优化阿拉伯语 RAG 流水线：对核心组件的系统性分析
Optimizing RAG Pipelines for Arabic: A Systematic Analysis of Core Components
AI总结：
本文系统评估阿拉伯语 RAG 的分块、嵌入、重排序与生成组件，发现句子感知分块、BGE-M3/Multilingual-E5-large、bge-reranker-v2-m3 与 Aya-8B 具有优势，并给出组件选择指南。
摘要：
检索增强生成（RAG）已成为一种强大的架构，能够将检索系统的精确性与大型语言模型的流畅性结合起来。尽管已有若干研究考察了面向高资源语言的 RAG 流水线，但针对阿拉伯语优化 RAG 组件仍未得到充分探索。本研究在一组多样化的阿拉伯语数据集上，对最先进的 RAG 组件进行了全面实证评估，包括分块策略、嵌入模型、重排序器和语言模型。我们使用 RAGAS 框架，系统比较了四项核心指标上的表现：上下文精确率、上下文召回率、答案忠实度和答案相关性。实验表明，句子感知分块优于所有其他切分方法，而 BGE-M3 和 Multilingual-E5-large 成为最有效的嵌入模型。加入重排序器（bge-reranker-v2-m3）显著提升了复杂数据集上的忠实度，并且 Aya-8B 在生成质量上超过 StableLM。这些发现为构建高质量阿拉伯语 RAG 流水线提供了关键洞见，并为在不同文档类型之间选择最优组件提供了实用指南。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
