Hybrid Neural Retrieval with Generative Query Refinement for Quranic Passage Retrieval

2026-06-11

AI Summary

This work addresses the semantic gap between Modern Standard Arabic queries and Classical Arabic texts of the Qur’an, along with challenges such as multi-verse retrieval and filtering unanswerable questions. The authors propose an end-to-end neural retrieval framework that combines AraColBERT for dense retrieval and BM25 for sparse retrieval in candidate recall, followed by a CAMeLBERTmix cross-encoder for semantic re-ranking. A confidence gating mechanism is introduced to filter out unanswerable queries, while an AraT5-based generative module aggregates information across multiple verses. Evaluated on an extended version of the QuranQA 2022 dataset, the approach achieves a Recall@10 of 0.7024 and MAP@10 of 0.4947, significantly outperforming baseline models while enhancing retrieval comprehensiveness and reliability without compromising contextual awareness.

Abstract

Quranic Passage Retrieval (PR) could be a challenging task due to the linguistic complexity and the semantic gap between the Modern Standard Arabic (MSA) used in daily queries and the Classical Arabic (CA) of the Holy Quran. These factors hinder conventional retrieval methods. To handle these limitations and improve multi-verse retrieval and filter the zero-answer queries, this paper proposes a four-phase neural architecture designed to enhance retrieval accuracy and contextual understanding. The methodology combines hybrid candidate retrieval using AraColBERT dense indexing and BM25 sparse retrieval, followed by semantic reranking with a CAMeLBERTmix cross-encoder. A confidence gating mechanism is then applied to filter zero-answer queries, and an AraT5-based refinement module for multi-verse aggregation. The system is evaluated on an expanded version of the Quran QA 2022 dataset. Results show improved performance compared to the baseline models, achieving a Recall@10 of 0.7024 and a Mean Average Precision (MAP@10) of 0.4947. While the system exhibits a marginal tradeoff in absolute top-rank precision (MRR = 0.5807) compared to heavily optimised single models, the proposed architecture provides a substantially more comprehensive, reliable, and context aware solution for multi-verse Quranic passage retrieval.

Problem

• Quranic Passage Retrieval
• Semantic Gap
• Classical Arabic
• Modern Standard Arabic
• Zero-answer Queries

Innovation

• Hybrid Neural Retrieval
• Generative Query Refinement
• Confidence Gating
• Multi-verse Aggregation
• Cross-encoder Reranking