# Improving Machine Translation with Large Language Models: A Preliminary Study with Cooperative Decoding

arXiv: https://arxiv.org/abs/2311.02851 · HTML: https://mlsanity.com/paper/2311.02851/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 50 references that are in the map.
- First posted on arXiv 6 Nov 2023.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Efficient Transformers: A Survey](https://mlsanity.com/paper/2009.06732/) (2020)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://mlsanity.com/paper/2004.02984/) (2020)
- [Reducing Transformer Depth on Demand with Structured Dropout](https://mlsanity.com/paper/1909.11556/) (2019)
- [Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT](https://mlsanity.com/paper/1909.05840/) (2019)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [Blockwise Parallel Decoding for Deep Autoregressive Models](https://mlsanity.com/paper/1811.03115/) (2018)
- [Few-shot Learning with Multilingual Language Models](https://mlsanity.com/paper/2112.10668/) (2021)
- [Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation](https://mlsanity.com/paper/2004.11867/) (2020)
- [Word Alignment by Fine-tuning Embeddings on Parallel Corpora](https://mlsanity.com/paper/2101.08231/) (2021)
- [In-context Examples Selection for Machine Translation](https://mlsanity.com/paper/2212.02437/) (2022)
- [Detecting Hallucinated Content in Conditional Neural Sequence Generation](https://mlsanity.com/paper/2011.02593/) (2020)
- [Accelerating Transformer Inference for Translation via Parallel Decoding](https://mlsanity.com/paper/2305.10427/) (2023)
- [BLEU might be Guilty but References are not Innocent](https://mlsanity.com/paper/2004.06063/) (2020)
- [The unreasonable effectiveness of few-shot learning for machine translation](https://mlsanity.com/paper/2302.01398/) (2023)
- [Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search](https://mlsanity.com/paper/2010.07003/) (2020)
- [Inference with Reference: Lossless Acceleration of Large Language Models](https://mlsanity.com/paper/2304.04487/) (2023)
- [A Survey on Green Deep Learning](https://mlsanity.com/paper/2111.05193/) (2021)
- [TIM: Teaching Large Language Models to Translate with Comparison](https://mlsanity.com/paper/2307.04408/) (2023)
- [BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models](https://mlsanity.com/paper/2306.10968/) (2023)
- [When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute](https://mlsanity.com/paper/2102.12459/) (2021)

## Built on by (most cited first, 10 of 10)

- [Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers](https://mlsanity.com/paper/2404.04925/) (2024)
- [G-DIG: Towards Gradient-based Diverse and High-quality Instruction Data Selection for Machine Translation](https://mlsanity.com/paper/2405.12915/) (2024)
- [Evaluating o1-Like LLMs: Unlocking Reasoning for Translation through Comprehensive Analysis](https://mlsanity.com/paper/2502.11544/) (2025)
- [Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations](https://mlsanity.com/paper/2404.07851/) (2024)
- [Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation](https://mlsanity.com/paper/2503.06594/) (2025)
- [LLM-based Translation Inference with Iterative Bilingual Understanding](https://mlsanity.com/paper/2410.12543/) (2024)
- [Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation](https://mlsanity.com/paper/2412.12627/) (2024)
- [Automatic Input Rewriting Improves Translation with Large Language Models](https://mlsanity.com/paper/2502.16682/) (2025)
- [Multi-Amateur Contrastive Decoding for Text Generation](https://mlsanity.com/paper/2507.21086/) (2025)
- [Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation](https://mlsanity.com/paper/2505.13554/) (2025)

## Abstract (arXiv)

Contemporary translation engines based on the encoder-decoder framework have made significant strides in development. However, the emergence of Large Language Models (LLMs) has disrupted their position by presenting the potential for achieving superior translation quality. To uncover the circumstances in which LLMs excel and explore how their strengths can be harnessed to enhance translation quality, we first conduct a comprehensive analysis to assess the strengths and limitations of various commercial NMT systems and MT-oriented LLMs. Our findings indicate that neither NMT nor MT-oriented LLMs alone can effectively address all the translation issues, but MT-oriented LLMs show promise as a complementary solution to NMT systems. Building upon these insights, we propose Cooperative Decoding (CoDec), which treats NMT systems as a pretranslation model and MT-oriented LLMs as a supplemental solution to handle complex scenarios beyond the capability of NMT alone. Experimental results on the WMT22 test sets and a newly collected test set WebCrawl demonstrate the effectiveness and efficiency of CoDec, highlighting its potential as a robust solution for combining NMT systems with MT-oriented LLMs in the field of machine translation.