mlsanityData to 7 Oct 2026

How to Design Translation Prompts for ChatGPT: An Empirical Study

arXiv 2304.02182 ↗First posted 5 Apr 2023cs.CLcited by 31

Not on the map. Why?

Abstract (arXiv)

The recently released ChatGPT has demonstrated surprising abilities in natural language understanding and natural language generation. Machine translation relies heavily on the abilities of language understanding and generation. Thus, in this paper, we explore how to assist machine translation with ChatGPT. We adopt several translation prompts on a wide range of translations. Our experimental results show that ChatGPT with designed translation prompts can achieve comparable or better performance over commercial translation systems for high-resource language translations. We further evaluate the translation quality using multiple references, and ChatGPT achieves superior performance compared to commercial systems. We also conduct experiments on domain-specific translations, the final results show that ChatGPT is able to comprehend the provided domain keyword and adjust accordingly to output proper translations. At last, we perform few-shot prompts that show consistent improvement across different base prompts. Our work provides empirical evidence that ChatGPT still has great potential in translations.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 27 of its 36 references that are in the map. First posted on arXiv 5 Apr 2023.

Builds on

27 of 36 references.

References · 27

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  5. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  6. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  7. 2020Stanza: A Python Natural Language Processing Toolkit for Many Human Languagescited by 719
  8. 2021Multimodal Few-Shot Learning with Frozen Language Modelscited by 657
  9. 2020Language-agnostic BERT Sentence Embeddingcited by 621
  10. 2020Beyond English-Centric Multilingual Machine Translationcited by 559
  11. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 556
  12. 2023How Good Are GPT Models at Machine Translation? A Comprehensive Evaluationcited by 344
15 more
  1. 2023Prompting Large Language Model for Machine Translation: A Case Studycited by 247
  2. 2022Prompting PaLM for Translation: Assessing Strategies and Performancecited by 144
  3. 2023Towards Making the Most of ChatGPT for Machine Translationcited by 138
  4. 2018Analyzing Uncertainty in Neural Machine Translationcited by 126
  5. 2019Neural Machine Translation: A Review and Surveycited by 99
  6. 2021Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Textcited by 89
  7. 2020A Survey of Deep Learning Techniques for Neural Machine Translationcited by 50
  8. 2020Incorporating BERT into Parallel Sequence Decoding with Adapterscited by 39
  9. 2021GPT3-to-plan: Extracting plans from text using GPT-3cited by 26
  10. 2021Revisiting Self-Training for Few-Shot Learning of Language Modelcited by 22
  11. 2019Controlling Neural Machine Translation Formality with Synthetic Supervisioncited by 18
  12. 2017Exploiting Linguistic Resources for Neural Machine Translation Using Multi-task Learningcited by 11
  13. 2019Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoringcited by 7
  14. 2018Learning from Chunk-based Feedback in Neural Machine Translationcited by 6
  15. 2022Improving English to Sinhala Neural Machine Translation using Part-of-Speech Tagcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 9; 2024: 8; 2025: 10; 2026: 4.

31 papers.

Sort:

By area:

  1. 2024Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMscited by 224
  2. 2023Leveraging GPT-4 for Automatic Translation Post-Editingcited by 56
  3. 2023GPTAraEval: A Comprehensive Evaluation of ChatGPT on Arabic NLPcited by 37
  4. 2023When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Taskscited by 37
  5. 2023An In-depth Look at Gemini's Language Abilitiescited by 28
  6. 2023Large Language Models are Complex Table Parserscited by 28
  7. 2023ChatGPT MT: Competitive for High- (but not Low-) Resource Languagescited by 23
  8. 2023TARJAMAT: Evaluation of Bard and ChatGPT on Machine Translation of Ten Arabic Varietiescited by 16
  9. 2023An Empirical Study of Translation Hypothesis Ensembling with Large Language Modelscited by 16
  10. 2024What is the Best Way for ChatGPT to Translate Poetry?cited by 14
  11. 2024Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptionscited by 12
  12. 2024Prompting ChatGPT for Translation: A Comparative Analysis of Translation Brief and Persona Promptscited by 12
19 more
  1. 2023Optimizing Machine Translation through Prompt Engineering: An Investigation into ChatGPT's Customizabilitycited by 11
  2. 2025Benchmarking the Detection of LLMs-Generated Modern Chinese Poetrycited by 10
  3. 2025Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translationcited by 8
  4. 2024LLM-based Translation Inference with Iterative Bilingual Understandingcited by 6
  5. 2024Gender Bias in Machine Translation and The Era of Large Language Modelscited by 4
  6. 2025Are AI agents the new machine translation frontier? Challenges and opportunities of single- and multi-agent systems for multilingual digital communicationcited by 4
  7. 2026Can ChatGPT Really Understand Modern Chinese Poetry?cited by 4
  8. 2024Aligning Translation-Specific Understanding to General Understanding in Large Language Modelscited by 3
  9. 2025ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoningcited by 3
  10. 2025MELAC: Massive Evaluation of Large Language Models with Alignment of Culture in Persian Languagecited by 3
  11. 2024Could We Have Had Better Multilingual LLMs If English Was Not the Central Language?cited by 2
  12. 2025Compensating for Data with Reasoning: Low-Resource Machine Translation with LLMscited by 2
  13. 2026Creativity Bias: How Machine Evaluation Struggles with Creativity in Literary Translationscited by 1
  14. 2025Missing the human touch? A computational stylometry analysis of GPT-4 translations of online Chinese literaturecited by 0
  15. 2025Designing LLMs for cultural sensitivity: Evidence from English-Japanese translationcited by 0
  16. 2025Multilingual LLM Prompting Strategies for Medical English-Vietnamese Machine Translationcited by 0
  17. 2025When the Gold Standard Isn't Necessarily Standard: Challenges of Evaluating the Translation of User-Generated Contentcited by 0
  18. 2026AI-assisted cultural heritage dissemination: Comparing NMT and glossary-augmented LLM translation in rock art documentscited by 0
  19. 2026The Role of Prompt Language and Translation-Theory-Driven Prompts in Large Language Models: A Case Study on Spanish-Chinese Journalistic Translationcited by 0