Crosslingual Retrieval Augmented In-context Learning for Bangla
This addresses the problem of low-resource language performance for users in regions like Bangladesh, though it appears incremental as it builds on existing methods.
The paper tackled the limited performance of large language models in low-resource languages like Bangla by using cross-lingual retrieval augmented in-context learning, resulting in steady improvements over zero-shot performance on Bangla tasks.
The promise of Large Language Models (LLMs) in Natural Language Processing has often been overshadowed by their limited performance in low-resource languages such as Bangla. To address this, our paper presents a pioneering approach that utilizes cross-lingual retrieval augmented in-context learning. By strategically sourcing semantically similar prompts from high-resource language, we enable multilingual pretrained language models (MPLMs), especially the generative model BLOOMZ, to successfully boost performance on Bangla tasks. Our extensive evaluation highlights that the cross-lingual retrieval augmented prompts bring steady improvements to MPLMs over the zero-shot performance.