Work

Burhan at IslamicEval: Fact-Augmented and LLM-Driven Retrieval for Islamic QA

Year: 2025

Type: conference-paper

Abstract: This paper presents our approach to the Qur'an and Hadith QA task in the IslamicEval 2025 Shared Task.Reliable retrieval requires both accuracy and context-aware answers from Qur'anic and Hadith text.To address this challenge, We combine semantic search with LLMbased re-ranking.To enhance alignment, we augment the corpus with LLM-extracted Islamic facts and paraphrased queries.An LLMbased binary classifier further verifies whether retrieved passages answer the questions.Results show improved accuracy and better alignment with user intent.

Source: Arabic Natural Language Processing Workshop (WANLP)

DOI: 10.18653/v1/2025.arabicnlp-sharedtasks.73

Authors: Mohammad Basheer, Watheq Mansour, Abdulhamid Touma, Ahmad Qadeib Alban

Institutions: The University of Queensland, Syrian Virtual University, Université Paris Dauphine-PSL

Language: English

Topic: Information Retrieval and Search Behavior

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W4416037779

FWCI:

Cites:

Cited by:

Related to: 10