Rekonstruksi Metodologi Verifikasi Hadis Berbantuan Artificial Intelligence
Integrasi Takhrij, Kritik Sanad-Matan dan Human-In-The-Loop
DOI:
https://doi.org/10.47945/tasamuh.v18i2.3321Keywords:
Hadith Verification, Artificial Intelligence, Human-In-The-Loop, Takhrīj, HallucinationAbstract
Classical hadith verification requires rigorous takhrīj, isnād criticism, and matn criticism. Meanwhile, the application of artificial intelligence (AI) in hadith studies remains fragmented across specific technical tasks and faces risks of hallucination, including fabricated hadith, incorrect attribution, hybrid hadith, and distortion of meaning. This article aims to formulate an AI-assisted methodological framework for hadith verification that integrates computational capabilities with the principles of uṣūl al-ḥadīth through a human-in-the-loop mechanism. This qualitative library research employs an integrative descriptive-analytical approach by examining studies on AI and hadith alongside the principles of uṣūl al-ḥadīth. The findings show that AI can assist takhrīj, isnād mapping, semantic analysis of matn, and hadith quality classification. However, AI outputs remain provisional and cannot replace assessments of ʿadālah, ḍabṭ, or determinations of hadith status. The risks of citation fabrication and hallucination in generative LLMs require auditing at every verification stage. The study proposes six stages: AI-assisted takhrīj, primary source verification, computationally assisted isnād criticism, text-assisted matn criticism, hadith quality assessment, and citation and hallucination auditing, with a feedback mechanism to previous stages when discrepancies are identified. Human-in-the-loop serves as an epistemic validation mechanism to ensure that AI functions as a methodological aid rather than an autonomous authority in determining hadith validity.
Downloads
References
Alghamdi, J., Albukhari, A., & Al-Dala’in, T. (2025). Pretrained Models Against Traditional Machine Learning for Detecting Fake Hadith. Electronics, 14(17), 3484. https://doi.org/10.3390/electronics14173484
Azis, A., Nur, H., Nasir, M., & Supriadi, A. (2026). Metodologi Hadits di Era Modern : Urgensi Kritik Sanad dan. SUJUD: Jurnal Agama, Sosial, dan Budaya, 2(3), 1447–1451. https://doi.org/10.63822/V5VBW165
Azwar, Usman, A. H., & Abdullah, M. F. R. (2025). Reimagining Hadith Scholarship in the Age of Artificial Intelligence: Insights from a PRISMA-Based Systematic Literature Review. e-Jurnal Penyelidikan dan Inovasi, 12(6), 43–66. https://doi.org/10.53840/ejpi.v12i6.333
Bakir, & Elmunsyah, H. (2025). Comparative Analysis of the Risk of Hadith Errors in Question-Answering Systems Based on Large Language Models. International Journal of Research and Scientific Innovation, 12(12), 262–272. https://doi.org/10.51244/IJRSI.2025.12120025
Farooqi, A. M., Malick, R. A. S., Shaikh, M. S., & Akhunzada, A. (2024). Multi-IsnadSet MIS for Sahih Muslim Hadith with chain of narrators, based on multiple ISNAD. Data in Brief, 54, 110439. https://doi.org/10.1016/j.dib.2024.110439
Lazaros, K., Vrahatis, A. G., & Kotsiantis, S. (2026). Human-in-the-Loop Artificial Intelligence: A Systematic Review of Concepts, Methods, and Applications. Entropy, 28(4), 377. https://doi.org/10.3390/e28040377
Mahmoud, S., Saif, O., Nabil, E., Abdeen, M., ElNainay, M., & Torki, M. (2022). AR-Sanad 280K: A Novel 280K Artificial Sanads Dataset for Hadith Narrator Disambiguation. Information, 13(2), 55. https://doi.org/10.3390/info13020055
Rohman, T., Huda, U., & Hartono. (2020). Methodology of Hadith Research: The Study of Hadith Criticism. Journal of Hadith Studies, 2(1), 73–84. https://doi.org/10.32506/johs.v2i1.26
Suhartawan, B. (2024). Memahami Konsep Metodologi Al-Jarh Wa Ta’dil. DIRAYAH : Jurnal Ilmu Hadis, 4(2), 190–206. https://doi.org/10.62359/dirayah.v4i2.263
Suppadungsuk, S., Thongprayoon, C., Krisanapan, P., Tangpanithandee, S., Valencia, O. G., Miao, J., Mekraksakit, P., Kashani, K., & Cheungpasitporn, W. (2023). Examining the Validity of ChatGPT in Identifying Relevant Nephrology Literature: Findings and Implications. Journal of Clinical Medicine, 12(17), 5550. https://doi.org/10.3390/jcm12175550
Walters, W. H., & Wilder, E. I. (2023). Fabrication and errors in the bibliographic citations generated by ChatGPT. Scientific Reports 2023 13:1, 13(1), 14045. https://doi.org/10.1038/s41598-023-41032-5




