# Optimizing RAG Pipelines for Arabic: A Systematic Analysis of Core Components

arXiv: https://arxiv.org/abs/2506.06339 · HTML: https://mlsanity.com/paper/2506.06339/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 12 of its 19 references that are in the map.
- First posted on arXiv 1 Jun 2025.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 12 of 12)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023)
- [AraBERT: Transformer-based Model for Arabic Language Understanding](https://mlsanity.com/paper/2003.00104/) (2020)
- [Neural Arabic Question Answering](https://mlsanity.com/paper/1906.05394/) (2019)
- [A Panoramic Survey of Natural Language Processing in the Arab World](https://mlsanity.com/paper/2011.12631/) (2020)
- [Pre-Training BERT on Arabic Tweets: Practical Considerations](https://mlsanity.com/paper/2102.10684/) (2021)
- [Not All Languages are Equal: Insights into Multilingual Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.21970/) (2024)
- [Exploring Retrieval Augmented Generation in Arabic](https://mlsanity.com/paper/2408.07425/) (2024)

## Built on by (most cited first, 3 of 3)

- [Transformer Tafsir at QIAS 2025 Shared Task: Hybrid Retrieval-Augmented Generation for Islamic Knowledge Question Answering](https://mlsanity.com/paper/2509.23793/) (2025)
- [Evaluation of Small Language Models for Arabic Language Processing](https://mlsanity.com/paper/2606.21460/) (2026)
- [A Comprehensive Analysis of Arabic Natural Language Processing Research: Trends, Topic Evolution, and Research Gaps -- A Bibliometric and Topic-Based Study](https://mlsanity.com/paper/2608.23421/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has emerged as a powerful architecture for combining the precision of retrieval systems with the fluency of large language models. While several studies have investigated RAG pipelines for high-resource languages, the optimization of RAG components for Arabic remains underexplored. This study presents a comprehensive empirical evaluation of state-of-the-art RAG components-including chunking strategies, embedding models, rerankers, and language models-across a diverse set of Arabic datasets. Using the RAGAS framework, we systematically compare performance across four core metrics: context precision, context recall, answer faithfulness, and answer relevancy. Our experiments demonstrate that sentence-aware chunking outperforms all other segmentation methods, while BGE-M3 and Multilingual-E5-large emerge as the most effective embedding models. The inclusion of a reranker (bge-reranker-v2-m3) significantly boosts faithfulness in complex datasets, and Aya-8B surpasses StableLM in generation quality. These findings provide critical insights for building high-quality Arabic RAG pipelines and offer practical guidelines for selecting optimal components across different document types.