The Impact of Contextual Prompting on LLM Translation Accuracy in Educational Sciences: An Exploratory Case Study of ChatGPT Pro

Mayssaa Moukatib; Rajae Khaloufi

doi:10.63939/ajts.9ggs0y80

Authors

Mayssaa Moukatib Abdelmalek Essaâdi, Tangier, Morocco Author https://orcid.org/0009-0004-9055-4169
Rajae Khaloufi Abdelmalek Essaâdi, Tangier, Morocco Author https://orcid.org/0009-0001-6624-3019

DOI:

https://doi.org/10.63939/ajts.9ggs0y80

Keywords:

Prompt Engineering, Machine Translation, Educational Sciences, ChatGPT Pro, Lexical Accuracy, Exploratory Case Study

Abstract

Integrating Large Language Models (LLMs) into specialized translation workflows introduces nuanced lexical and register-related challenges. This exploratory case study investigates how progressively constrained prompt engineering influences the translation of domain-specific pedagogical terminology from English into Arabic. Using ChatGPT Pro (GPT-4), an 84-word source excerpt containing four key Task-Based Language Teaching (TBLT) pedagogical terms was translated under three prompting conditions: zero-shot baseline, role-prompting (expert persona), and context-rich prompting (localized to Moroccan secondary education). The resulting Arabic outputs were evaluated against recognized Moroccan pedagogical frameworks and specialized Arabic educational lexicons using an explicit three-tier adequacy rubric. Descriptive analysis revealed marked lexical variations: zero-shot prompting yielded literal semantic calques, whereas context-rich prompting aligned closely with localized curricular terminology. While these exploratory findings demonstrate that contextual constraints assist the model in selecting domain-appropriate registers, the results highlight the necessity of continued human expertise and institutional oversight in specialized machine translation post-editing.

Downloads

Download data is not yet available.

Author Biographies

Mayssaa Moukatib, Abdelmalek Essaâdi, Tangier, Morocco

Mayssaa MOUKATIB is a PhD researcher specializing in Translation Studies and Linguistics at the King Fahd School of Translation, Abdelmalek Essaâdi University, Morocco. She is also a secondary-school English teacher. She holds a Bachelor's degree in English Studies, specializing in Linguistics, and a Master's degree in Translation Studies and Linguistics. Her academic interests include artificial intelligence in translation, human–machine translation, machine translation post-editing, translator education, and the translation of specialized educational terminology. Her research particularly explores the integration of emerging AI technologies into translation practices and pedagogical frameworks.
Rajae Khaloufi, Abdelmalek Essaâdi, Tangier, Morocco

Rajae KHALOUFI is an Associate Professor and translator at the King Fahd School of Translation, Abdelmalek Essaâdi University, Morocco. She holds a PhD in Linguistics, Communication and Translation. Her academic and research interests encompass Translation Studies, Literary Translation, Performance Studies, and intercultural communication. Her scholarly contributions examine the intersections of translation, cultural representation, and artistic expression, with particular attention to the role of translation in facilitating intercultural understanding and knowledge exchange.

References

Almahasees, Z. (2021). Analysing English-Arabic machine translation: Google Translate, Microsoft Translator and Sakhr (1st ed.). Routledge. https://doi.org/10.4324/9781003191018 DOI: https://doi.org/10.4324/9781003191018-1

Al-Sharifi, S. A. (2000). Dictionary of educational sciences terms: Arabic - English / English - Arabic. Obeikan Publishing

Ben Chtioui, M. (2014). Educational assessment. Regional Centers for Education and Training Professions (CRMEF)

Bowker, L. (2023). Translation technology and the changing role of the translator. In F. Zanettin & C. Rundle (Eds.), The Routledge handbook of translation and technology (pp. 411-426). Routledge. https://doi.org/10.4324/9781315311258-26 DOI: https://doi.org/10.4324/9781315311258-26

Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., 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., Wu, J., Winter, C., … Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877-1901. https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf

Castilho, S., Doherty, S., Gaspari, F., & Moorkens, J. (2018). Approaches to human and machine translation quality assessment. In J. Moorkens, S. Castilho, F. Gaspari, & S. Doherty (Eds.), Translation quality assessment: From principles to practice (pp. 9-38). Springer. https://doi.org/10.1007/978-3-319-91241-7_2 DOI: https://doi.org/10.1007/978-3-319-91241-7_2

Chen, S., & Wang, J. (2019). Effects of task-based language teaching (TBLT) approach and language assessment on students' competences in intensive reading course. English Language Teaching, 12(3), 119-138. https://doi.org/10.5539/elt.v12n3p119 DOI: https://doi.org/10.5539/elt.v12n3p119

European Commission. (2022). European Master's in Translation competence framework 2022. Directorate-General for Translation. https://commission.europa.eu/system/files/2022-11/emt_competence_fwk_2022_en.pdf

Hamdan, M. (2007). Dictionary of education and teaching terminology: Arabic - English. Dar Knoz Al-Maarifa

Jiao, W., Wang, W., Huang, J., Wang, X., & Tu, Z. (2023). Is ChatGPT a good translator? A preliminary study. arXiv. https://doi.org/10.48550/arXiv.2301.08745

Koehn, P. (2020). Neural machine translation. Cambridge University Press. https://doi.org/10.1017/9781108608480 DOI: https://doi.org/10.1017/9781108608480

Ministry of National Education, Preschool and Sports. (2024a). ANG COLL.046-24: Qualifying training for middle school English teachers [Official directive]. Kingdom of Morocco

Ministry of National Education, Preschool and Sports. (2024b). Ministerial decree concerning the organization of qualifying training for primary education teachers (Decree No. 22 November 2024). Kingdom of Morocco

Moorkens, J. (2018). What to expect from neural machine translation: A practical in-class translation evaluation exercise. The Interpreter and Translator Trainer, 12(4), 375-387. https://doi.org/10.1080/1750399X.2018.1501639 DOI: https://doi.org/10.1080/1750399X.2018.1501639

Nord, C. (1997). Translating as a purposeful activity: Functionalist approaches explained. Routledge

OpenAI. (2024). GPT-4 technical report. arXiv. https://doi.org/10.48550/arXiv.2303.08774

Peng, K., Ding, L., Zhong, Q., Shen, L., Liu, X., Zhang, M., Ouyang, Y., & Tao, D. (2023). Towards making the most of ChatGPT for machine translation. arXiv. https://doi.org/10.48550/arXiv.2303.13780 DOI: https://doi.org/10.2139/ssrn.4390455

Regional Centers for Education and Training Professions (CRMEF). (2022). Module descriptor card: Planning. Ministry of National Education, Preschool and Sports

Regional Centers for Education and Training Professions (CRMEF). (2022). [Management module: Teaching and learning situations. Ministry of National Education, Preschool and Sports

Reynolds, L., & McDonell, K. (2021). Prompt programming for large language models: Beyond the few-shot paradigm. Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems, 1-7. https://doi.org/10.1145/3411763.3451760 DOI: https://doi.org/10.1145/3411763.3451760

Sellami, A. L., Sawalhi, R., Romanowski, M. H., & Amatullah, T. (2019). Definitions of educational leadership: Arab educators’ perspectives. International Journal of Leadership in Education, 25(5), 767-786. https://doi.org/10.1080/13603124.2019.1690701 DOI: https://doi.org/10.1080/13603124.2019.1690701

UNESCO International Bureau of Education. (2013). Glossary of curriculum terminology. UNESCO-IBE. https://2h.ae/QuNQe