Exploring Retrieval Augmented Generation in Arabic
It addresses the problem of adapting RAG to Arabic, a language with unique characteristics and resource constraints, for NLP researchers and practitioners, but is incremental as it applies existing methods to a new domain.
This paper tackled the underexplored application of Retrieval Augmented Generation (RAG) to Arabic text by implementing and evaluating pipelines with various semantic embedding models and LLMs, showing that existing models can be effectively employed for this purpose.
Recently, Retrieval Augmented Generation (RAG) has emerged as a powerful technique in natural language processing, combining the strengths of retrieval-based and generation-based models to enhance text generation tasks. However, the application of RAG in Arabic, a language with unique characteristics and resource constraints, remains underexplored. This paper presents a comprehensive case study on the implementation and evaluation of RAG for Arabic text. The work focuses on exploring various semantic embedding models in the retrieval stage and several LLMs in the generation stage, in order to investigate what works and what doesn't in the context of Arabic. The work also touches upon the issue of variations between document dialect and query dialect in the retrieval stage. Results show that existing semantic embedding models and LLMs can be effectively employed to build Arabic RAG pipelines.