AI-Mediated Translation and Epistemic Hierarchies
LLMs, Literary Language, and Translational Decision-Making in Joyce’s Ulysses
Keywords:
artificial intelligence, large language models, literary translation, language mediation, epistemic hierarchiesAbstract
Large language models (LLMs) are increasingly used to mediate linguistic and cultural exchange, yet their capacity to preserve linguistically and historically marked forms remains insufficiently understood. This study examines how AI-mediated translation negotiates linguistic difference and cultural expression through a comparative analysis of James Joyce’s “Oxen of the Sun” from Ulysses. The analysis compares Enrico Terrinoni’s professional Italian translation with translations generated by ChatGPT and Google Translate. An adaptation of the Multidimensional Quality Metrics (MQM) framework, developed specifically for the assessment of literary translation, is combined with qualitative close reading to examine accuracy, fluency, diachronic style, register, multilingualism, wordplay, and formal experimentation. The findings indicate a distinction between linguistic competence and strategic translational competence. While ChatGPT produces comparatively fluent and coherent Italian, it frequently normalises stylistically and historically marked forms, reducing the differentiation that structures Joyce’s text. Google Translate exhibits more extensive difficulties in both semantic transfer and stylistic reconstruction, whereas Terrinoni’s translation demonstrates more consistent strategic management of competing textual priorities. These findings suggest that LLM-mediated translation should be examined not only in terms of linguistic accuracy and fluency, but also in terms of how AI systems preserve, transform, or neutralise culturally and historically situated forms of expression. The study contributes to critical discussions of AI, language, and epistemic hierarchies by proposing literary translation as a site for examining the non-neutral mediation of linguistic and cultural difference.
References
Baker, M. (2018). In other words: A coursebook on translation (3rd ed.). Routledge.
Bakhtin, M. M. (2010). The dialogic imagination: Four essays (M. Holquist, Ed.; C. Emerson & M. Holquist, Trans.). University of Texas Press.
Bannister, P., Alcalde Peñalver, E., & Santamaría Urbieta, A. (2024). International students and generative artificial intelligence: A cross-cultural exploration of HE academic integrity policy. Journal of International Students, 14(3), 149–170.
Boase-Beier, J. (2004). Translation and style: A brief introduction. Language and Literature, 13(1), 9–11.
Castilho, S., Gaspari, F., Moorkens, J., Popović, M., & Toral, A. (2019). Editors’ foreword to the special issue on human factors in neural machine translation. Machine Translation, 33(1–2), 1–7.
Duscovich, D. (2026). Intercultural competence and translation quality: Assessing AI and human literary translations. Dialogica, 2(1), 51–75.
Elkins, K. (2024). In search of a translator: Using AI to evaluate what’s lost in translation. Frontiers in Computer Science, 6, Article 1444021.
Gifford, D., & Seidman, R. J. (1988). Ulysses annotated: Notes for James Joyce’s Ulysses. University of California Press.
Griebel, S., & Underwood, T. (2026). Fluency and faithfulness in human and machine literary translation. In S. Hamilton, E. Öhman, R. M. M. Hicke, Y. Bizzoni, A. Bax, J. A. Matthews, & M. Hämäläinen (Eds.), Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities (pp. 178–189). Association for Computational Linguistics. https://doi.org/10.18653/v1/2026.nlp4dh-1.17
Guerberof-Arenas, A., & Toral, A. (2020). The impact of post-editing and machine translation on creativity and reading experience. Translation Spaces, 9(2), 255–282. https://doi.org/10.1075/ts.20035.gue
Guerberof-Arenas, A., & Toral Ruiz, A. (2022). Creativity in translation: Machine translation as a constraint for literary texts. Translation Spaces, 11(2), 184–212. https://doi.org/10.1075/ts.21025.gue
House, J. (2015). Translation quality assessment: Past and present. Routledge.
Hsieh, C., Ochiai, Y., Matsuda, I., Fushimi, T., & Li, J. (2026). Exploring the role of large language models during the culture shock phase: A study of international students in Japan. Journal of International Students, 16(13), 273–304.
Joyce, J. (2021). Ulisse: Testo inglese a fronte (E. Terrinoni, Ed. & Trans.). Bompiani.
Karmi, K. (2026). Writing a thesis in the era of ChatGPT: The lived experiences of PhD international students at UK universities. Journal of International Students, 16(13), 103–124.
Karpinska, M., & Iyyer, M. (2023). Large language models effectively leverage document-level context for literary translation, but critical errors persist. In Proceedings of the Eighth Conference on Machine Translation (WMT) (pp. 419–451). Association for Computational Linguistics.
Levý, J. (1967). Translation as a decision process. In To honor Roman Jakobson: Essays on the occasion of his 70th birthday, 11 October 1966 (Vol. 2, pp. 1171–1182). De Gruyter Mouton.
Levý, J. (2011). The art of translation (P. J. Corness, Trans.; Z. Jettmarová, Ed.). John Benjamins Publishing Company.
Lin, Z., Zhu, Z., Huang, H., Wang, G., & He, P. (2026). Better literary translation: A multi-aspect data generation and LLM training approach. In Y. Li, G. Rehm, & M. Tu (Eds.), Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) (pp. 329–345). Association for Computational Linguistics. https://doi.org/10.18653/v1/2026.acl-industry.22
Lommel, A. R., Uszkoreit, H., & Burchardt, A. (2014). Multidimensional quality metrics (MQM): A framework for declaring and describing translation quality metrics. Tradumàtica, 12, 455–463.
Mariana, V., Cox, T., & Melby, A. (2015). The Multidimensional Quality Metrics (MQM) framework: A new framework for translation quality assessment. The Journal of Specialised Translation, 23, 137–161.
Orăsan, C. (2023). ChatGPT for translators: A survey. In Proceedings of the First Workshop on NLP Tools and Resources for Translation and Interpreting Applications (pp. 61–63). Association for Computational Linguistics.
Scalena, D., Sarti, G., Bisazza, A., Fersini, E., & Nissim, M. (2026). Steering large language models for machine translation personalization. In V. Demberg, K. Inui, & L. Marquez (Eds.), Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 4681–4701). Association for Computational Linguistics. https://doi.org/10.18653/v1/2026.eacl-long.217
Tan, S., Zhu, D., Tran, K., Denkowski, M., Trenous, S., Ribeiro, L. F. R., Byrne, B., & Hieber, F. (2026). What does LLM refinement actually improve? A systematic study on document-level literary translation. In M. Liakata, V. P. Moreira, J. Zhang, & D. Jurgens (Eds.), Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 5929–5957). Association for Computational Linguistics. https://doi.org/10.18653/v1/2026.acl-long.268
Toral, A., & Way, A. (2018). What level of quality can neural machine translation attain on literary text? In J. Moorkens, S. Castilho, F. Gaspari, & S. Doherty (Eds.), Translation quality assessment: From principles to practice (pp. 263–287). Springer.
Wang, L., Lyu, C., Ji, T., Zhang, Z., Yu, D., Shi, S., & Tu, Z. (2023). Document-level machine translation with large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (pp. 16646–16661). Association for Computational Linguistics.
Wang, S., Wong, D. F., Yao, J., & Chao, L. S. (2024). What is the best way for ChatGPT to translate poetry? In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 14025–14043). Association for Computational Linguistics.
Zhang, R., Eger, S., Tezcan, A., Zhao, W., Ponzetto, S. P., & Macken, L. (2026). Beyond reproduction: A paired-task framework for assessing LLM comprehension and creativity in literary translation. In M. Liakata, V. P. Moreira, J. Zhang, & D. Jurgens (Eds.), Findings of the Association for Computational Linguistics: ACL 2026 (pp. 40862–40884). Association for Computational Linguistics. https://doi.org/10.18653/v1/2026.findings-acl.2030
