Rhetoric, Creativity, and Machine Limits: ChatGPT 4.5 Plus as a Model for Comparing Human and AI-Generated Arabic Prose

Year 2025, Volume: 9 Issue: 2, 740 - 771, 30.06.2025

Mohammed Yaseen

https://doi.org/10.32711/tiad.1670986

Abstract

While recent advances in generative AI have significantly enhanced the fluency and coherence of machine-produced texts, questions remain regarding the extent to which such systems can emulate the creative, rhetorical, and cultural intricacies of human-authored Arabic prose. This study investigates this issue by focusing on a single advanced language model—ChatGPT 4.5 Plus—as a representative case. It juxtaposes AI-generated prose with selected works by Abdullah İbnü’l-Mukaffa‘, Mustafa Sâdık er-Râfîî, and Ğassân Kenefânî, examining stylistic and rhetorical features through a dual methodological lens: computational linguistic metrics and critical literary analysis. The findings suggest that although ChatGPT 4.5 Plus demonstrates commendable syntactic fluency and textual organization, it currently falls short in reproducing the semantic density, cultural embeddedness, and rhetorical subtlety that characterize human creativity. However, this limitation is understood not as a definitive judgment on AI’s potential, but rather as a reflection of the present capabilities of the studied model. The study concludes by highlighting the enduring significance of human experience in Arabic literary expression and advocates for the development of culturally responsive AI systems, trained on diverse Arabic corpora, to better complement human literary production in the future.

Keywords

Arabic Prose , Artificial Intelligence , Literary Creativity , Rhetorical Deviation , Generative Texts

Ethical Statement

This study was conducted in accordance with scientific and ethical principles. All sources used in the preparation of the article have been duly cited, and no part of the study involves plagiarism or unethical academic conduct. The author confirms that the manuscript is original, has not been published elsewhere, and is not under consideration by any other journal.

Supporting Institution

This study has not received any financial or logistical support from any institution or organization.

Thanks

I would like to express my sincere gratitude to all academic circles that provided scholarly guidance and encouragement throughout the research process. In particular, I extend my heartfelt thanks to the Editor-in-Chief and the esteemed Editorial Board for granting me the opportunity to have my article evaluated and considered for publication in their distinguished journal, which enjoys a high academic and international reputation.

Arapça Düz Yazıda Retorik ve Yaratıcılık Açısından İnsan ve Yapay Zeka (ChatGPT 4.5 Plus) Tarafından Üretilen Metinlerin Sınırlarının Karşılaştırmalı Analizi

Abstract

Bu çalışma, insan kaleminden çıkan Arapça nesrin yaratıcı ve retorik derinliğini üretken yapay zekânın — örnek olay olarak ChatGPT 4.5 Plus — ne ölçüde yansıtabildiğini incelemektedir. Model tarafından üretilen metinler, İbn Mukaffaʿ, Mustafa Sâdık er-Râfîî ve Ğassân Kenefânî’nin eserlerinden seçilen örneklerle karşılaştırılmıştır. İnceleme, hesaplamalı dilbilim ölçütleri ile modern Arap edebiyat eleştirisini birleştiren karma bir yöntem kullanır. Bulgular, modelin sözdizimsel akıcılık ve metinsel tutarlılıkta başarılı olduğunu, ancak insan yaratıcılığını belirleyen anlam zenginliği, kültürel derinlik ve retorik incelikleri henüz yeterince üretemediğini göstermektedir. Bu sınırlamalar, yapay zekânın nihai potansiyeline dair kesin bir yargı değil, incelenen modelin mevcut kabiliyetlerinin yansımasıdır. Çalışma, insan deneyiminin edebî üretimdeki kalıcı önemini vurgular ve çeşitli Arapça derlemelerle eğitilecek, kültürel açıdan duyarlı sistemlerin geliştirilmesini önermektedir.

Keywords

Arap Nesri , Yapay Zeka , Edebi Yenilik , Dilsel Sapma , Güncel Metinler

Ethical Statement

Bu çalışma, bilimsel ve etik ilkelere uygun olarak yürütülmüştür. Makalenin hazırlanmasında yararlanılan tüm kaynaklar usulüne uygun şekilde belirtilmiş olup, çalışmanın hiçbir bölümünde intihal veya etik dışı akademik bir davranış söz konusu değildir. Yazar, çalışmanın özgün olduğunu, daha önce başka bir yerde yayımlanmadığını ve başka bir dergide değerlendirme sürecinde olmadığını beyan eder.

Supporting Institution

Bu çalışma, herhangi bir kurum veya kuruluş tarafından maddi ya da lojistik olarak desteklenmemiştir.

Thanks

Araştırma süreci boyunca akademik rehberlik ve teşvik sağlayan tüm bilim çevrelerine en içten teşekkürlerimi sunarım. Özellikle, makalemin değerlendirilmesine ve saygın, yüksek akademik ve uluslararası itibara sahip dergilerinde yayımlanmasına imkân tanıdıkları için Baş Editöre ve kıymetli Editörler Kuruluna gönülden teşekkür ederim.

References

• Bahdanau, Dzmitry et al. “Neural Machine Translation by Jointly Learning to Align and Translate.” https://arxiv.org/abs/1409.0473
• Bender, Emily M. et al. “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. Virtual Event Canada: ACM, 2021. https://doi.org/10.1145/3442188.3445922
• Boden, Margaret A. - Boden, Margaret A. Creativity and Art: Three Roads to Surprise. Oxford, New York: Oxford University Press, 2010.
• Cevherî, İsmâil b. Hammâd el-. TÂCÜ’l-LUGA. 6 Volume. Beyrut: Dârü’l-ʿİlm li’l-Melâyîn, 2. bs., 1979.
• ChatGPT-4, OpenAI. “Compose a Fable in the Style of El-Edebü’l-Kebîr.” OpenAI, March 25, 2025.
• ChatGPT-4, OpenAI. “Compose a Short Story in the Style of Er-Râfîî’s ‘al-Aydī al-Mutawaḍḍiʾa’ from Vaḥyü’l-Ḳalem.” OpenAI, March 25, 2025.
• ChatGPT-4, OpenAI. “OpenAI, ChatGPT-4, Response to the Prompt: ‘Write a Story in the Style of Ğassân Kenefânî’s A World Not Ours’, Accessed 25 March 2025.” OpenAI, March 25, 2025.
• Gaffar, Hafiz - Albarashdi, Saleh. “Copyright Protection for AI-Generated Works: Exploring Originality and Ownership in a Digital Landscape.” Asian Journal of International Law 15/1 (January 2025), 23–46. https://doi.org/10.1017/S2044251323000735
• Gallego Cuiñas, Ana. “Literature Seen Through Big Data and Artificial Intelligence: Key Concepts and Critical Challenges.” Humanities and Big Data in Ibero-America. ed. Ana Gallego Cuiñas - Daniel Torres-Salinas. 25–42. De Gruyter, 2023. https://doi.org/10.1515/9783110753523-003
• Ğassân, Kenefânî. A World Not Ours. 1 Volume. Beyrut: Arab Research Foundation, 1st Ed., 1987.
• Ghassemiazghandi, Mozhgan. “An Evaluation of ChatGPT’s Translation Accuracy Using BLEU Score.” Theory and Practice in Language Studies 14/4 (April 29, 2024), 985–994. https://doi.org/10.17507/tpls.1404.07
• Hago Elmahdi, Omer Elsheikh - Mahyoub Hezam, Abdulrahman Mokbel. “Stylistic Use of Structural Meaning in Kanafani’s Men in the Sun.” English Literature and Language Review 66 (June 20, 2020), 92–98. https://doi.org/10.32861/ellr.66.92.98
• Hassim, Norillah Abdullah et al. JIMK. “[IBN AL-MUQAFFA’S SOCIOLOGICAL APPROACH IN AL-ADAB AL-KABIR]” Vol. 22 No. 3 (2021) (December 28, 2021), 8. https://doi.org/10.37231/jimk.2021.22.3.605
• Hatim, B. - Mason, Ian. Discourse and the Translator. London: Routledge, 1st Edition., 2014. https://doi.org/10.4324/9781315846583
• Heerden, Imke van - Bas, Anil. “A Perspective on Literary Metaphor in the Context of Generative AI.” arXiv, 2024. arXiv, DOI.org (Datacite). Accessed June 22, 2025. https://doi.org/10.48550/ARXIV.2409.01053
• İbn Fâris, Ebü’l-Hüseyn Ahmed. Muʿcemü Mekāyîsi’l-Luġa. 1 Volume. Beyrut: Dâru’l-Cîl, 6th Ed., 1979.
• İbn Manzûr, Muḥammed b. Mukrim. LİSÂNÜ’l-ARAB. 15 Volume. Beyrut: Dâr Ṣâdir, 3. bs., 1993.
• İbnü’l-Mukaffa‘, Abdullah. El-Edebü’l-Kebîr. Kahire: Hindâvî Eğitim ve Kültür Vakfı, 1st Ed., 2017.
• Abdul-Raof, Hussein. Arabic Rhetoric: A Pragmatic Analysis. 1 Volume. London: Routledge, 2011. https://www.routledge.com/Arabic-Rhetoric-A-Pragmatic-Analysis/Abdul-Raof/p/book/9780415663793
• Al-Shaibani, Maged S. - Ahmed, Moataz. “The Arabic AI Fingerprint: Stylometric Analysis and Detection of Large Language Models Text.” arXiv, 2025. arXiv, DOI.org (Datacite). Accessed June 22, 2025. https://doi.org/10.48550/ARXIV.2505.23276
• Alwajih, Fakhraddin et al. “Dallah: A Dialect-Aware Multimodal Large Language Model for Arabic.” Proceedings of The Second Arabic Natural Language Processing Conference. 320–336. Bangkok, Thailand: Association for Computational Linguistics, 2024. https://doi.org/10.18653/v1/2024.arabicnlp-1.27
• Atiyye, Muhammed et al. “A Lexical Database for Modern Standard Arabic Interoperable with a Finite State Morphological Transducer.” Systems and Frameworks for Computational Morphology. ed. Cerstin Mahlow - Michael Piotrowski. 100/98–118. Communications in Computer and Information Science. Berlin, Heidelberg: Springer Berlin Heidelberg, 2011. https://doi.org/10.1007/978-3-642-23138-4_7
• Bahdanau, Dzmitry et al. “Neural Machine Translation by Jointly Learning to Align and Translate.” https://arxiv.org/abs/1409.0473
• Bender, Emily M. et al. “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. Virtual Event Canada: ACM, 2021. https://doi.org/10.1145/3442188.3445922
• Boden, Margaret A. - Boden, Margaret A. Creativity and Art: Three Roads to Surprise. Oxford, New York: Oxford University Press, 2010.
• Cevherî, İsmâil b. Hammâd el-. TÂCÜ’l-LUGA. 6 Volume. Beyrut: Dârü’l-ʿİlm li’l-Melâyîn, 2. bs., 1979.
• ChatGPT-4, OpenAI. “Compose a Fable in the Style of El-Edebü’l-Kebîr.” OpenAI, March 25, 2025.
• ChatGPT-4, OpenAI. “Compose a Short Story in the Style of Er-Râfîî’s ‘al-Aydī al-Mutawaḍḍiʾa’ from Vaḥyü’l-Ḳalem.” OpenAI, March 25, 2025.
• ChatGPT-4, OpenAI. “OpenAI, ChatGPT-4, Response to the Prompt: ‘Write a Story in the Style of Ğassân Kenefânî’s A World Not Ours’, Accessed 25 March 2025.” OpenAI, March 25, 2025.
• Gaffar, Hafiz - Albarashdi, Saleh. “Copyright Protection for AI-Generated Works: Exploring Originality and Ownership in a Digital Landscape.” Asian Journal of International Law 15/1 (January 2025), 23–46. https://doi.org/10.1017/S2044251323000735
• Gallego Cuiñas, Ana. “Literature Seen Through Big Data and Artificial Intelligence: Key Concepts and Critical Challenges.” Humanities and Big Data in Ibero-America. ed. Ana Gallego Cuiñas - Daniel Torres-Salinas. 25–42. De Gruyter, 2023. https://doi.org/10.1515/9783110753523-003
• Ğassân, Kenefânî. A World Not Ours. 1 Volume. Beyrut: Arab Research Foundation, 1st Ed., 1987.
• Ghassemiazghandi, Mozhgan. “An Evaluation of ChatGPT’s Translation Accuracy Using BLEU Score.” Theory and Practice in Language Studies 14/4 (April 29, 2024), 985–994. https://doi.org/10.17507/tpls.1404.07
• Hago Elmahdi, Omer Elsheikh - Mahyoub Hezam, Abdulrahman Mokbel. “Stylistic Use of Structural Meaning in Kanafani’s Men in the Sun.” English Literature and Language Review 66 (June 20, 2020), 92–98. https://doi.org/10.32861/ellr.66.92.98
• Hassim, Norillah Abdullah et al. JIMK. “[IBN AL-MUQAFFA’S SOCIOLOGICAL APPROACH IN AL-ADAB AL-KABIR]” Vol. 22 No. 3 (2021) (December 28, 2021), 8. https://doi.org/10.37231/jimk.2021.22.3.605
• Hatim, B. - Mason, Ian. Discourse and the Translator. London: Routledge, 1st Edition., 2014. https://doi.org/10.4324/9781315846583
• Heerden, Imke van - Bas, Anil. “A Perspective on Literary Metaphor in the Context of Generative AI.” arXiv, 2024. arXiv, DOI.org (Datacite). Accessed June 22, 2025. https://doi.org/10.48550/ARXIV.2409.01053
• İbn Fâris, Ebü’l-Hüseyn Ahmed. Muʿcemü Mekāyîsi’l-Luġa. 1 Volume. Beyrut: Dâru’l-Cîl, 6th Ed., 1979.
• İbn Manzûr, Muḥammed b. Mukrim. LİSÂNÜ’l-ARAB. 15 Volume. Beyrut: Dâr Ṣâdir, 3. bs., 1993.
• İbnü’l-Mukaffa‘, Abdullah. El-Edebü’l-Kebîr. Kahire: Hindâvî Eğitim ve Kültür Vakfı, 1st Ed., 2017.
• Kaabi, Moza H. Al et al. “Developing the Teaching Arabic Rhetoric: A Comparative Analysis of Artificial Intelligence and Traditional Hermeneutical Approaches.” Journal of Infrastructure, Policy and Development 8/15 (December 11, 2024), 9925. https://doi.org/10.24294/jipd9925
• Kadaoui, Karima et al. “TARJAMAT: Evaluation of Bard and ChatGPT on Machine Translation of Ten Arabic Varieties.” Proceedings of ArabicNLP 2023. 52–75. Singapore (Hybrid): Association for Computational Linguistics, 2023. https://doi.org/10.18653/v1/2023.arabicnlp-1.6
• McCarthy, Philip M. - Jarvis, Scott. “MTLD, Vocd-D, and HD-D: A Validation Study of Sophisticated Approaches to Lexical Diversity Assessment.” Behavior Research Methods 42/2 (May 2010), 381–392. https://doi.org/10.3758/BRM.42.2.381
• Mousi, Basel et al. “AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs.” arXiv, 2024. arXiv, DOI.org (Datacite). Accessed June 22, 2025. https://doi.org/10.48550/ARXIV.2409.11404
• Naous, Tarek - Xu, Wei. “On The Origin of Cultural Biases in Language Models: From Pre-Training Data to Linguistic Phenomena.” arXiv, 2025. arXiv, DOI.org (Datacite). Accessed June 22, 2025. https://doi.org/10.48550/ARXIV.2501.04662
• Nida, Eugene A. (Eugene Albert). The Theory and Practice of Translation. Leiden, E.J. Brill, 1st Ed., 1969. http://archive.org/details/theorypracticeof0000unse_p0n2
• Noam, Chomsky. Aspects of the Theory of Syntax. UK: Cambridge, MA: MIT Press, 50th Edition., 1965. https://mitpress.mit.edu/9780262527408/aspects-of-the-theory-of-syntax/
• Premkumar, Bindu. “The Impact of Artificial Intelligence on Literary Creation and Criticism: Emerging Trends and Implications.” International Journal of Language, Literature and Culture 4/4 (2024), 37–41. https://doi.org/10.22161/ijllc.4.4.5
• Propp, V. Morphology of the Folktale. 1 Volume. United States of America: the American Folklore Society and Indiana University, 1st Ed., 1968.
• Râfîî, Mustafa Sâdık er-. Vaḥyü’l-Ḳalem. 1 Volume. Londra: Hindavi Kültür ve Eğitim Vakfı, 1st Ed., 2014.
• Rockhill, Paul. The Reception Theory of Hans Robert Jauss: Theory and Application. Oregon , United States: Portland State University. Department of History., Master Of Arts (M.A.) In History, 2000. https://doi.org/10.15760/etd.7029
• Shahmerdanova, Roya. “Artificial Intelligence in Translation: Challenges and Opportunities.” Acta Globalis Humanitatis et Linguarum 2/1 (January 11, 2025), 62–70. https://doi.org/10.69760/aghel.02500108
• Tian, Yufei et al. “Are Large Language Models Capable of Generating Human-Level Narratives?” arXiv, 2024. arXiv, DOI.org (Datacite). Accessed June 22, 2025. https://doi.org/10.48550/ARXIV.2407.13248
• Umar, Ahmed Muḫtâr. Muʿcemu’l-Luġa el-ʿArabiyye el-Muʿāsıra. 1 Volume. Kahire: Ālemü’l-Kütüb, 1. bs., 2008.
• Venuti, Lawrence. The Translator’s Invisibility. London: Routledge, 1st Ed., 2003. https://doi.org/10.4324/9780203360064
• work(s):, E. Paul Torrance Reviewed. “Scientific Views of Creativity and Factors Affecting Its Growth.” Daedalus 94/3, (1965), 663–681.
• Yang, Liwei - Zhou, Guijun. “A Semantic Similarity Analysis of Multiple English Translations of The Analects: Based on a Natural Language Processing Algorithm.” Frontiers in Psychology 13 (November 10, 2022), 992890. https://doi.org/10.3389/fpsyg.2022.992890
• Yenice, Mehmet. Klasik ve Çağdaş Dönemlerde Anlam Bileşenleri - Abdülkâhir el-Cürcânî ve Temmâm Hassân Üzerine Bir Araştırma ve Karşılaştırma. Ankara: İlahiyat Yayınları, 1st Ed., 2021. https://www.ilahiyatyayin.com/klasik-ve-cagdas-donemlerde-anlam-bilesenleri-abdulkahir-el-curcani-ve-temmam-hassan-uzerine-bir-arastirma-ve-karsilastirma/