From Classification to Generation: Insights into Crosslingual Retrieval Augmented ICL
This addresses performance gaps for users in low-resource language settings, though it is incremental as it builds on existing retrieval-augmented methods.
The paper tackled the problem of limited in-context learning performance of large language models in low-resource languages by introducing cross-lingual retrieval-augmented in-context learning, which improved zero-shot performance in classification tasks but faced challenges in generation tasks.
The remarkable ability of Large Language Models (LLMs) to understand and follow instructions has sometimes been limited by their in-context learning (ICL) performance in low-resource languages. To address this, we introduce a novel approach that leverages cross-lingual retrieval-augmented in-context learning (CREA-ICL). By extracting semantically similar prompts from high-resource languages, we aim to improve the zero-shot performance of multilingual pre-trained language models (MPLMs) across diverse tasks. Though our approach yields steady improvements in classification tasks, it faces challenges in generation tasks. Our evaluation offers insights into the performance dynamics of retrieval-augmented in-context learning across both classification and generation domains.