Artificial Intelligence-Based ESP (English For Specific Purposes) Tutor Applications For Science And Engineering Undergraduate Students In Saudi Arabia
DOI:
https://doi.org/10.29284/zgeq5y45Keywords:
ESP writing; retrieval-augmented generation; large language models; academic writing support; Saudi higher education; vector databases; AI tutors; Arabic-English context.Abstract
While the emergence of artificial intelligence brings changes to the domain of academic assistance, the presence of academic communication continuesin the contexts of foreign language learning, information studies, and human computer interaction. This work considers the usage of AI-driven computing applications used by university students for their assignments related to English for Specific Purposes in science and engineering courses at Saudi higher education establishments. Though the emphasis is made on scientific studies focused on advances in terms of better searching algorithms and language models, no attention is given to chatbot systems that provide students with generic tips on how to write essays. The purpose of this study is to discuss important features involved in designing, teaching, evaluating, and the contextual application of AI tutoring tools. Academic journals and papers written within the scope of interest from 2020 until 2025 were obtained from scholarly indexes. Next, the sources were subject to thematic narrative analysis. Thus, even though the capability of open-ended text production seems promising, computing designs based on fine-tuning language models, embeddings, vector searches, segmenting/indexing approaches, hybrid searches, re-ranking, and prompt handling appear the most reliable way to build an AI tutor in terms of contextualized comments on grammar, coherence, argumentative writing, citation, and writing style. Moreover, it can be stated that hallucination prevention, appropriate source referencing, fairness, security, and Arabic-English dual language tutoring are key principles for building AI tutors. However, as observed from the literature review, there are still inconsistencies concerning criteria and measuring the assessment of writing skills, autonomy, and management.
References
1. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474.
2. Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W.-t. (2020). Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 6769–6781). Association for Computational Linguistics.
3. Khattab, O., & Zaharia, M. (2020). ColBERT: Efficient and effective passage search via contextualized late interaction over BERT. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 39–48). ACM.
4. Santhanam, K., Khattab, O., Saad-Falcon, J., Potts, C., & Zaharia, M. (2022). ColBERTv2: Effective and efficient retrieval via lightweight late interaction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 3715–3734). Association for Computational Linguistics.
5. Lin, S., Hilton, J., & Evans, O. (2022). TruthfulQA: Measuring how models mimic human falsehoods. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 3214–3252). Association for Computational Linguistics.
6. Ali, F., Choy, D., Divaharan, S., Tay, H. Y., & Chen, W. (2023). Supporting self-directed learning and self-assessment using TeacherGAIA, a generative AI chatbot application: Learning approaches and prompt engineering. Learning: Research and Practice, 9(2), 135–147.
7. Kohnke, L., Moorhouse, B. L., & Zou, D. (2023). ChatGPT for language teaching and learning. RELC Journal, 54(2), 537–550.
8. UNESCO. (2023). Guidance for generative AI in education and research. UNESCO.
9. Asai, A., Wu, Z., Wang, Y., Sil, A., &Hajishirzi, H. (2024). Self-RAG: Learning to retrieve, generate, and critique through self-reflection. In Proceedings of the International Conference on Learning Representations (ICLR 2024).
10. Pan, J. J., Wang, J., & Li, G. (2024). Survey of vector database management systems. The VLDB Journal, 33, 1591–1615.
11. Warschauer, M., & Xu, Y. (2024). Generative AI for language learning: Entering a new era. Language Learning & Technology, 28(2), 1–4.
12. Levine, S., Beck, S. W., Mah, C., Phalen, L., & Pittman, J. (2024). How do students use ChatGPT as a writing support? Journal of Adolescent & Adult Literacy. Advance online publication.
13. Wang, C., Li, Z., & Bonk, C. J. (2024). Understanding self-directed learning in AI-assisted writing: A mixed methods study of postsecondary learners. Computers and Education: Artificial Intelligence, 6, 100247.
14. Mohamed, A. M. (2024). Exploring the potential of an AI-based chatbot (ChatGPT) in enhancing English as a foreign language teaching: Perceptions of EFL faculty members. Education and Information Technologies, 29, 3195–3217.
15. Sobaih, A. E. E., Elshaer, I. A., &Hasanein, A. M. (2024). Examining students’ acceptance and use of ChatGPT in Saudi Arabian higher education. European Journal of Investigation in Health, Psychology and Education, 14(3), 709–721.
16. Lo, C. K., Yu, P. L. H., Xu, S., Ng, D. T. K., & Jong, M. S.-Y. (2024). Exploring the application of ChatGPT in ESL/EFL education and related research issues: A systematic review of empirical studies. Smart Learning Environments, 11, 50.
17. Lee, S., Cai, Y., Meng, D., Wang, Z., & Wu, Y. (2024). Unleashing large language models’ proficiency in zero-shot essay scoring. In Findings of the Association for Computational Linguistics: EMNLP 2024 (pp. 181–198). Association for Computational Linguistics.
18. Nair, I. J., Tan, J., Su, X., Gere, A., Wang, X., & Wang, L. (2024). Closing the loop: Learning to generate writing feedback via language model simulated student revisions. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (pp. 16636–16657). Association for Computational Linguistics.
19. Yu, Y., Ping, W., Liu, Z., Wang, B., You, J., Zhang, C., Shoeybi, M., & Catanzaro, B. (2024). RankRAG: Unifying context ranking with retrieval-augmented generation in LLMs. In Advances in Neural Information Processing Systems.
20. Doan, N. N., Härmä, A., Celebi, R., & Gottardo, V. (2024). A hybrid retrieval approach for advancing retrieval-augmented generation systems. In Proceedings of the 7th International Conference on Natural Language and Speech Processing (ICNLSP 2024) (pp. 397–409). Association for Computational Linguistics.
21. Zhong, Z., Liu, H., Cui, X., Zhang, X., & Qin, Z. (2025). Mix-of-granularity: Optimize the chunking granularity for retrieval-augmented generation. In Proceedings of the 31st International Conference on Computational Linguistics (pp. 5756–5774). Association for Computational Linguistics.
22. Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Yang, Q., Gao, Y., Yu, J., Zhou, Y., & others. (2025). A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Computing Surveys, 58(1), Article 9.
23. Zhang, Y., Li, Y., Cui, L., Cai, D., Liu, L., Fu, T., Huang, X., Zhao, E., Zhang, Y., Chen, Y., Shi, F., Xie, C., Fang, H.-S., & others. (2025). A survey on hallucination in large language models. Computational Linguistics, 51(4), 1373–1416.
24. Li, Z., Wang, Z., Wang, W., Hung, K., Xie, H., & Wang, F. L. (2025). Retrieval-augmented generation for educational application: A systematic survey. Computers and Education: Artificial Intelligence, 8, 100417.
25. Maurya, K. K., Srivatsa, K. A., Petukhova, K., & Kochmar, E. (2025). Unifying AI tutor evaluation: An evaluation taxonomy for pedagogical ability assessment of LLM-powered AI tutors. In Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) (pp. 1234–1251). Association for Computational Linguistics.
26. Seo, H., Kim, J., Lee, H., & Kim, Y. (2025). Large language models as evaluators in education: Verification of feedback consistency and accuracy. Applied Sciences, 15(2), 671.
27. Ghazawi, R., & Simpson, E. (2025). How well can LLMs grade essays in Arabic? Computers and Education: Artificial Intelligence, 8, 100389.
28. Alsofyani, A. H., &Barzanji, A. M. (2025). The effects of ChatGPT-generated feedback on Saudi EFL learners’ writing skills and perception at the tertiary level: A mixed-methods study. Journal of Educational Computing Research, 63.
29. Lee, D., & Palmer, E. (2025). Prompt engineering in higher education: A systematic review to help inform curricula. International Journal of Educational Technology in Higher Education, 22, 7.
30. Qian, Y. (2025). Prompt engineering in education: A systematic review of approaches and educational applications. Journal of Educational Computing Research, 63(7–8), 1782–1818.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
