mlsanityData to 7 Oct 2026

On-the-Fly Fusion of Large Language Models and Machine Translation

arXiv 2311.08306 ↗First posted 14 Nov 2023cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

We propose the on-the-fly ensembling of a machine translation model with an LLM, prompted on the same task and input. We perform experiments on 4 language pairs (both directions) with varying data amounts. We find that a slightly weaker-at-translation LLM can improve translations of a NMT model, and ensembling with an LLM can produce better translations than ensembling two stronger MT models. We combine our method with various techniques from LLM prompting, such as in context learning and translation context.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 39 of its 69 references that are in the map. First posted on arXiv 14 Nov 2023.

Builds on

39 of 69 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  5. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  6. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  7. 2022Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Modelcited by 557
  8. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 550
  9. 2023Benchmarking Large Language Models for News Summarizationcited by 444
  10. 2023How Good Are GPT Models at Machine Translation? A Comprehensive Evaluationcited by 344
  11. 2016Using the Output Embedding to Improve Language Modelscited by 266
  12. 2023Sentiment Analysis in the Era of Large Language Models: A Reality Checkcited by 262
27 more
  1. 2023Prompting Large Language Model for Machine Translation: A Case Studycited by 247
  2. 2018Marian: Fast Neural Machine Translation in C++cited by 202
  3. 2022In-context Examples Selection for Machine Translationcited by 172
  4. 2015On Using Monolingual Corpora in Neural Machine Translationcited by 149
  5. 2022Prompting PaLM for Translation: Assessing Strategies and Performancecited by 144
  6. 2021The Multilingual TEDx Corpus for Speech Recognition and Translationcited by 101
  7. 2018Has Machine Translation Achieved Human Parity? A Case for Document-level Evaluationcited by 88
  8. 2018On the Impact of Various Types of Noise on Neural Machine Translationcited by 76
  9. 2023Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capabilitycited by 62
  10. 2023BigTranslate: Augmenting Large Language Models with Multilingual Translation Capability over 100 Languagescited by 60
  11. 2018Attaining the Unattainable? Reassessing Claims of Human Parity in Neural Machine Translationcited by 58
  12. 2022Embarrassingly Easy Document-Level MT Metrics: How to Convert Any Pretrained Metric Into a Document-Level Metriccited by 56
  13. 2023Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructionscited by 55
  14. 2023TIM: Teaching Large Language Models to Translate with Comparisoncited by 50
  15. 2019Simple and Effective Noisy Channel Modeling for Neural Machine Translationcited by 37
  16. 2018Simple Fusion: Return of the Language Modelcited by 30
  17. 2023Improving Translation Faithfulness of Large Language Models via Augmenting Instructionscited by 28
  18. 2023CombLM: Adapting Black-Box Language Models through Small Fine-Tuned Modelscited by 26
  19. 2020Simulated Multiple Reference Training Improves Low-Resource Machine Translationcited by 22
  20. 2016A Character-Level Decoder without Explicit Segmentation for Neural Machine Translationcited by 21
  21. 2016Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Latticescited by 17
  22. 2023Identifying Context-Dependent Translations for Evaluation Set Productioncited by 14
  23. 2019Neural Machine Translation with Explicit Phrase Alignmentcited by 12
  24. 2023Document-Level Language Models for Machine Translationcited by 12
  25. 2016The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMTcited by 6
  26. 2016Vocabulary Manipulation for Neural Machine Translationcited by 5
  27. 2016Neural Machine Translation Advised by Statistical Machine Translationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 1.

5 papers.

  1. 2024X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scalecited by 36
  2. 2025Ensemble Learning for Large Language Models in Text and Code Generation: A Surveycited by 8
  3. 2024Language Modelling Approaches to Adaptive Machine Translationcited by 3
  4. 2026Rethinking LLM Ensembling from the Perspective of Mixture Modelscited by 1
  5. 2025CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understandingcited by 0