# Translating Step-by-Step: Decomposing the Translation Process for Improved Translation Quality of Long-Form Texts

arXiv: https://arxiv.org/abs/2409.06790 · HTML: https://mlsanity.com/paper/2409.06790/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 24 references that are in the map.
- First posted on arXiv 10 Sep 2024.

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

- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Tower: An Open Multilingual Large Language Model for Translation-Related Tasks](https://mlsanity.com/paper/2402.17733/) (2024)
- [Hallucinations in Large Multilingual Translation Models](https://mlsanity.com/paper/2303.16104/) (2023)
- [(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts](https://mlsanity.com/paper/2405.11804/) (2024)
- [Translate Meanings, Not Just Words: IdiomKB's Role in Optimizing Idiomatic Translation with Language Models](https://mlsanity.com/paper/2308.13961/) (2023)
- [Fluency Over Adequacy: A Pilot Study in Measuring User Trust in Imperfect MT](https://mlsanity.com/paper/1802.06041/) (2018)
- [Preliminary WMT24 Ranking of General MT Systems and LLMs](https://mlsanity.com/paper/2407.19884/) (2024)

## Built on by (most cited first, 30 of 31)

- [Thinking LLMs: General Instruction Following with Thought Generation](https://mlsanity.com/paper/2410.10630/) (2024)
- [Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation](https://mlsanity.com/paper/2503.04554/) (2025)
- [Creative and Context-Aware Translation of East Asian Idioms with GPT-4](https://mlsanity.com/paper/2410.00988/) (2024)
- [Redefining Machine Translation on Social Network Services with Large Language Models](https://mlsanity.com/paper/2504.07901/) (2025)
- [An Interdisciplinary Approach to Human-Centered Machine Translation](https://mlsanity.com/paper/2506.13468/) (2025)
- [Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinement](https://mlsanity.com/paper/2504.05614/) (2025)
- [TACTIC: Translation Agents with Cognitive-Theoretic Interactive Collaboration](https://mlsanity.com/paper/2506.08403/) (2025)
- [Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis](https://mlsanity.com/paper/2409.20059/) (2024)
- [CoAM: Corpus of All-Type Multiword Expressions](https://mlsanity.com/paper/2412.18151/) (2024)
- [Automatic Input Rewriting Improves Translation with Large Language Models](https://mlsanity.com/paper/2502.16682/) (2025)
- [Leveraging Domain Knowledge at Inference Time for LLM Translation: Retrieval versus Generation](https://mlsanity.com/paper/2503.05010/) (2025)
- [DMDTEval: An Evaluation and Analysis of LLMs on Disambiguation in Multi-domain Translation](https://mlsanity.com/paper/2504.20371/) (2025)
- [Steering Large Language Models for Machine Translation Personalization](https://mlsanity.com/paper/2505.16612/) (2025)
- [Translation Analytics for Freelancers: I. Introduction, Data Preparation, Baseline Evaluations](https://mlsanity.com/paper/2504.14619/) (2025)
- [Translation in the Wild](https://mlsanity.com/paper/2505.23548/) (2025)
- [What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation](https://mlsanity.com/paper/2605.13368/) (2026)
- [Same evaluation, more tokens: On the effect of input length for machine translation evaluation using Large Language Models](https://mlsanity.com/paper/2505.01761/) (2025)
- [TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation](https://mlsanity.com/paper/2508.08680/) (2025)
- [Remedy-R: Generative Reasoning for Machine Translation Evaluation without Error Annotations](https://mlsanity.com/paper/2512.18906/) (2025)
- [STAR : Sentence Translation Alignment Rate for Document-to-Document Machine Translation](https://mlsanity.com/paper/2608.27161/) (2026)
- [Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport](https://mlsanity.com/paper/2505.23078/) (2025)
- [Beyond the Sentence: A Survey on Context-Aware Machine Translation with Large Language Models](https://mlsanity.com/paper/2506.07583/) (2025)
- [LangMark: A Multilingual Dataset for Automatic Post-Editing](https://mlsanity.com/paper/2511.17153/) (2025)
- [SAMAS: A Spectrum-Guided Multi-Agent System for Achieving Style Fidelity in Literary Translation](https://mlsanity.com/paper/2602.19840/) (2026)
- [Should We be Pedantic About Reasoning Errors in Machine Translation?](https://mlsanity.com/paper/2604.09890/) (2026)
- [Agentic AI Translate: An Agentic Translator Prototype for Translation as Communication Design](https://mlsanity.com/paper/2605.17041/) (2026)
- [Smarter edits? Post-editing with error highlights and translation suggestions](https://mlsanity.com/paper/2605.21135/) (2026)
- [Translation Analytics for Freelancers II: Benchmarking Local LLMs for Confidential Translation Workflows](https://mlsanity.com/paper/2605.31452/) (2026)
- [DeepTrans Studio: Turning Expert Interventions into Shared Team Knowledge in Agentic Translation Workflows](https://mlsanity.com/paper/2606.29727/) (2026)
- [PAMT: Process-Aligned Reinforcement Learning for Multi-Domain Machine Translation](https://mlsanity.com/paper/2608.03077/) (2026)

## Abstract (arXiv)

In this paper we present a step-by-step approach to long-form text translation, drawing on established processes in translation studies. Instead of viewing machine translation as a single, monolithic task, we propose a framework that engages language models in a multi-turn interaction, encompassing pre-translation research, drafting, refining, and proofreading, resulting in progressively improved translations. Extensive automatic evaluations using Gemini 1.5 Pro across ten language pairs show that translating step-by-step yields large translation quality improvements over conventional zero-shot prompting approaches and earlier human-like baseline strategies, resulting in state-of-the-art results on WMT2024.