Interpreting Anthropomorphic Qur'anic Verses through Artificial Intelligence: A Comparative Study of ChatGPT and Gemini
DOI:
https://doi.org/10.58518/alfurqan.v9i1.5045Keywords:
Artificial Intelligence, Anthropomorphic Qur'anic Verses, Chatgpt, Gemini, Qur'anic TranslationAbstract
The rapid adoption of generative artificial intelligence (AI) has expanded its application to Qur'anic translation and interpretation, raising important questions regarding the reliability of AI-generated outputs for theologically sensitive verses. Among the most challenging passages are anthropomorphic (mutashābihāt) verses, whose translation requires careful negotiation between literal meaning and established theological traditions. This study compares the translation strategies employed by ChatGPT and Gemini in rendering anthropomorphic Qur'anic expressions and evaluates the consistency of their outputs across repeated interactions. This research employs a qualitative comparative design using library research and content analysis. Four categories of anthropomorphic expressions—wajh (face), aʿyun (eyes), yad (hand), and istawā (rising over the Throne)—were translated repeatedly by both AI systems using identical prompts administered in different sessions. The resulting outputs were classified into three interpretive approaches: literal translation, ta'wīl (figurative interpretation), and tafwīḍ (consigning the ultimate meaning to God). Comparative analysis was then conducted to examine translation preferences and output consistency. The findings demonstrate substantial differences in theological translation strategies between the two AI models. ChatGPT predominantly adopts literal translation (39 of 72 outputs), followed by ta'wīl (19) and tafwīḍ (14), whereas Gemini produces more literal renderings (42 of 72 outputs) together with ta'wīl (30) but does not employ tafwīḍ. ChatGPT also exhibits strategy shifts across repeated sessions, particularly in translating istawā, where responses change from tafwīḍ to literal interpretation. By contrast, Gemini maintains comparatively stable translation patterns despite relying primarily on literal formulations. These findings indicate that generative AI systems differ not only linguistically but also in their implicit theological orientation when processing anthropomorphic Qur'anic expressions. This study contributes to the emerging field of digital Qur'anic studies by providing a systematic framework for evaluating AI translation strategies from a theological perspective. It demonstrates that AI-generated Qur'anic translations should not be regarded as doctrinally neutral, particularly when dealing with verses carrying significant theological implications. The study is limited to two large language models and four categories of anthropomorphic expressions. Future research should expand comparisons to additional AI systems, multilingual translation settings, and broader corpora of mutashābihāt verses to develop more comprehensive evaluation standards for AI-assisted Qur'anic interpretation.
References
Abdalhussein, H. F. (2025). Comparative analysis of AI and human translations of Qur'anic legal verses in Surah Al-Ma'idah. Ijaz Arabi: Journal of Arabic Learning, 8(1), 262–275. https://doi.org/10.18860/ijazarabi.v8i1.28804
Abubakari, M. S. (2025). Generative AI in contemporary Islamic religious education discourse: Revelation meets algorithm. In Intersections of AI and Freedom of Religion or Belief.
Ahmad, S. (2017). Urgensi siyaq dalam penafsiran Al-Qur'an. Syi'ar: Jurnal Ushuluddin, Adab, dan Dakwah, 17(1), 119–128.
Al Bayan, A. (2020). Studi kritis terjemah Al-Qur'an Depag RI (Telaah terhadap ayat-ayat mutasyabihat dan aqidah dalam perspektif NU). Jurnal Syntax Admiration, 1(6), 638–655.
Al-Azani, S., Abudalfa, S., & Samma, H. (2026). A comprehensive review of artificial intelligence in Qur'anic research: Trends, methods, challenges, and future directions. Information Processing & Management.
Ali, T. M., Habiter, Z. A., Ahmed, H. A., & Mijbel, Y. K. (2025). Utilization of artificial intelligence applications in Islamic religious and belief services. Lecture Notes in Networks and Systems.
Alkhouri, K. I. (2025). Spiritual confusion in the era of artificial intelligence: A psychology of religion perspective. International Review of Psychiatry.
Al-Qatthan, M. K. (n.d.). Mabāḥith fī 'Ulūm al-Qur'ān (7th ed.). Maktabah Wahbah.
Arif, M., Abd Aziz, M. K. N., Hassan, H., & Rismawati, B. V. (2026). Artificial intelligence in Islamic religious education: A PRISMA-based review and SEI-CHAT framework. Online Learning in Educational Research.
Astor, A., Khir-Allah, G., & Martínez-Cuadros, R. (2024). Anonymity and digital Islamic authority. Religions.
Atallah, F. A. (2026). Digital mediation and fatwa authority in contemporary Islam: A critical Islamic legal and media-theoretical framework. Religions.
Azhar, M. H. M., Bakri, M. F. M., Ahmad, K., & Rosele, M. I. (2025). Ethics and limitations of artificial intelligence (AI) in Qur'anic interpretation according to the epistemological framework of Islamic knowledge. Quranica.
Badan Pengembangan dan Pembinaan Bahasa. (2023). Kamus Besar Bahasa Indonesia. Kementerian Pendidikan, Kebudayaan, Riset, dan Teknologi Republik Indonesia. https://kbbi.kemdikbud.go.id/
Bahri, I. S. (2020). Konsep mayoritas Ahlussunnah Wal Jamaah. Bahasa Rakyat.
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021). On the dangers of stochastic parrots: Can language models be too big? Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, 610–623. https://doi.org/10.1145/3442188.3445922
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., Brynjolfsson, E., Buch, S., Card, D., Castellon, R., Chatterji, N., Chen, A., Creel, K., Davis, J. Q., Demszky, D., ... Liang, P. (2021). On the opportunities and risks of foundation models. Stanford Center for Research on Foundation Models. https://doi.org/10.48550/arXiv.2108.07258
Broughton, V. (2019). The roles of intellectual creativity and automation in representing diversity: Human and machine bias. Knowledge Organization, 46(6), 450–462.
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., ... Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901.
Campbell, H. A. (2020). Digital creators and rethinking religious authority. Routledge.
Campbell, H. A. (2022). Approaching religious authority through the emergence of new forms of online leadership. In The Oxford Handbook of Digital Religion. Oxford University Press.
Carbajal, I. (2025). Exploring the digital boundaries of religion: An analysis of the limits of artificial intelligence and theology. Cuadernos de Teología.
Dia, M. (2025). Large language models and translation practice: Opportunities and challenges. Journal of Language and Artificial Intelligence.
Dong, X. (2025). A multi-time and multi-perspective selection framework for machine translation based on large language models. In Proceedings of the 2025 4th International Conference on Intelligent Mechanical and Human-Computer Interaction Technology (IHCIT 2025).
Dzulraidi, D. H., Jalil, A. A., & Sin, M. L. M. (2025). Ketepatan ChatGPT dalam terjemahan Al-Quran: Analisis perbandingan dengan terjemahan autoritatif. QURANICA: International Journal of Quranic Research, 14(Special Issue), 21–52.
Fathan, M. A. R., Mubina, A. F., Ramadhan, P. G., Fahma, A. W., & Nurrohim, A. (2025). Kritik interpretasi tafsir toleransi beragama berdasar artificial intelligence: Studi komparatif ChatGPT dan Gemini AI. TASHDIQ: Jurnal Kajian Agama dan Dakwah, 15(1). https://doi.org/10.3783/tashdiqv2i9.2461
Fitryansyah, M. A., & Fauziah, F. N. (2024). Bridging tradition and technology: Artificial intelligence in the interpretation of Indonesian religious manuscripts. Jurnal Lektur Keagamaan.
Herrera-Poyatos, D., Peláez-González, C., Zuheros, C., Herrera-Poyatos, A., Tejedor, V., Herrera, F., & Montes, R. (2025). An overview of model uncertainty and variability in LLM-based sentiment analysis: Challenges, mitigation strategies, and the role of explainability. Frontiers in Artificial Intelligence, 8, 1609097. https://doi.org/10.3389/frai.2025.1609097
Issa, M. A. J. (2026). Employing artificial intelligence for the use of the redundant "min" according to Al-Samin Al-Halabi in his book Al-Durr Al-Masun fi al-'Ulum al-Kitab al-Maknun. Lecture Notes in Networks and Systems.
Kannike, U. M. M., & Fahm, A. O. (2025). Exploring artificial intelligence ethical governance from an Islamic ethics perspective. Journal of Fiqh.
Kim, M. (2015). Dynamic equivalence and its application in translation studies. Journal of Translation Studies.
Lala. (2025). Islamic guidance and artificial intelligence: An epistemological perspective. Philosophy & Technology.
Lohlker, R., & Wahid, S. H. (2026). Transformation of Islamic religious authority. Religions.
Messina, A., & Scotta, S. (2026). Introducing background temperature to characterise hidden randomness in large language models. Transactions on Machine Learning Research.
Muhamad, F. N., Yaakob, M. A., Abdullah, M. R., Mohamad, N., & Basarud-din, S. K. (2025). Model kecerdasan buatan bagi penjanaan pengajaran surah Al-Quran melalui pendekatan tafsir interaktif berasaskan pemprosesan bahasa semula jadi dan pembelajaran mesin. QURANICA: International Journal of Quranic Research, 14(Special Issue), 1–20.
Nida, E. A., & Taber, C. R. (1982). The theory and practice of translation. E. J. Brill.
Nord, C. (2006). Translating as a purposeful activity: Functionalist approaches explained. St. Jerome Publishing.
Nord, C. (2022). Skopos theory and functional translation. In The Routledge Handbook of Translation Studies. Routledge.
Olatoye, A. A., & Tella, A. (2026). A comprehensive review of artificial intelligence usage patterns in information generation among theologians. Journal of Religious Information and Theology.
Omar, N. H., & Ibrahim, M. (2019). Evaluation of Muslim scholars on the method of interpretations of verses on divine attributes by contemporary Salafi school. International Journal of Islamic Thought.
Purnomo, B. (2020). Metode tafwidh dan takwil diterapkan dalam Terjemahan Al-Qur'an Edisi Penyempurnaan Tahun 2019. https://lajnah.kemenag.go.id/
Putrawan, B. K. (2025). From prayer to data: The transformation of theology in the age of artificial intelligence and its implications for religious practice. Transformation.
Qaruty, R. A., Alqaruty, S., Al-Tkhayneh, K. M., & Abdel Hadi, S. (2025). Artificial intelligence and Islamic jurisprudence: Ethical, legal, and theological considerations. In Proceedings of the International Conference on Cyber Security and AI-Based Systems (Cyber-AI 2025).
Senin, N., Hambali, K. M. K., Ramli, W. A. W., ... & Ismail, N. (2023). Anthropomorphism according to Al-Ghazali (d. 1111) and Maimonides (d. 1204): A comparative discourse. HTS Teologiese Studies/Theological Studies.
Statcounter Global Stats. (2026). AI chatbot market share worldwide.
Sun, Y., et al. (2025). Large language models in translation: A review of capabilities, challenges, and future directions. Machine Translation Journal.
Tatan, A., & Al-Kailani, M. A. (n.d.). 'Aun al-Murīd li Sharḥ Jawharat al-Tawḥīd fī 'Aqīdah Ahl al-Sunnah wa al-Jamā'ah (Vol. 1). Dar al-Basya'ir.
Wahid, S. H., & Abdulloh, S. (2026). Digital Islamic authority: Revolutionary shift or mere hype? A systematic review. SN Social Sciences.
Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., Metzler, D., Chi, E., Hashimoto, T., Vinyals, O., Liang, P., Dean, J., & Fedus, W. (2022). Emergent abilities of large language models. Transactions on Machine Learning Research, 2022, 1–30. https://openreview.net/forum?id=yzkSU5zdwD
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Al Furqan: Jurnal Ilmu Al Quran dan Tafsir
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
2.png)
