@inproceedings{egdom-etal-2024-make,
    title = "{\textquoteleft}Can make mistakes'. Prompting {C}hat{GPT} to Enhance Literary {MT} output",
    author = "Egdom, Gys-Walt  and
      Declercq, Christophe  and
      Kosters, Onno",
    editor = "Vanroy, Bram  and
      Lefer, Marie-Aude  and
      Macken, Lieve  and
      Ruffo, Paola",
    booktitle = "Proceedings of the 1st Workshop on Creative-text Translation and Technology",
    month = jun,
    year = "2024",
    address = "Sheffield, United Kingdom",
    publisher = "European Association for Machine Translation",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.ctt-1.2/",
    pages = "10--20",
    abstract = "Operating at the intersection of generative AI (artificial intelligence), machine transla-tion (MT), and literary translation, this paper examines to what extent prompt-driven post-editing (PE) can enhance the quality of ma-chine-translated literary texts. We assess how different types of instruction influence PE performance, particularly focusing on lit-erary nuances and author-specific styles. Situated within posthumanist translation theory, which often challenges traditional notions of human intervention in translation processes, the study explores the practical implementation of generative AI in multilin-gual workflows. While the findings suggest that prompted PE can improve translation output to some extent, its effectiveness var-ies, especially in literary contexts. This highlights the need for a critical review of prompt engineering approaches and empha-sizes the importance of further research to navigate the complexities of integrating AI into creative translation workflows effective-ly."
}