# The unreasonable effectiveness of few-shot learning for machine translation

arXiv: https://arxiv.org/abs/2302.01398 · HTML: https://mlsanity.com/paper/2302.01398/

## Key facts

- Cited by 91 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 44 of its 59 references that are in the map.
- First posted on arXiv 2 Feb 2023.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 44)

- [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)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [Galactica: A Large Language Model for Science](https://mlsanity.com/paper/2211.09085/) (2022)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [MASS: Masked Sequence to Sequence Pre-training for Language Generation](https://mlsanity.com/paper/1905.02450/) (2019)
- [Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation](https://mlsanity.com/paper/2104.14478/) (2021)
- [Unsupervised Machine Translation Using Monolingual Corpora Only](https://mlsanity.com/paper/1711.00043/) (2017)
- [Scaling Laws for Transfer](https://mlsanity.com/paper/2102.01293/) (2021)
- [Scaling Up Models and Data with textttt5x and textttseqio](https://mlsanity.com/paper/2203.17189/) (2022)
- [In-context Examples Selection for Machine Translation](https://mlsanity.com/paper/2212.02437/) (2022)
- [To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation](https://mlsanity.com/paper/2107.10821/) (2021)
- [Prompting PaLM for Translation: Assessing Strategies and Performance](https://mlsanity.com/paper/2211.09102/) (2022)
- [Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation](https://mlsanity.com/paper/2005.10283/) (2020)
- [High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics](https://mlsanity.com/paper/2111.09388/) (2021)
- [Facebook AI WMT21 News Translation Task Submission](https://mlsanity.com/paper/2108.03265/) (2021)
- [Data Scaling Laws in NMT: The Effect of Noise and Architecture](https://mlsanity.com/paper/2202.01994/) (2022)
- [Denoising Neural Machine Translation Training with Trusted Data and Online Data Selection](https://mlsanity.com/paper/1809.00068/) (2018)
- [When Does Unsupervised Machine Translation Work?](https://mlsanity.com/paper/2004.05516/) (2020)
- [When and Why is Unsupervised Neural Machine Translation Useless?](https://mlsanity.com/paper/2004.10581/) (2020)
- [Multi-Task Neural Models for Translating Between Styles Within and Across Languages](https://mlsanity.com/paper/1806.04357/) (2018)
- [Unsupervised Neural Machine Translation with Generative Language Models Only](https://mlsanity.com/paper/2110.05448/) (2021)

## Built on by (most cited first, 30 of 91)

- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method](https://mlsanity.com/paper/2402.17193/) (2024)
- [ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics](https://mlsanity.com/paper/2302.12433/) (2023)
- [MADLAD-400: A Multilingual And Document-Level Large Audited Dataset](https://mlsanity.com/paper/2309.04662/) (2023)
- [Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis](https://mlsanity.com/paper/2304.04675/) (2023)
- [Hallucinations in Large Multilingual Translation Models](https://mlsanity.com/paper/2303.16104/) (2023)
- [Visual In-Context Learning for Large Vision-Language Models](https://mlsanity.com/paper/2402.11574/) (2024)
- [Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM](https://mlsanity.com/paper/2303.01911/) (2023)
- [Leveraging GPT-4 for Automatic Translation Post-Editing](https://mlsanity.com/paper/2305.14878/) (2023)
- [Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions](https://mlsanity.com/paper/2305.15083/) (2023)
- [Active Learning Principles for In-Context Learning with Large Language Models](https://mlsanity.com/paper/2305.14264/) (2023)
- [Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers](https://mlsanity.com/paper/2404.04925/) (2024)
- [TIM: Teaching Large Language Models to Translate with Comparison](https://mlsanity.com/paper/2307.04408/) (2023)
- [Steering Large Language Models for Machine Translation with Finetuning and In-Context Learning](https://mlsanity.com/paper/2310.13448/) (2023)
- [Exploring Human-Like Translation Strategy with Large Language Models](https://mlsanity.com/paper/2305.04118/) (2023)
- [BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models](https://mlsanity.com/paper/2306.10968/) (2023)
- [Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding](https://mlsanity.com/paper/2309.07098/) (2023)
- [Benchmarks for Automated Commonsense Reasoning: A Survey](https://mlsanity.com/paper/2302.04752/) (2023)
- [TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement](https://mlsanity.com/paper/2402.16379/) (2024)
- [Transformers are Minimax Optimal Nonparametric In-Context Learners](https://mlsanity.com/paper/2408.12186/) (2024)
- [A Survey of Recent Backdoor Attacks and Defenses in Large Language Models](https://mlsanity.com/paper/2406.06852/) (2024)
- [Teaching Large Language Models an Unseen Language on the Fly](https://mlsanity.com/paper/2402.19167/) (2024)
- [G-DIG: Towards Gradient-based Diverse and High-quality Instruction Data Selection for Machine Translation](https://mlsanity.com/paper/2405.12915/) (2024)
- [Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2311.08380/) (2023)
- [Model-as-a-Service (MaaS): A Survey](https://mlsanity.com/paper/2311.05804/) (2023)
- [The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities](https://mlsanity.com/paper/2405.20089/) (2024)
- [Seed-X: Building Strong Multilingual Translation LLM with 7B Parameters](https://mlsanity.com/paper/2507.13618/) (2025)
- [Poro 34B and the Blessing of Multilinguality](https://mlsanity.com/paper/2404.01856/) (2024)
- [How Much Data is Enough Data? Fine-Tuning Large Language Models for In-House Translation: Performance Evaluation Across Multiple Dataset Sizes](https://mlsanity.com/paper/2409.03454/) (2024)

## Abstract (arXiv)

We demonstrate the potential of few-shot translation systems, trained with unpaired language data, for both high and low-resource language pairs. We show that with only 5 examples of high-quality translation data shown at inference, a transformer decoder-only model trained solely with self-supervised learning, is able to match specialized supervised state-of-the-art models as well as more general commercial translation systems. In particular, we outperform the best performing system on the WMT'21 English - Chinese news translation task by only using five examples of English - Chinese parallel data at inference. Moreover, our approach in building these models does not necessitate joint multilingual training or back-translation, is conceptually simple and shows the potential to extend to the multilingual setting. Furthermore, the resulting models are two orders of magnitude smaller than state-of-the-art language models. We then analyze the factors which impact the performance of few-shot translation systems, and highlight that the quality of the few-shot demonstrations heavily determines the quality of the translations generated by our models. Finally, we show that the few-shot paradigm also provides a way to control certain attributes of the translation -- we show that we are able to control for regional varieties and formality using only a five examples at inference, paving the way towards controllable machine translation systems.