Extending Creativity: Large Language Models and the Practice of Poetry Translation

Natalia Resende, James Hadley


Abstract
The aim of this paper is to propose a framework to support literary translators—particularly poetry translators—in making effective use of large language models (LLMs) through established prompt engineering strategies applied to both pre-translation and translation stages. The paper illustrates these strategies using poems characterized by multiple layers of syntactic, semantic, phonological, and cultural complexity, and discusses how LLMs perform in response to each prompting technique. It also engages with the longstanding claim that poetry translation is a purely human endeavour and cannot be computer-assisted, arguing instead that LLMs, rather than replacing human creativity, have the potential to extend it.
Anthology ID:
2026.eamt-1.50
Volume:
Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1)
Month:
June
Year:
2026
Address:
Tilburg, The Netherlands
Editors:
Dimitar Shterionov, Eva Vanmassenhove, Mirella De Sisto, Fred Blain, Javad Pourmostafa Roshan Sharami, Lisa Lepp, Chiara Manna, Argentina Anna Rescigno, Alina Karakanta, Ayla Rigouts Terryn, Manuel Lardelli, Natalia Resende, Elena Murgolo, Janiça Hackenbuchner, Anna Zaretskaya, Miquel Esplà-Gomis, Thierry Etchegoyhen, Dagmar Gromann, Rachel Bawden, Barry Haddow, Sara Szoc, Mikel Forcada, Helena Moniz
Venue:
EAMT
SIG:
Publisher:
European Association for Machine Translation
Note:
Pages:
787–799
Language:
URL:
https://aclanthology.org/2026.eamt-1.50/
DOI:
Bibkey:
Cite (ACL):
Natalia Resende and James Hadley. 2026. Extending Creativity: Large Language Models and the Practice of Poetry Translation. In Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1), pages 787–799, Tilburg, The Netherlands. European Association for Machine Translation.
Cite (Informal):
Extending Creativity: Large Language Models and the Practice of Poetry Translation (Resende & Hadley, EAMT 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.eamt-1.50.pdf