# Please Translate Again: Two Simple Experiments on Whether Human-Like Reasoning Helps Translation

arXiv: https://arxiv.org/abs/2506.04521 · HTML: https://mlsanity.com/paper/2506.04521/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 3 of its 27 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 3 of 3)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects](https://mlsanity.com/paper/2502.12404/) (2025)

## Built on by (most cited first, 7 of 7)

- [Investigating Test-Time Scaling with Reranking for Machine Translation](https://mlsanity.com/paper/2509.19020/) (2025)
- [What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation](https://mlsanity.com/paper/2605.13368/) (2026)
- [OpenWHO: A Document-Level Parallel Corpus for Health Translation in Low-Resource Languages](https://mlsanity.com/paper/2508.16048/) (2025)
- [Remedy-R: Generative Reasoning for Machine Translation Evaluation without Error Annotations](https://mlsanity.com/paper/2512.18906/) (2025)
- [Beyond "To whom it may concern": Tailoring Machine Translation to Audience and Intent](https://mlsanity.com/paper/2606.03259/) (2026)
- [How Early Adopters Used Generative AI Worldwide: Variation by Country Income and Language](https://mlsanity.com/paper/2605.30685/) (2026)
- [Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation](https://mlsanity.com/paper/2609.13770/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) demonstrate strong reasoning capabilities for many tasks, often by explicitly decomposing the task via Chain-of-Thought (CoT) reasoning. Recent work on LLM-based translation designs hand-crafted prompts to decompose translation, or trains models to incorporate intermediate steps. Translating Step-by-step (Briakou et al., 2024), for instance, introduces a multi-step prompt with decomposition and refinement of translation with LLMs, which achieved state-of-the-art results on WMT24 test data. In this work, we scrutinise this strategy's effectiveness. Empirically, we find no clear evidence that performance gains stem from explicitly decomposing the translation process via CoT, at least for the models on test; and we show prompting LLMs to 'translate again' and self-refine yields even better results than human-like step-by-step prompting. While the decomposition influences translation behaviour, faithfulness to the decomposition has both positive and negative effects on translation. Our analysis therefore suggests a divergence between the optimal translation strategies for humans and LLMs.