{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:52:28Z","timestamp":1780501948460,"version":"3.54.1"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"25","license":[{"start":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T00:00:00Z","timestamp":1748822400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T00:00:00Z","timestamp":1748822400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100018777","name":"Nile University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100018777","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Question\u2013answering (QA) systems face considerable challenges when involved in Islamic fatwas due to the complexity and sensitivity of the data. Such problems involve providing accurate and reliable responses, managing hallucinations and inaccurate responses, and maintaining the stability of the generated responses. Prior studies have concentrated mainly on collecting and preprocessing Islamic datasets or developing retrieval-based QA systems, overlooking the precision and reliability required for fatwa issuance. To address this issue, we propose a QA approach utilizing advanced retrieval-augmented generation (RAG), which is enhanced by a re-ranker to increase response stability, eliminate hallucinations, and prioritize the most appropriate and exact answer. This enhancement significantly improves response stability and reduces hallucinations by improving the data used for answer generation. We conducted experiments across three setups: (1) base LLM, (2) LLM with RAG, and (3) LLM with RAG and re-ranker. The third method of LLM with RAG includes a re-ranker for knowledge retrieval, which improves the process and ensures relevant and trustworthy data. This differentiates it from the second method, which uses a retrieval model. The Flash re-ranker retrieves the most relevant data, which increases the response stability and trustworthiness. Evaluations using BERTScore, hallucination, completeness, and irrelevance metrics demonstrated that the third experiment LLM with RAG and re-ranker outperformed other setups, providing precise, stable, and dependable answers. This research contributes a robust methodology to improve AI-driven fatwa systems, guaranteeing higher precision and trustworthiness in Islamic QA systems.<\/jats:p>","DOI":"10.1007\/s00521-025-11229-y","type":"journal-article","created":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T12:05:06Z","timestamp":1748865906000},"page":"20957-20982","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Aftina: enhancing stability and preventing hallucination in AI-based Islamic fatwa generation using LLMs and RAG"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6001-6701","authenticated-orcid":false,"given":"Marryam Yahya","family":"Mohammed","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sama Ayman","family":"Ali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salma Khaled","family":"Ali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ayad Abdul","family":"Majeed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ensaf Hussein","family":"Mohamed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,2]]},"reference":[{"key":"11229_CR1","doi-asserted-by":"crossref","unstructured":"Qamar F, Latif S, Latif R (2024) A benchmark dataset with larger Context for non-factoid question answering over islamic text. arXiv:2409.09844","DOI":"10.3724\/2096-7004.di.2025.0065"},{"key":"11229_CR2","first-page":"503","volume":"12","author":"I Elhalwany","year":"2015","unstructured":"Elhalwany I, Mohammed A, Wassif K, Hefny H (2015) Using textual case-based reasoning in intelligent fatawa qa system. Int Arab J Inf Technol 12:503\u2013509","journal-title":"Int Arab J Inf Technol"},{"key":"11229_CR3","doi-asserted-by":"publisher","first-page":"1633","DOI":"10.7717\/peerj-cs.1633","volume":"9","author":"A Alrayzah","year":"2023","unstructured":"Alrayzah A, Alsolami F, Saleh M (2023) Challenges and opportunities for arabic question-answering systems: current techniques and future directions. PeerJ Comput Sci 9:1633. https:\/\/doi.org\/10.7717\/peerj-cs.1633","journal-title":"PeerJ Comput Sci"},{"issue":"10","key":"11229_CR4","doi-asserted-by":"publisher","first-page":"155","DOI":"10.3390\/data8100155","volume":"8","author":"O Alyemny","year":"2023","unstructured":"Alyemny O, Al-Khalifa H, Mirza A (2023) A data-driven exploration of a new islamic fatwas dataset for arabic nlp tasks. Data 8(10):155. https:\/\/doi.org\/10.3390\/data8100155","journal-title":"Data"},{"key":"11229_CR5","doi-asserted-by":"crossref","unstructured":"Abdallah A, Kasem M, Abdalla M, Mahmoud M, Elkasaby M, Elbendary Y, Jatowt A (2024) ArabicaQA: A Comprehensive Dataset for Arabic Question Answering. arXiv:2403.17848","DOI":"10.1145\/3626772.3657889"},{"issue":"4","key":"11229_CR6","doi-asserted-by":"publisher","first-page":"118","DOI":"10.47760\/ijcsmc.2021.v10i04.017","volume":"10","author":"AA Munshi","year":"2021","unstructured":"Munshi AA, AlSabban WH, Farag AT, Rakha OE, Al Sallab AA, Alotaibi M (2021) Towards an automated islamic fatwa system: survey, dataset and benchmarks. Int J Comput Sci Mobile Comput 10(4):118\u2013131","journal-title":"Int J Comput Sci Mobile Comput"},{"issue":"12","key":"11229_CR7","doi-asserted-by":"publisher","first-page":"7165","DOI":"10.1007\/s10115-024-02199-z","volume":"66","author":"G Yigit","year":"2024","unstructured":"Yigit G, Amasyali MF (2024) From text to multimodal: a survey of adversarial example generation in question answering systems. Knowl Inf Syst 66(12):7165\u20137204. https:\/\/doi.org\/10.1007\/s10115-024-02199-z","journal-title":"Knowl Inf Syst"},{"key":"11229_CR8","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1007\/978-981-15-3412-6_17","volume-title":"Semantic Technology","author":"L Wu","year":"2020","unstructured":"Wu L, Wu P, Zhang X (2020) A seq2seq-based approach to question answering over knowledge bases. In: Wang X, Lisi FA, Xiao G, Botoeva E (eds) Semantic Technology. Springer, Singapore, pp 170\u2013181"},{"issue":"9","key":"11229_CR9","doi-asserted-by":"publisher","first-page":"115","DOI":"10.3390\/bdcc8090115","volume":"8","author":"A Mansurova","year":"2024","unstructured":"Mansurova A, Mansurova A, Nugumanova A (2024) Qa-rag: exploring llm reliance on external knowledge. Big Data Cognitive Comput 8(9):115. https:\/\/doi.org\/10.3390\/bdcc8090115","journal-title":"Big Data Cognitive Comput"},{"key":"11229_CR10","unstructured":"Pham DK, Vo BQ (2024) Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Models. arXiv:2408.13808"},{"key":"11229_CR11","unstructured":"Zhou Y, Liu Y, Li X, Jin J, Qian H, Liu Z, Li C, Dou Z, Ho T-Y, Yu PS (2024) Trustworthiness in Retrieval-Augmented Generation Systems: A Survey. arXiv:2409.10102"},{"issue":"6","key":"11229_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3400396","volume":"19","author":"R Malhas","year":"2020","unstructured":"Malhas R, Elsayed T (2020) Ayatec: Building a reusable verse-based test collection for arabic question answering on the holy qur\u2019an. ACM Trans Asian Low-Resour Lang Inf Process 19(6):1. https:\/\/doi.org\/10.1145\/3400396","journal-title":"ACM Trans Asian Low-Resour Lang Inf Process"},{"key":"11229_CR13","unstructured":"Malhas R, Mansour W, Elsayed T (2022) Qur\u2019an QA 2022: Overview of the first shared task on question answering over the holy qur\u2019an. In: Al-Khalifa, H., Elsayed, T., Mubarak, H., Al-Thubaity, A., Magdy, W., Darwish, K. (eds.) Proceedinsg of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur\u2019an QA and Fine-Grained Hate Speech Detection, pp. 79\u201387. European Language Resources Association, Marseille, France. https:\/\/aclanthology.org\/2022.osact-1.9"},{"issue":"1","key":"11229_CR14","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1566\/1\/012007","volume":"1566","author":"MT Sihotang","year":"2020","unstructured":"Sihotang MT, Jaya I, Hizriadi A, Hardi SM (2020) Answering islamic questions with a chatbot using fuzzy string-matching algorithm. J Phys: Conf Ser 1566(1):012007. https:\/\/doi.org\/10.1088\/1742-6596\/1566\/1\/012007","journal-title":"J Phys: Conf Ser"},{"key":"11229_CR15","unstructured":"O\u2019Shea K, Nash R (2015) An Introduction to Convolutional Neural Networks. arXiv:1511.08458"},{"key":"11229_CR16","doi-asserted-by":"publisher","DOI":"10.24996\/ijs.2024.65.4.38","author":"RNE Anggraini","year":"2024","unstructured":"Anggraini RNE, Tursina D, Sarno R (2024) Islamic qa with chatbot system using convolutional neural network. Iraqi J Sci. https:\/\/doi.org\/10.24996\/ijs.2024.65.4.38","journal-title":"Iraqi J Sci"},{"key":"11229_CR17","unstructured":"PISS KTB, TIM Dakwah Pesantren: Tanya Jawab Islam: Piss KTB. Daarul Hijrah Technology, Indonesia (2015). https:\/\/books.google.com\/books\/about\/Tanya_Jawab_Islam.html?id=GMZQCwAAQBAJ"},{"key":"11229_CR18","doi-asserted-by":"publisher","first-page":"1464","DOI":"10.3390\/electronics12061464","volume":"12","author":"Q Zhang","year":"2023","unstructured":"Zhang Q, Zhang Y, Shao Y, Liu M, Li J, Yuan J, Wang R (2023) Boosting adversarial attacks with nadam optimizer. Electronics 12:1464","journal-title":"Electronics"},{"key":"11229_CR19","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1007\/s10462-021-10031-1","volume":"55","author":"T Alwaneen","year":"2021","unstructured":"Alwaneen T, Azmi A, Aboalsamh H, Cambria E, Hussain A (2021) Arabic question answering system: a survey. Artif Intell Rev 55:207. https:\/\/doi.org\/10.1007\/s10462-021-10031-1","journal-title":"Artif Intell Rev"},{"issue":"1","key":"11229_CR20","first-page":"9","volume":"11","author":"S Alnefaie","year":"2023","unstructured":"Alnefaie S, Atwell E, Alsalka M (2023) Islamic question answering systems survey and evaluation criteria. Int J Islamic Appl Comput Sci Technol 11(1):9","journal-title":"Int J Islamic Appl Comput Sci Technol"},{"key":"11229_CR21","first-page":"346","volume":"22","author":"SS Alotaibi","year":"2022","unstructured":"Alotaibi SS, Munshi AA, Farag AT, Rakha OE, Al Sallab AA, Alotaibi M (2022) KAB: knowledge augmented BERT2BERT automated questions answering system for Jurisprudential legal opinions. IJCSNS Int J Comput Sci Netw Secur 22:346","journal-title":"IJCSNS Int J Comput Sci Netw Secur"},{"key":"11229_CR22","doi-asserted-by":"crossref","unstructured":"Alan AY, Karaarslan E (2024) Aydin: A RAG-based Question Answering System Proposal for Understanding Islam: MufassirQAS LLM. arXiv:2401.15378","DOI":"10.2139\/ssrn.4707470"},{"key":"11229_CR23","doi-asserted-by":"crossref","unstructured":"Hasan MA, Hasanain M, Ahmad F, Laskar SR, Upadhyay S, Sukhadia VN, Kutlu M, Chowdhury SA, Alam F (2024) NativQA: Multilingual Culturally-Aligned Natural Query for LLMs. arXiv:2407.09823","DOI":"10.18653\/v1\/2025.findings-acl.770"},{"key":"11229_CR24","doi-asserted-by":"crossref","unstructured":"Hasan MA, Hasanain M, Ahmad F, Laskar SR, Upadhyay S, Sukhadia VN, Kutlu M, Chowdhury SA, Alam F (2024) NativQA: Multilingual Culturally-Aligned Natural Query for LLMs. arXiv:2407.09823. arXiv:2407.09823","DOI":"10.18653\/v1\/2025.findings-acl.770"},{"issue":"02","key":"11229_CR25","first-page":"243","volume":"21","author":"M Alqarni","year":"1970","unstructured":"Alqarni M (1970) Embedding search for quranic texts based on large language models. Int Arab J Inf Technol(IAJIT) 21(02):243\u2013256","journal-title":"Int Arab J Inf Technol(IAJIT)"},{"key":"11229_CR26","unstructured":"Gao Y, Xiong Y, Gao X, Jia K, Pan J, Bi Y, Dai Y, Sun J, Wang M, Wang H (2024) Retrieval-Augmented Generation for Large Language Models: A Survey. arXiv:2312.10997"},{"key":"11229_CR27","unstructured":"Zhong Z, Liu H, Cui X, Zhang X, Qin Z (2024) Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation. arXiv:2406.00456"},{"key":"11229_CR28","unstructured":"Wang L, Yang N, Huang X, Yang L, Majumder R, Wei F (2024) Multilingual e5 text embeddings: A technical report. arXiv preprint arXiv:2402.05672"},{"key":"11229_CR29","unstructured":"Acharya A, Murthy R, Kumar V, Sen J (2024) NLLB-E5: A Scalable Multilingual Retrieval Model. arXiv:2409.05401"},{"key":"11229_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/tacl_a_00530","volume":"11","author":"S Siriwardhana","year":"2023","unstructured":"Siriwardhana S, Weerasekera R, Wen E, Kaluarachchi T, Rana R, Nanayakkara S (2023) Improving the domain adaptation of retrieval augmented generation (RAG) models for open domain question answering. Trans Assoc Comput Linguist 11:1\u201317. https:\/\/doi.org\/10.1162\/tacl_a_00530","journal-title":"Trans Assoc Comput Linguist"},{"key":"11229_CR31","unstructured":"Douze M, Guzhva A, Deng C, Johnson J, Szilvasy G, Mazar\u00e9 P-E, Lomeli M, Hosseini L, J\u00e9gou H (2024) The Faiss library. arXiv:2401.08281"},{"key":"11229_CR32","unstructured":"Team S (2024) Silma. Silma. https:\/\/www.silma.ai"},{"key":"11229_CR33","unstructured":"Huang H, Yu F, Zhu J, Sun X, Cheng H, Song D, Chen Z, Alharthi A, An B, Liu Z, et al (2023) Acegpt, localizing large language models in arabic. arXiv preprint arXiv:2309.12053"},{"key":"11229_CR34","unstructured":"Team G, Georgiev P al (2024) Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv:2403.05160"},{"key":"11229_CR35","unstructured":"Team G (2024) Gemma: Open Models Based on Gemini Research and Technology. arXiv:2403.08295"},{"key":"11229_CR36","unstructured":"Saab K, Tu T, Weng W-H, Tanno R al, D.S (2024) Capabilities of Gemini Models in Medicine. arXiv:2404.18416"},{"key":"11229_CR37","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.11093524","author":"P Damodaran","year":"2024","unstructured":"Damodaran P (2024) FlashRank, Lightest and fastest 2nd stage Reranker for search pipelines. Zenodo. https:\/\/doi.org\/10.5281\/zenodo.11093524","journal-title":"Zenodo"},{"key":"11229_CR38","doi-asserted-by":"crossref","unstructured":"Wu S, Xiong Y, Cui Y, Wu H, Chen C, Yuan Y, Huang L, Liu X, Kuo T-W, Guan N, et al (2024) Retrieval-augmented generation for natural language processing: A survey. arXiv preprint arXiv:2407.13193","DOI":"10.21203\/rs.3.rs-6959723\/v1"},{"key":"11229_CR39","unstructured":"Eibich M, Nagpal S, Fred-Ojala A (2024) ARAGOG: Advanced RAG Output Grading. arXiv:2404.01037"},{"key":"11229_CR40","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu W-j (2002) Bleu: a method for automatic evaluation of machine translation, pp. 311\u2013318","DOI":"10.3115\/1073083.1073135"},{"key":"11229_CR41","unstructured":"Banerjee S, Lavie A (2005) METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In: Goldstein, J., Lavie, A., Lin, C.-Y., Voss, C. (eds.) Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation And\/or Summarization, pp. 65\u201372. Association for Computational Linguistics, Ann Arbor, Michigan. https:\/\/aclanthology.org\/W05-0909"},{"key":"11229_CR42","unstructured":"Powers DMW (2020) Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv:2010.16061"},{"key":"11229_CR43","unstructured":"Zhang T, Kishore V, Wu F, Weinberger KQ, Artzi Y (2020) BERTScore: Evaluating Text Generation with BERT. arXiv:1904.09675"},{"key":"11229_CR44","doi-asserted-by":"crossref","unstructured":"Zhu K, Luo Y, Xu D, Wang R, Yu S, Wang S, Yan Y, Liu Z, Han X, Liu Z, Sun M (2024) RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework. arXiv:2408.01262","DOI":"10.18653\/v1\/2025.acl-long.418"},{"key":"11229_CR45","unstructured":"OpenAI: GPT-4 Technical Report (2024). arXiv:2303.08774"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11229-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-025-11229-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11229-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T16:38:39Z","timestamp":1759595919000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-025-11229-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,2]]},"references-count":45,"journal-issue":{"issue":"25","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["11229"],"URL":"https:\/\/doi.org\/10.1007\/s00521-025-11229-y","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,2]]},"assertion":[{"value":"10 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 October 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The original online version of this article was revised to update the fourth author's affiliation details.","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}}]}}