XAMPLER: Learning to Retrieve Cross-Lingual In-Context Examples

TL;DR

XAMPLER is a novel cross-lingual example retrieval method that enhances few-shot in-context learning for multiple languages using only English data, leveraging multilingual models to improve performance on diverse benchmarks.

Contribution

Introduces XAMPLER, a cross-lingual retrieval approach that uses English annotations and multilingual models to improve in-context learning across many languages.

Findings

Significant performance gains on multilingual benchmarks.

Effective retrieval of cross-lingual examples using only English data.

Demonstrates scalability across 176 languages.

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. Our code is available at https://github.com/cisnlp/XAMPLER.