Grounding Arabic LLMs in the Doha Historical Dictionary: Retrieval-Augmented Understanding of Quran and Hadith

2026-03-25

AI Summary

This work addresses the challenges faced by Arabic large language models in accurately interpreting classical texts such as the Qur’an and Hadith, where contextual understanding remains limited. To mitigate this, the study introduces an intent-driven hybrid retrieval routing mechanism within a retrieval-augmented generation (RAG) framework, incorporating the Doha Historical Dictionary of Arabic (DHDA) to provide precise historical lexical context. This approach significantly enhances the comprehension capabilities of native Arabic large language models—including Fanar and ALLaM—achieving over 85% accuracy on classical text understanding tasks and substantially narrowing the performance gap with closed-source models like Gemini. Human evaluation further confirms the system’s reliability, yielding a Kappa agreement coefficient of 0.87.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

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.

Problem

• Arabic LLMs
• Quran
• Hadith
• historical texts
• religious texts

Innovation

• Retrieval-Augmented Generation
• Diachronic Lexicography
• Arabic Historical Texts
• Intent-based Routing
• Doha Historical Dictionary