Exploring the Role of AI in Diplomacy-related Translation Tasks: An Empirical Study on ChatGPT's Potential Use in Diplomatic Texts’ Translation

Article Sidebar

PDF
Published: Jun 30, 2026
Keywords:
Diplomatic Translation, ChatGPT, Large Language Models (LLMs), AI-Assisted Translation, Diplomatic Discourse, Translation Quality Assessment, English–Turkish Translation

Main Article Content

Yaşar Akgün
yasar.akgun@ieu.edu.tr, Izmir University of Economics - Turkey
Nihal Yetkin-Karakoç
nihal.yetkin@ieu.edu.tr, Izmir University of Economics – Turkey
Mirza İşi
mirza.isi@std.ieu.edu.tr, Izmir University of Economics – Turkey

Abstract

Diplomatic language, with its culturally sensitive and formally stratified character, presents distinctive challenges for translation. Although artificial intelligence (AI) and large language models (LLMs), such as ChatGPT, have shown considerable potential in technical and pragmatic translation tasks, their applicability to the specialised domain of diplomatic translation remains underexamined. This study addresses this gap by empirically assessing ChatGPT’s performance in translating diplomatic texts in comparison with human translators. Three diplomatic texts—two translated from English into Turkish and one from Turkish into English—were assigned to five third- and fourth-year undergraduate students enrolled in the English Translation and Interpreting Department at Izmir University of Economics, all of whom had completed a course in political text translation. The same texts were translated by ChatGPT (GPT-4o) using the prompt: “Translate the following texts with a diplomatic tone.” To ensure blind evaluation, all translations were handwritten and anonymised before submission. A jury consisting of two scholars in international relations and one retired ambassador evaluated the translations using a five-criterion rubric. ChatGPT obtained the highest overall score among the six participants and outperformed the five human translators across all three texts. The margin was narrowest in Text 3, translated from Turkish into English, yet ChatGPT still achieved the highest score. This result may be attributed to the formulaic and template-based nature of diplomatic correspondence, which aligns with the pattern-recognition capacities of LLMs trained on large, English-dominant datasets. The study suggests that ChatGPT has substantial potential for written diplomatic translation, particularly in texts conforming to established diplomatic conventions. These findings have implications for translation pedagogy, diplomatic communication, and the integration of AI tools into professional translation workflows. Future research should extend the inquiry to interpreting contexts and to more rhetorically complex diplomatic texts.

Article Details

How to Cite
Akgün , Y., Yetkin-Karakoç , N., & İşi , M. (2026). Exploring the Role of AI in Diplomacy-related Translation Tasks: An Empirical Study on ChatGPT’s Potential Use in Diplomatic Texts’ Translation . Traduction Et Langues, 25(01), 135-156. Retrieved from https://revue.univ-oran2.dz/revuetranslang/index.php/translang/article/view/1076
Issue
Vol 25 No 01 (2026): Traduction et Langues Volume : 25 Issue : 01/ June 2026
Section
Articles
Author Biographies

Yaşar Akgün , yasar.akgun@ieu.edu.tr, Izmir University of Economics - Turkey

Yaşar Akgün graduated from the Department of Translation and Interpreting at Kutahya Dumlupınar University as High Honour student. Having finished his master degree at Ege University in the field of Translation Studies with the thesis named The analysis of note taking language in consecutive interpreting within the scope of English and Turkish language pair: A case study with professionals and semiprofessionals, he is currently pursuing his PhD at Dokuz Eylül University in the field of Translation Studies. His main interests are diplomatic interpreting, consecutive interpreting and postcolonial translation studies. He has penned several articles published in both national and international journals in specified fiels and translated several literary books published in Türkiye. Affiliated with the Department of Translation and Interpreting, he is currently working as a research assistant at İzmir University of Economics.

Nihal Yetkin-Karakoç , nihal.yetkin@ieu.edu.tr, Izmir University of Economics – Turkey

Nihal Yetkin Karakoç graduated from the Department of English Translation and Interpreting at Hacettepe University. Between 1996 and 1999, she performed consecutive interpreting at the Ministry of National Defense for high-level officials, including the minister and the undersecretary, during bilateral meetings. From 1999 to 2002, she worked as a translator and interpreter at TAI, an international aviation company with Turkish-American partnership. In 2005, she completed her master’s thesis in English Linguistics at Hacettepe University, and in 2009, she completed her doctoral dissertation. She received the title of associate professor in 2017 and was promoted to professor in 2023. Since 2007, she has been working at İzmir University of Economics. Her main fields of interest include translation of diplomatic texts, interpreting, linguistics, subtitling and women’s studies. In these fields, she has published numerous articles and book chapters in both national and international journals and books.

Mirza İşi , mirza.isi@std.ieu.edu.tr, Izmir University of Economics – Turkey

 

Mirza İşi is currently pursuing a double major in English Translation and Interpreting and Computer Engineering at İzmir University of Economics, with a primary focus on artificial intelligence. He also works at Outlier, a subsidiary of Scale AI, as a Quality Control Auditor, where he contributes to the training of various large language models (LLMs) for major clients, including through Reinforcement Learning from Human Feedback (RLHF), one of the most widely used methods in the field. Through this work, he has developed a solid understanding of how LLMs function and are trained. His academic background in translation studies, combined with his technical expertise in computer engineering, enables him to approach AI and language-related research from an interdisciplinary perspective, with particular interest in the intersection of AI and translation.

References

Akgün, Y., & Yetkin Karakoç, N. (2024). The different aspects of diplomatic mediation: The extralinguistic motives of having an interpreter in diplomatic settings. İletişim ve Diplomasi, 12, 75–89. https://doi.org/10.54722/iletisimvediplomasi.1488687
Al Salem, M. N., Alghazo, S., Abusalim, N., & Rabab’ah, G. (2026). How AI translation personas reframe diplomatic texts. Studies in Media and Communication, 14(2), 198–212. https://doi.org/10.11114/smc.v14i2.8391
Almahasees, Z., Al-Harahsheh, A., & Albudairi, Y. (2025). Assessing DeepSeek and ChatGPT in English-Arabic translation of political texts. Research Journal in Advanced Humanities, 6(1). https://doi.org/10.58256/jrdwr620
Bahdanau, D., Cho, K., & Bengio, Y. (2015). Neural machine translation by jointly learning to align and translate. In Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015). https://arxiv.org/abs/1409.0473
Bobeica, G. (2022). Diplomatic language as part of the language for specific purposes. Études Interdisciplinaires en Sciences Humaines, 8, 600–610.
Bowker, L. (2019). Fit-for-purpose translation. In M. O’Hagan (Ed.), The Routledge handbook of translation and technology (pp. 453–468). Routledge.
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. https://arxiv.org/abs/2005.14165
Çetiner, C. (2018). Analyzing the attitudes of translation students towards CAT (computer-aided translation) tools. Journal of Language and Linguistic Studies, 14(1), 153–161.
Çetiner, C., & İşisağ, K. U. (2019). Undergraduate level translation students’ attitudes towards machine translation post-editing training. International Journal of Languages’ Education, 7(1), 110–120. https://doi.org/10.18298/ijlet.3242
Chang, Y., Wang, X., Wang, J., Wu, Y., Yang, L., Zhu, K., Chen, H., Yi, X., Wang, C., Wang, Y., Ye, W., Zhang, Y., Chang, Y., Yu, P. S., Yang, Q., & Xie, X. (2024). A survey on evaluation of large language models. ACM Transactions on Intelligent Systems and Technology, 15(3), 1–45. https://doi.org/10.1145/3641289
D’Acquisto, G. (2017). A linguistic analysis of diplomatic discourse. Cambridge Scholars Publishing.
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 4171–4186). Association for Computational Linguistics. https://doi.org/10.18653/v1/N19-1423
Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., & Liu, T. (2024). A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Transactions on Information Systems, 43(2), Article 1. https://doi.org/10.1145/3703155
Hutchins, W. J., & Somers, H. L. (1992). An introduction to machine translation. Academic Press.
Jaber, A. (2001). Language and diplomacy. In J. Kurbalija & H. Slavik (Eds.), Language and diplomacy (pp. 49–54). DiploProjects.
Jiang, L., Jiang, Y., & Han, L. (2024). The potential of ChatGPT in translation evaluation: A case study of Chinese-Portuguese machine translation. Cadernos de Tradução, 44(1). https://doi.org/10.5007/2175-7968.2024.e98613
Johnson, M., Schuster, M., Le, Q. V., Krikun, M., Wu, Y., Chen, Z., Thorat, N., Viégas, F., Wattenberg, M., Corrado, G., Hughes, M., & Dean, J. (2017). Google’s multilingual neural machine translation system: Enabling zero-shot translation. Transactions of the Association for Computational Linguistics, 5, 339–351. https://doi.org/10.1162/tacl_a_00065
Kingscott, G. (2002). Technical translation and related disciplines. Perspectives: Studies in Translatology, 10(4), 247–255.
Martirosyan, A. (2022). Modality’s features of diplomatic discourse. Bulletin of Eurasia International University, 129–144. https://doi.org/10.53614/18294952-2022.1-129
Mercan, H., Akgün, Y., & Odacıoğlu, M. C. (2024). The evolution of machine translation: A review study. Lotus: International Journal of Language and Translation Studies, 3(1), 53–72. https://doi.org/10.55003/lotus.1453321
Odacıoğlu, M. C. (2021). Çeviri edincinden çevirmen edincine geçişte çevirmen adaylarının sorumlulukları ve çeviri eğitiminin bu sürece katkısı. RumeliDE Dil ve Edebiyat Araştırmaları Dergisi, (20), 897–912. https://doi.org/10.29000/rumelide.897299
OpenAI. (2023). GPT-4 technical report. https://arxiv.org/abs/2303.08774
Özcan, O. (2024). Avrupa Komisyonu’nun makine çeviri sistemi eTranslation’da metin çevirisi. Journal of Academic Studies in World Languages, Literatures and Translation (WOLLT), 5(2), 191–216.
Pokharel, S. (2020). Diplomatic language: An analysis of salutations from speeches used in international diplomacy. Diplomatic Language: An Analysis of Salutations From Speeches Used in International Diplomacy, 3(1), 180–193. https://doi.org/10.3126/joia.v3i1.29094
Searle, J. R. (1980). Minds, brains, and programs. Behavioral and Brain Sciences, 3(3), 417–424. https://doi.org/10.1017/S0140525X00005756
Song, C., & Kao, Q. (2025). Comparing generative AI and advanced learners in translation tasks using the House model: Similarities and pedagogical implications. International Journal of Chinese Language Teaching, 1–28. https://doi.org/10.46451/ijclt.250503
Turing, A. M. (1950). Computing machinery and intelligence. Mind, 59(236), 433–460. https://doi.org/10.1093/mind/LIX.236.433
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 5998–6008. https://arxiv.org/abs/1706.03762
Vraila, S. (2024). AI in political translation: Revolutionising communication or risking manipulation? In New Trends in Translation and Technology Conference 2024 (pp. 226–229). https://doi.org/10.26615/issn.2815-4711.2024_019
Yetkin-Karakoç, N. (2022). Çeviri ve diplomasi (2nd ed.). Çeviribilim Yayınları.
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026). A survey of large language models. Frontiers of Computer Science, 20, Article 2012627. https://doi.org/10.1007/s11704-026-60308-3
Zhou, L., Muhammad Alif, M. S. N., & Peng, J. (2025). The impact of ChatGPT on part-time translators working with the English language: A threat or a complementary tool? World Journal of English Language, 15(7), 103. https://doi.org/10.5430/wjel.v15n7p103