Detecting Culture-Religious Hallucination of AI-Generated Feedback on EFL Students’ Argumentative Essay

Sari Dewi Noviyanti; Awwalia Fitratin Izza

Authors

Sari Dewi Noviyanti Universitas Islam Negeri (UIN) Walisongo Semarang
Awwalia Fitratin Izza Universitas Islam Negeri (UIN) Walisongo Semarang

Keywords:

AI Hallucination; EFL Essay Assessment; Generative Feedback; Large Language Models; Islamic Content

Abstract

The implications of using large language models (LLMs) in educational technology around generative feedback have positive and negative implications particularly when its content related to religion and culture. This study examines the patterns of hallucination in AI feedback towards Islamic content in EFL student essays in Islamic learning context. A systematic evaluation was conducted of five leading LLMs (ChatGPT, Claude, Grok, DeepSeek, and Gemini) using a newly created hallucination multi-type classification framework. The LLMs were prompt to provide feedback on EFL student essays containing Islamic content; then an evaluation was conducted to the responses using 6 types of hallucination indicators namely source fabrication, attribution errors, content misrepresentation, citation errors, contextual misapplication, and theological misstatement. This study found clear patterns of hallucination across all models, which ChatGPT generated the most errors and Claude Sonnet 4 produces the least errors in his feedback. While LLMs responded to the prompts with hallucination in some forms, the patterns and implications of hallucination were distinctly different across all examples. This information is valuable for educators and developers to consider regarding the legitimacy of AI feedback in religious contexts.

Downloads

Download data is not yet available.

References

Abbas, A., Tirumala, K., Simig, D., Ganguli, S., & Morcos, A. S. (2023). SemDeDup: Data-efficient learning at web-scale through semantic deduplication. aRxIV: Journal of Computer Science. https://doi.org/10.48550/arXiv.2303.09540.

Abbas, N. F., Qasim, T. A., & Jasim, H. A. S. (2023). Request Constructions in Classical Arabic versus Modern Arabic: A Corpus-based Study. Journal of Ethnic and Cultural Studies, 10(5), 1–15. https://doi.org/10.29333/ejecs/1598

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). https://doi.org/10.18860/ijazarabi.v8i1.28804

Abdelnour, M. G. (2025). Artificial Intelligence and the Islamic Theology of Technology: From “Means” to “Meanings” and from “Minds” to “Hearts.” Religions, 16(6), 796. https://doi.org/10.3390/rel16060796

Achruh, Rapi, M., Rusdi, M., & Idris, R. (2024a). Challenges and Opportunities of Artificial Intelligence Adoption in Islamic Education in Indonesian Higher Education Institutions. International Journal of Learning, Teaching and Educational Research, 23(11), 423–443. https://doi.org/10.26803/ijlter.23.11.22

Achruh, Rapi, M., Rusdi, M., & Idris, R. (2024b). Challenges and Opportunities of Artificial Intelligence Adoption in Islamic Education in Indonesian Higher Education Institutions. International Journal of Learning, Teaching and Educational Research, 23(11), 423–443. https://doi.org/10.26803/ijlter.23.11.22

Addzaky, K. U., Hasanah, U., Hasanah, I. F., & Asy’ari, M. (2025). Contextualizing Liberation Theology in Indonesian Religious Literature Through the Contributions of K.H. Abdurrahman Wahid. Jurnal Lektur Keagamaan, 23(1), 142–178. https://doi.org/10.31291/jlka.v23i1.1285

Ahmed Mohamed, F., Madihah Sheikh Abdul Aziz, & Murni Mahmud. (2023). Cues to Deception in Islamic Websites Text and Design. International Journal on Perceptive and Cognitive Computing, 9(1), 14–23. https://doi.org/10.31436/ijpcc.v9i1.299

Barnett, S., Kurniawan, S., Thudumu, S., Brannelly, Z., & Abdelrazek, M. (2024). Seven failure points when engineering a retrieval augmented generation system. Proceedings - 2024 IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI, CAIN 2024, 194–199. https://doi.org/10.1145/3644815.3644945

Berglund, L., Tong, M., Kaufmann, M., Balesni, M., Stickland, A. C., Korbak, T., & Evans, O. (2024). the Reversal Curse: Llms Trained on “a Is B” Fail To Learn “B Is a.” 12th International Conference on Learning Representations, ICLR 2024. https://doi.org/10.48550/arXiv.2309.12288.

Bobula, M. (2024). Generative artificial intelligence (AI) in higher education: a comprehensive review of challenges, opportunities, and implications. Journal of Learning Development in Higher Education, (30), 30. https://doi.org/10.47408/jldhe.vi30.1137

Casal-Otero, L., Catala, A., Fernández-Morante, C., Taboada, M., Cebreiro, B., & Barro, S. (2023). AI literacy in K-12: a systematic literature review. International Journal of STEM Education, 10(1), 29. https://doi.org/10.1186/s40594-023-00418-7

Deiniatur, M., & Hasanah, U. (2024). Multicultural Education of EFL Classrooms in Indonesian Islamic Higher Education: Challenges and Strategies. Pedagogy : Journal of English Language Teaching, 12(2), 158–177. https://doi.org/10.32332/joelt.v12i2.9542

Fathia Baresh, E. (2024). Incorporating Cultural Background in Teaching EFL Writing in Libyan: A Critical Literature Review. Al-Lisan, Vol. 9, pp. 1–16. https://doi.org/10.30603/al.v9i1.3811

Fitria, T. N. (2023). Artificial intelligence (AI) technology in OpenAI ChatGPT application: A review of ChatGPT in writing English essay. ELT Forum: Journal of English Language Teaching, 12(1), 44–58. https://doi.org/10.15294/elt.v12i1.64069

Ghufron, M. A., Rohman, T., & Aditia, M. R. (2024). English Language Teaching Materials and Religious Moderation in Indonesian Primary Schools: A Narrative Case Study. Lingua Cultura, 18(1), 141–153. https://doi.org/10.21512/lc.v18i1.11982

Ilyas, M., & Afzal, N. (2021). Teaching literary texts through cultural model to efl students. Eurasian Journal of Applied Linguistics, Vol. 7, pp. 22–30. https://doi.org/10.32601/ejal.911502

Kimsesiz, F. (2024). Reflections from Learners of English as a Foreign Language in a Multicultural Non-native Context. Acuity: Journal of English Language Pedagogy, Literature, and Culture, Vol. 9, p. 2024. Retrieved from https://jurnal.unai.edu/index.php/acuity

Kurata, L., Ayanwale, M. A., Molefi, R. R., & Sanni, T. (2025). Teaching religious studies with artificial intelligence: A qualitative analysis of Lesotho secondary schools teachers’ perceptions. International Journal of Educational Research Open, 8. https://doi.org/10.1016/j.ijedro.2024.100417

Lee, C., Kim, J., Lim, J. S., & Shin, D. (2025). Generative AI risks and resilience: How users adapt to hallucination and privacy challenges. Telematics and Informatics Reports, 19. https://doi.org/10.1016/j.teler.2025.100221

Li, J., Yuan, Y., & Zhang, Z. (2024). Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases. AirXv: Journal of Computer Science: Computation and Language. https://doi.org/10.48550/arXiv.2403.10446

Mahmud, M., & Abubakar, A. (2015). Investigating the act of deception in online-Islamic Content. Proceedings - 2014 3rd International Conference on User Science and Engineering: Experience. Engineer. Engage, i-USEr 2014, 242–247. Malaysia. https://doi.org/10.1109/IUSER.2014.7002710

Malik, S. A. (2023). Artificial Intelligence and Islamic Thought: Two Distinctive Challenges. Journal of Islamic and Muslim Studies, Vol. 8, pp. 108–115. https://doi.org/10.2979/jims.00020

Marzuki, Widiati, U., Rusdin, D., Darwin, & Indrawati, I. (2023). The impact of AI writing tools on the content and organization of students’ writing: EFL teachers’ perspective. Cogent Education, 10(2). https://doi.org/10.1080/2331186X.2023.2236469

Mohamed, A. M., Shaaban, T. S., Bakry, S. H., Guillén-Gámez, F. D., & Strzelecki, A. (2025). Empowering the Faculty of Education Students: Applying AI’s Potential for Motivating and Enhancing Learning. Innovative Higher Education, 50(2), 587–609. https://doi.org/10.1007/s10755-024-09747-z

Mozelius, P., Lindqvist, M. H., Cleveland-Innes, M., Jaldemark, J., & Sundgren, M. (2024). Educating the Educators on Generative Artificial Intelligence in Higher Education. Proceedings of the 4th International Conference on AI Research, ICAIR 2024, 4(1), 296–302. https://doi.org/10.34190/icair.4.1.3026

Putri, F. R., & Iswati, H. D. (2025). A qualitative exploration of students use of humata.ai to understand thesis literature: a cognitive load perspective. Wiralodra English Journal, 9(2), 166–179. https://doi.org/10.31943/wej.v9i2.471

Sharma, S., Mittal, P., Kumar, M., & Bhardwaj, V. (2025). The role of large language models in personalized learning: a systematic review of educational impact. Discover Sustainability, 6(1), 243. https://doi.org/10.1007/s43621-025-01094-z

Sun, Y., Sheng, D., Zhou, Z., & Wu, Y. (2024). AI hallucination: towards a comprehensive classification of distorted information in artificial intelligence-generated content. Humanities and Social Sciences Communications, 11(1), 1278. https://doi.org/10.1057/s41599-024-03811-x

Syuhda, N., Irwansyah, D., Adiwijaya, S. N., Harya, T. D., Deiniatur, M., & Septiyana, L. (2024). Contextualizing Islamic Traditions in English Language Teaching at Indonesian Islamic Higher Education. Forum for Linguistic Studies, 6(3), 260–273. https://doi.org/10.30564/fls.v6i3.6739

Tan, X., Cheng, G., & Ling, M. H. (2025). Artificial intelligence in teaching and teacher professional development: A systematic review. Computers and Education: Artificial Intelligence, 8. https://doi.org/10.1016/j.caeai.2024.100355

Vieriu, A. M., & Petrea, G. (2025). The Impact of Artificial Intelligence (AI) on Students’ Academic Development. Education Sciences, 15(3), 343. https://doi.org/10.3390/educsci15030343

Zhang, K. (2025). Enhancing Critical Writing Through AI Feedback: A Randomized Control Study. Behavioral Sciences, Vol. 15. Basel, Switzerland. https://doi.org/10.3390/bs15050600