated English data. XAMPLER first trains a retriever based on Glot500, a multilingual small language model, using positive and negative English examples constructed from the predictions of a multilingual large language model, i.e., MaLA500. Leveraging the cross-lingual capacity of the retriever, it can directly retrieve English examples as few-shot examples for in-context learning of target languages. Experiments on two multilingual text classification benchmarks, namely SIB200 with 176 languages and MasakhaNEWS with 16 languages, demonstrate that XAMPLER substantially improves the in-context learning performance across languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2025-xampler">
<titleInfo>
<title>XAMPLER: Learning to Retrieve Cross-Lingual In-Context Examples</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peiqin</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hinrich</namePart>
<namePart type="family">Schuetze</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>Findings of the Association for Computational Linguistics: NAACL 2025</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">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>Recent studies indicate that leveraging off-the-shelf or fine-tuned retrievers, capable of retrieving relevant in-context examples tailored to the input query, enhances few-shot in-context learning of English. However, adapting these methods to other languages, especially low-resource ones, poses challenges due to the scarcity of cross-lingual retrievers and annotated data. Thus, we introduce XAMPLER: Cross-Lingual Example Retrieval, a method tailored to tackle the challenge of cross-lingual in-context learning using only annotated English data. XAMPLER first trains a retriever based on Glot500, a multilingual small language model, using positive and negative English examples constructed from the predictions of a multilingual large language model, i.e., MaLA500. Leveraging the cross-lingual capacity of the retriever, it can directly retrieve English examples as few-shot examples for in-context learning of target languages. Experiments on two multilingual text classification benchmarks, namely SIB200 with 176 languages and MasakhaNEWS with 16 languages, demonstrate that XAMPLER substantially improves the in-context learning performance across languages.</abstract>
<identifier type="citekey">lin-etal-2025-xampler</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.221</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.221/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>3968</start>
<end>3977</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T XAMPLER: Learning to Retrieve Cross-Lingual In-Context Examples
%A Lin, Peiqin
%A Martins, Andre
%A Schuetze, Hinrich
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F lin-etal-2025-xampler
%X Recent studies indicate that leveraging off-the-shelf or fine-tuned retrievers, capable of retrieving relevant in-context examples tailored to the input query, enhances few-shot in-context learning of English. However, adapting these methods to other languages, especially low-resource ones, poses challenges due to the scarcity of cross-lingual retrievers and annotated data. Thus, we introduce XAMPLER: Cross-Lingual Example Retrieval, a method tailored to tackle the challenge of cross-lingual in-context learning using only annotated English data. XAMPLER first trains a retriever based on Glot500, a multilingual small language model, using positive and negative English examples constructed from the predictions of a multilingual large language model, i.e., MaLA500. Leveraging the cross-lingual capacity of the retriever, it can directly retrieve English examples as few-shot examples for in-context learning of target languages. Experiments on two multilingual text classification benchmarks, namely SIB200 with 176 languages and MasakhaNEWS with 16 languages, demonstrate that XAMPLER substantially improves the in-context learning performance across languages.
%R 10.18653/v1/2025.findings-naacl.221
%U https://aclanthology.org/2025.findings-naacl.221/
%U https://doi.org/10.18653/v1/2025.findings-naacl.221
%P 3968-3977
Markdown (Informal)
[XAMPLER: Learning to Retrieve Cross-Lingual In-Context Examples](https://aclanthology.org/2025.findings-naacl.221/) (Lin et al., Findings 2025)
ACL