mlsanityData to 14 Oct 2026

Iterative Translation Refinement with Large Language Models

arXiv 2306.03856 ↗First posted 6 Jun 2023cs.CL cs.AIcited by 27

Not on the map. Why?

Abstract (arXiv)

We propose iteratively prompting a large language model to self-correct a translation, with inspiration from their strong language understanding and translation capability as well as a human-like translation approach. Interestingly, multi-turn querying reduces the output's string-based metric scores, but neural metrics suggest comparable or improved quality. Human evaluations indicate better fluency and naturalness compared to initial translations and even human references, all while maintaining quality. Ablation studies underscore the importance of anchoring the refinement to the source and a reasonable seed translation for quality considerations. We also discuss the challenges in evaluation and relation to human performance and translationese.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 35 of its 66 references that are in the map. First posted on arXiv 6 Jun 2023.

Builds on

35 of 66 references.

References · 35

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2020Scaling Laws for Neural Language Modelscited by 6,586
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  6. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  7. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  8. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  9. 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
  10. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
  11. 2023Large Language Models Are State-of-the-Art Evaluators of Translation Qualitycited by 420
  12. 2023How Good Are GPT Models at Machine Translation? A Comprehensive Evaluationcited by 348
23 more
  1. 2023Prompting Large Language Model for Machine Translation: A Case Studycited by 250
  2. 2019Levenshtein Transformercited by 199
  3. 2018Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinementcited by 195
  4. 2023Is ChatGPT A Good Translator? Yes With GPT-4 As The Enginecited by 176
  5. 2022In-context Examples Selection for Machine Translationcited by 172
  6. 2022Prompting PaLM for Translation: Assessing Strategies and Performancecited by 145
  7. 2020BLEU might be Guilty but References are not Innocentcited by 110
  8. 2023Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Modelscited by 87
  9. 2023Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capabilitycited by 62
  10. 2018Attaining the Unattainable? Reassessing Claims of Human Parity in Neural Machine Translationcited by 58
  11. 2021Facebook AI WMT21 News Translation Task Submissioncited by 57
  12. 2023Leveraging GPT-4 for Automatic Translation Post-Editingcited by 56
  13. 2019Translationese as a Language in "Multilingual" NMTcited by 36
  14. 2023Do GPTs Produce Less Literal Translations?cited by 30
  15. 2019Post-editese: an Exacerbated Translationesecited by 29
  16. 2020EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraintscited by 24
  17. 2020Can Automatic Post-Editing Improve NMT?cited by 17
  18. 2020Human-Paraphrased References Improve Neural Machine Translationcited by 16
  19. 2018MS-UEdin Submission to the WMT2018 APE Shared Task: Dual-Source Transformer for Automatic Post-Editingcited by 13
  20. 2016Pre-Translation for Neural Machine Translationcited by 9
  21. 2016Iterative Refinement for Machine Translationcited by 5
  22. 2022Towards Debiasing Translation Artifactscited by 3
  23. 2019The Transference Architecture for Automatic Post-Editingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 10; 2025: 7; 2026: 2.

27 papers.

Sort:

By area:

  1. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 240
  2. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 238
  3. 2024A Survey on Self-Evolution of Large Language Modelscited by 91
  4. 2023A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoningcited by 41
  5. 2024SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correctioncited by 40
  6. 2025A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Modelscited by 30
  7. 2024LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thoughtcited by 28
  8. 2024Language Imbalance Driven Rewarding for Multilingual Self-improvingcited by 28
  9. 2023An Empirical Study of Translation Hypothesis Ensembling with Large Language Modelscited by 16
  10. 2024On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Conceptcited by 16
  11. 2024Enhancing LLM Reasoning with Multi-Path Collaborative Reactive and Reflection agentscited by 15
  12. 2025Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translationcited by 14
15 more
  1. 2023StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solvingcited by 13
  2. 2025Feedback Friction: LLMs Struggle to Fully Incorporate External Feedbackcited by 11
  3. 2023Towards Effective Disambiguation for Machine Translation with Large Language Modelscited by 8
  4. 2023Terminology-Aware Translation with Constrained Decoding and Large Language Model Promptingcited by 8
  5. 2024Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Modelscited by 8
  6. 2026Autoregressive Models Rival Diffusion Models at ANY-ORDER Generationcited by 4
  7. 2023Exploring Iterative Enhancement for Improving Learnersourced Multiple-Choice Question Explanations with Large Language Modelscited by 3
  8. 2023SCALE: Synergized Collaboration of Asymmetric Language Translation Enginescited by 3
  9. 2024PrefixLLM: LLM-aided Prefix Circuit Designcited by 3
  10. 2025Agents of Discoverycited by 3
  11. 2025Towards Self-Refinement of Vision-Language Models with Triangular Consistencycited by 3
  12. 2025Speech Translation Refinement using Large Language Modelscited by 2
  13. 2024Hybrid Student-Teacher Large Language Model Refinement for Cancer Toxicity Symptom Extractioncited by 0
  14. 2025Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decodingcited by 0
  15. 2026Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoningcited by 0