Myroslava Slyvka

doi:10.36074/grail-of-science.21.08.2026.023

EVALUATING ARTIFICIAL INTELLIGENCE VERSUS HUMAN EXPERTISE IN LITERARY TRANSLATION

Authors

Myroslava Slyvka State Higher Educational Institution “Uzhhorod National University”, Ukraine https://orcid.org/0000-0002-8673-7147

DOI:

https://doi.org/10.36074/grail-of-science.21.08.2026.023

Keywords:

literary translation, artificial intelligence, Large Language Models (LLMs), machine translation evolution, translation quality assessment, dynamic equivalence, stylistic nuance, human translation competence

Summary

This study explores the comparative capabilities of artificial intelligence systems (such as Large Language Models like ChatGPT and Gemini, along with tools like DeepL) and professional human linguists in the domain of literary translation. The text outlines the historical progression of machine translation from early rule-based systems (RBMT) and statistical models (SMT) to neural machine translation (NMT) and contemporary generative LLMs. It highlights the distinct nature of literary translation, which requires aesthetic equivalence, dynamic adaptation (domestication vs. foreignization), global narrative consistency, and ethical responsibility toward the source author's voice. Furthermore, the study addresses the methodological complexities of translation quality assessment, contrasting traditional frameworks like Multidimensional Quality Metrics (MQM) and n-gram metrics like BLEU with hybrid approaches and LLM-driven evaluations. Ultimately, while modern AI systems demonstrate strong localized fluency and syntactic handling, expert human translators remain vital for navigating subtle stylistic nuances, cultural realia, and overall aesthetic artistic integrity.

Downloads

PDF

Downloads

Download data is not yet available.

License

References

Freitag, M., Rei, R., Mathur, N., Lo, C. K., Stewart, C., Foster, G., Lavie, A., & Federmann, C. (2023). Experts, errors, and context: A large-scale study of human evaluation for machine translation. Transactions of the Association for Computational Linguistics, 11, 1461–1477. https://doi.org/10.1162/tacl_a_00612

Sharkova, N. (2025). Mashynnyi pereklad naukovykh tekstiv u haluzi metalurhii: Porivnialnyi analiz ChatGPT ta DeepL Translator [Machine translation of scientific texts in metallurgy: A comparative analysis of ChatGPT and DeepL Translator]. Naukovi zapysky. Seriia: Filolohichni nauky, 215, 41–50. https://doi.org/10.32782/2522-4077-2025- 215-50

Slyvka, M. I. (2023). Vstup do perekladoznavstva: Navchalno-metodychnyi posibnyk dlia studentiv vyshchykh navchalnykh zakladiv [Introduction to translation studies: Study guide for higher education students]. Uzhhorod National University.

Slyvka, M., & Madzhara, T. (2023). Developing effective communication skills in teaching science.08.12.2023.70

Yan, J., Yan, P., Chen, Y., Li, J., Zhu, X., & Zhang, Y. (2024). GPT-4 vs. human translators: A comprehensive evaluation of translation quality across languages, domains, and expertise levels (arXiv Preprint arXiv:2403.01562). arXiv. https://doi.org/10.48550/arXiv.2403.01562