优化阿拉伯语RAG管道，找出最佳组件组合
Optimizing RAG Pipelines for Arabic: A Systematic Analysis of Core Components
- 测试不同分块、嵌入、重排序和生成模型的组合效果
- 句子级分块和BGE-M3嵌入表现最优，重排序提升答案可信度
- 适合开发高精度阿拉伯语问答系统的研究者与工程师
检索增强生成（RAG）结合了检索系统的精准性与大语言模型的流畅性，已成为主流架构。尽管已有研究关注高资源语言的RAG优化，但阿拉伯语的RAG组件优化仍缺乏系统探索。本研究对多种阿拉伯语数据集上的先进RAG组件——包括分块策略、嵌入模型、重排序器和语言模型——进行了全面实证评估。采用RAGAS框架，系统比较了上下文精确率、上下文召回率、答案忠实度和答案相关性四项核心指标。实验表明，句子感知分块优于其他分割方法；BGE-M3与Multilingual-E5-large是表现最佳的嵌入模型；引入bge-reranker-v2-m3重排序器显著提升复杂数据集中的忠实度；Aya-8B在生成质量上优于StableLM。研究为构建高质量阿拉伯语RAG系统提供了关键洞见与实用选型指南。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。