mlsanityData to 7 Oct 2026

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

arXiv 2409.06790 ↗First posted 10 Sep 2024cs.CLcited by 31

Not on the map. Why?

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.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 8 of its 24 references that are in the map. First posted on arXiv 10 Sep 2024.

Builds on

8 of 24 references.

References · 8

  1. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
  2. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  3. 2024Tower: An Open Multilingual Large Language Model for Translation-Related Taskscited by 205
  4. 2023Hallucinations in Large Multilingual Translation Modelscited by 126
  5. 2024(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Textscited by 49
  6. 2023Translate Meanings, Not Just Words: IdiomKB's Role in Optimizing Idiomatic Translation with Language Modelscited by 23
  7. 2018Fluency Over Adequacy: A Pilot Study in Measuring User Trust in Imperfect MTcited by 21
  8. 2024Preliminary WMT24 Ranking of General MT Systems and LLMscited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 17; 2026: 10.

31 papers.

Sort:

By area:

  1. 2024Thinking LLMs: General Instruction Following with Thought Generationcited by 45
  2. 2025Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translationcited by 13
  3. 2024Creative and Context-Aware Translation of East Asian Idioms with GPT-4cited by 10
  4. 2025Redefining Machine Translation on Social Network Services with Large Language Modelscited by 6
  5. 2025An Interdisciplinary Approach to Human-Centered Machine Translationcited by 6
  6. 2025Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinementcited by 5
  7. 2025TACTIC: Translation Agents with Cognitive-Theoretic Interactive Collaborationcited by 5
  8. 2024Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysiscited by 4
  9. 2024CoAM: Corpus of All-Type Multiword Expressionscited by 4
  10. 2025Automatic Input Rewriting Improves Translation with Large Language Modelscited by 4
  11. 2025Leveraging Domain Knowledge at Inference Time for LLM Translation: Retrieval versus Generationcited by 4
  12. 2025DMDTEval: An Evaluation and Analysis of LLMs on Disambiguation in Multi-domain Translationcited by 3
19 more
  1. 2025Translation Analytics for Freelancers: I. Introduction, Data Preparation, Baseline Evaluationscited by 2
  2. 2025Steering Large Language Models for Machine Translation Personalizationcited by 2
  3. 2025Translation in the Wildcited by 2
  4. 2026What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translationcited by 2
  5. 2025Same evaluation, more tokens: On the effect of input length for machine translation evaluation using Large Language Modelscited by 1
  6. 2025TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translationcited by 1
  7. 2025Remedy-R: Generative Reasoning for Machine Translation Evaluation without Error Annotationscited by 1
  8. 2026STAR : Sentence Translation Alignment Rate for Document-to-Document Machine Translationcited by 1
  9. 2025Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transportcited by 0
  10. 2025Beyond the Sentence: A Survey on Context-Aware Machine Translation with Large Language Modelscited by 0
  11. 2025LangMark: A Multilingual Dataset for Automatic Post-Editingcited by 0
  12. 2026SAMAS: A Spectrum-Guided Multi-Agent System for Achieving Style Fidelity in Literary Translationcited by 0
  13. 2026Should We be Pedantic About Reasoning Errors in Machine Translation?cited by 0
  14. 2026Agentic AI Translate: An Agentic Translator Prototype for Translation as Communication Designcited by 0
  15. 2026Smarter edits? Post-editing with error highlights and translation suggestionscited by 0
  16. 2026Translation Analytics for Freelancers II: Benchmarking Local LLMs for Confidential Translation Workflowscited by 0
  17. 2026DeepTrans Studio: Turning Expert Interventions into Shared Team Knowledge in Agentic Translation Workflowscited by 0
  18. 2026PAMT: Process-Aligned Reinforcement Learning for Multi-Domain Machine Translationcited by 0
  19. 2026When Does Reasoning Help in Machine Translation? A Hierarchical Analysis of LRM Reasoning Tracescited by 0