# Testing the Deliteralization Hypothesis in Human and Machine Translation

arXiv: https://arxiv.org/abs/2605.25686 · HTML: https://mlsanity.com/paper/2605.25686/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 48 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings](https://mlsanity.com/paper/2004.08728/) (2020)
- [MetricX-24: The Google Submission to the WMT 2024 Metrics Shared Task](https://mlsanity.com/paper/2410.03983/) (2024)
- [WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects](https://mlsanity.com/paper/2502.12404/) (2025)
- [The Effect of Translationese in Machine Translation Test Sets](https://mlsanity.com/paper/1906.08069/) (2019)
- [Do GPTs Produce Less Literal Translations?](https://mlsanity.com/paper/2305.16806/) (2023)
- [Post-editese: an Exacerbated Translationese](https://mlsanity.com/paper/1907.00900/) (2019)
- [Lost in Literalism: How Supervised Training Shapes Translationese in LLMs](https://mlsanity.com/paper/2503.04369/) (2025)
- [To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation](https://mlsanity.com/paper/2401.01419/) (2024)

## Abstract (arXiv)

The recent shift from dedicated NMT systems to general-purpose LLMs has reshaped machine translation, with LLMs reported to produce more fluent, less literal output than their predecessors. We test whether this shift extends to the deliteralization hypothesis, the long-standing claim from translation studies that translations become progressively less literal as they are drafted and revised. Using the WMT24++ dataset, we compare the literality of human translations and post-editions to that of two NMT systems and six LLMs across 54 language pairs and three tasks: direct translation, iterative self-revision, and post-editing of human drafts. Literality is measured via a validated Synthetic Literality Index built from six heuristics. We find that (i) human translations remain significantly less literal than those of all tested MT systems, though recent LLMs narrow the gap; (ii) when prompted to iteratively revise their own output, LLMs deliteralize monotonically, providing the first evidence that the hypothesis applies natively to LLM generation; and (iii) as post-editors, LLMs invert the revision triggers of human post-editors, tolerating literal drafts and targeting idiomatic human formulations for revision.