Prompt engineering in scientific and technical literature translation using artificial intelligence tools
Abstract
The paper in question is devoted to the relevant issue of translation studies related to the translation quality, in particular the one that involves the use of artificial intelligence (AI) tools.
The objective of the research is to determine the role of prompt engineering in increasing the accuracy and adequacy of scientific and technical literature translation using AI tools.
One of the universal AI systems, which allow you to influence the result obtained due to their flexibility, the OpenAI large language model ChatGPT is chosen for testing. The user's, in our case - a professional translator's, interaction with the generative AI model in question is organized by means of prompts. To optimize prompts, the developers offer guidelines that explain the essence of prompt engineering, the function of which is to improve queries that formulate tasks for the universal AI model.
The English-Ukrainian translation of scientific and technical literature using ChatGPT-5.3 has been tested. The analysis of the items translated by this AI model has helped us determine that creating a prompt requires more attention of the translator, since scientific and technical literature is a complex entity in terms of its lexical and grammatical features. It is the wise choice of the type of prompt accompanying the source language text that enables the translator to improve the quality of the translation done by the given AI model.
Our testing of the ChatGPT AI model to assess the possibility to enhance the translation quality by having the prompt optimized gives grounds to state that prompt engineering is gaining unique significance for translation studies, as it allows to compensate for the limitations of universal AI systems in reproducing the peculiar characteristics of the scientific and technical text during translation, in particular, maintaining consistency of the terminology rendered, as well as taking into account the meaning of syntactic constructions of the source language for their adequate representation in the target language.
Further research is planned to study the peculiarities of integrating the highlighted topic into the course “Theory and Practice of Translation” for higher education students of the relevant specialization.
Downloads
References
Veselovska, H., Radetska, S. (2021). Machine translation: its typology, advantages and disadvantages. Humanities science current issues, 35(7), 23–27. https://doi.org/10.24919/2308-4863/35-7-4 [in Ukrainian].
Goodmanian, A., Sitko, A., & Struk, I. (2019). Functional and pragmatic adequacy of journalistic style texts translation applying machine translation systems. Lviv Philological Journal, 5, 48–54. https://doi.org/10.32447/2663-340X-2019-5-8. [in Ukrainian].
Zubach, O., & Melnychuk O. (2024). Scientific and technical texts: translation aspect. Scientific Notes of V. I. Vernadsky Taurida National University. Series: Philology. Journalism, 35(74) (3, Pt. 1), 95–100. https://doi.org/10.32782/2710-4656/2024.3.1/17 [in Ukrainian].
Karaban, V. I. (2018). Translation of English scientific and technical literature: Grammatical difficulties, lexical, terminological and genre-stylistic problems (5th ed., rev.). Vinnytsia: Nova Knyha. [in Ukrainian].
Chumachenko, D., Mishkin, D., Andriienko, O., Krakovetskyi, O., Turuta, O., Dubno, O., Khrushchova, D., Kobrin, A., Avdieieva, T., Kravets, I., Herasymiak, V., Shabanov, O., & Bystrytska, A. (Eds.). (2024). Dictionary of terms in the field of artificial intelligence. Kyiv: Ministry of Digital Transformation of Ukraine. [in Ukrainian].
Boonstra, L. (2024). Prompt Engineering. GPT AI Flow. URL: https://www.gptaiflow.com/assets/files/2025-01-18-pdf-1-TechAI-Goolge-whitepaper_Prompt%20Engineering_v4-af36dcc7a49bb7269a58b1c9b89a8ae1.pdf. [in English].
Dürr, K. (2025, September 18). From rules to robots: the history of machine translation. SwissGlobal. URL: https://swissglobal.ch/en/blog/from-rules-to-robots-the-history-of-machine-translation/. [in English].
Fuel injection. (accessed 10.03.2026). Britannica. URL: https://www.britannica.com/technology/fuel-injection. [in English].
Kyrychuk, L. (2018). Translation Strategies, Methods and Techniques: in Pursuit of Translation Adequacy. Research trends in modern linguistics and literature, 1, 64–80. [in English].
Olkhovska, A., & Frolova, I. (2020).Using machine translation engines in the classroom: a survey of translation students’ performance. Advanced Education, 15, 47–55. https://doi.org/10.20535/2410-8286.197812 [in English].
Stöeckli, А. (2025, September 15). DeepL or ChatGPT: which AI translation tool is right for you? SwissGlobal. URL: https://swissglobal.ch/en/blog/deepl-or-chatgpt-which-ai-translation-tool-is-right-for-you/. [in English].
What is ChatGPT? (accessed 10.03.2026). OpenAI. URL: https://help.openai.com/en/articles/6783457-what-is-chatgpt. [in English].
