Optimising ChatGPT for creativity in literary translation: A case study from English into Dutch, Chinese, Catalan and Spanish
Not on the map. Why?
Abstract (arXiv)
This study examines the variability of Chat-GPT machine translation (MT) outputs across six different configurations in four languages,with a focus on creativity in a literary text. We evaluate GPT translations in different text granularity levels, temperature settings and prompting strategies with a Creativity Score formula. We found that prompting ChatGPT with a minimal instruction yields the best creative translations, with "Translate the following text into [TG] creatively" at the temperature of 1.0 outperforming other configurations and DeepL in Spanish, Dutch, and Chinese. Nonetheless, ChatGPT consistently underperforms compared to human translation (HT).
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 9 of its 27 references that are in the map. First posted on arXiv 25 Apr 2025.
Builds on
9 of 27 references.
References · 9
- 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
- 2023How Good Are GPT Models at Machine Translation? A Comprehensive Evaluationcited by 348
- 2022CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Taskcited by 207
- 2023Towards Making the Most of ChatGPT for Machine Translationcited by 138
- 2023A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4cited by 81
- 2023Large language models effectively leverage document-level context for literary translation, but critical errors persistcited by 80
- 2019Comparison of Diverse Decoding Methods from Conditional Language Modelscited by 78
- 2021The Impact of Post-editing and Machine Translation on Creativity and Reading Experiencecited by 10
- 2024Investigating Length Issues in Document-level Machine Translationcited by 10
Built on by
Citing papers per year: 2026: 2.
2 papers.