# Fluency and Faithfulness in Human and Machine Literary Translation

arXiv: https://arxiv.org/abs/2605.15282 · HTML: https://mlsanity.com/paper/2605.15282/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 14 May 2026.

## Builds on (most cited first, 8 of 8)

- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2209.06243/) (2022)
- [Large language models effectively leverage document-level context for literary translation, but critical errors persist](https://mlsanity.com/paper/2304.03245/) (2023)
- [Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature](https://mlsanity.com/paper/2210.14250/) (2022)
- [DEMETR: Diagnosing Evaluation Metrics for Translation](https://mlsanity.com/paper/2210.13746/) (2022)
- [How Good Are LLMs for Literary Translation, Really? Literary Translation Evaluation with Humans and LLMs](https://mlsanity.com/paper/2410.18697/) (2024)
- [The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics](https://mlsanity.com/paper/2305.11806/) (2023)

## Abstract (arXiv)

Literary translation requires balancing target-language fluency with faithfulness to the source. Recent large language models (LLMs) often produce fluent translations, but it remains unclear whether fluency corresponds to semantic preservation in literary text. We examine this relationship using 130,486 translated paragraphs from 106 novels in 16 source languages, including human, Google Translate, and TranslateGemma translations. Fluency is measured as original-likeness with a translationese classifier trained on paragraph part-of-speech n-grams, and faithfulness with the automatic translation evaluation metric COMET-KIWI. We control for paragraph length and find a consistent negative correlation between fluency and faithfulness. The pattern appears for both human and Google Translate, but is weaker and often non-significant for TranslateGemma. These results show that segment length matters for automatic evaluation and suggest a tradeoff between fluency and faithfulness in literary translation.