# Optimising ChatGPT for creativity in literary translation: A case study from English into Dutch, Chinese, Catalan and Spanish

arXiv: https://arxiv.org/abs/2504.18221 · HTML: https://mlsanity.com/paper/2504.18221/

## 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 (most cited first, 9 of 9)

- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2209.06243/) (2022)
- [Towards Making the Most of ChatGPT for Machine Translation](https://mlsanity.com/paper/2303.13780/) (2023)
- [A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4](https://mlsanity.com/paper/2310.12321/) (2023)
- [Large language models effectively leverage document-level context for literary translation, but critical errors persist](https://mlsanity.com/paper/2304.03245/) (2023)
- [Comparison of Diverse Decoding Methods from Conditional Language Models](https://mlsanity.com/paper/1906.06362/) (2019)
- [The Impact of Post-editing and Machine Translation on Creativity and Reading Experience](https://mlsanity.com/paper/2101.06125/) (2021)
- [Investigating Length Issues in Document-level Machine Translation](https://mlsanity.com/paper/2412.17592/) (2024)

## Built on by (most cited first, 2 of 2)

- [Creativity Bias: How Machine Evaluation Struggles with Creativity in Literary Translations](https://mlsanity.com/paper/2605.13596/) (2026)
- [Causally Evaluating the Learnability of Formal Language Tasks](https://mlsanity.com/paper/2606.09822/) (2026)

## 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).