以多哈历史词典为基础 grounding Arabic LLMs：检索增强的古兰经和圣训理解
Grounding Arabic LLMs in the Doha Historical Dictionary: Retrieval-Augmented Understanding of Quran and Hadith
AI总结：
本文提出基于多哈历史词典的检索增强生成框架，提升阿拉伯语LLM对历史宗教文本的理解能力，实验表明在Fanar和ALLaM模型上准确率超过85%。
摘要：
大型语言模型（LLMs）在许多语言任务中取得了显著进展，但仍在处理复杂的古代和宗教阿拉伯文本如古兰经和圣训时面临挑战。为解决这一限制，我们开发了一个基于历时词典知识的检索增强生成（RAG）框架。不同于以往依赖通用语料库的RAG系统，我们的方法从多哈历史阿拉伯词典（DHDA）中检索证据，该词典记录了阿拉伯词汇的历史发展。所提出的流程结合了混合检索与基于意图的路由机制，为LLM提供精确且上下文相关的历 史信息。实验表明，这种方法提高了阿拉伯语原生LLM的准确性，包括Fanar和ALLaM，超过85%，显著缩小了与Gemini等专有大型模型的性能差距。Gemini也作为LLM-as-a-judge系统用于自动评估。自动判断通过人类评估验证，显示高一致性（kappa = 0.87）。错误分析进一步突显了关键语言挑战，包括变音符号和复合表达。这些发现展示了将历时词典资源整合到检索增强生成框架中的价值，以增强阿拉伯语理解，特别是对于历史和宗教文本。代码和资源可在：https://github.com/somayaeltanbouly/Doha-Dictionary-RAG 公开获取。
英文摘要：
Large language models (LLMs) have achieved remarkable progress in many language tasks, yet they continue to struggle with complex historical and religious Arabic texts such as the Quran and Hadith. To address this limitation, we develop a retrieval-augmented generation (RAG) framework grounded in diachronic lexicographic knowledge. Unlike prior RAG systems that rely on general-purpose corpora, our approach retrieves evidence from the Doha Historical Dictionary of Arabic (DHDA), a large-scale resource documenting the historical development of Arabic vocabulary. The proposed pipeline combines hybrid retrieval with an intent-based routing mechanism to provide LLMs with precise, contextually relevant historical information. Our experiments show that this approach improves the accuracy of Arabic-native LLMs, including Fanar and ALLaM, to over 85\%, substantially reducing the performance gap with Gemini, a proprietary large-scale model. Gemini also serves as an LLM-as-a-judge system for automatic evaluation in our experiments. The automated judgments were verified through human evaluation, demonstrating high agreement (kappa = 0.87). An error analysis further highlights key linguistic challenges, including diacritics and compound expressions. These findings demonstrate the value of integrating diachronic lexicographic resources into retrieval-augmented generation frameworks to enhance Arabic language understanding, particularly for historical and religious texts. The code and resources are publicly available at: https://github.com/somayaeltanbouly/Doha-Dictionary-RAG.
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。
