# Mufu: Multilingual Fused Learning for Low-Resource Translation with LLM

arXiv: https://arxiv.org/abs/2409.13949 · HTML: https://mlsanity.com/paper/2409.13949/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 93 references that are in the map.
- First posted on arXiv 20 Sep 2024.

## Builds on (most cited first, 30 of 39)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/1606.07947/) (2016)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [LoRA Learns Less and Forgets Less](https://mlsanity.com/paper/2405.09673/) (2024)
- [Few-shot Learning with Multilingual Language Models](https://mlsanity.com/paper/2112.10668/) (2021)
- [Prompting Large Language Model for Machine Translation: A Case Study](https://mlsanity.com/paper/2301.07069/) (2023)
- [Tower: An Open Multilingual Large Language Model for Translation-Related Tasks](https://mlsanity.com/paper/2402.17733/) (2024)
- [MADLAD-400: A Multilingual And Document-Level Large Audited Dataset](https://mlsanity.com/paper/2309.04662/) (2023)
- [GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4](https://mlsanity.com/paper/2310.13988/) (2023)
- [Prompting PaLM for Translation: Assessing Strategies and Performance](https://mlsanity.com/paper/2211.09102/) (2022)
- [Language Models are Few-shot Multilingual Learners](https://mlsanity.com/paper/2109.07684/) (2021)
- [A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models](https://mlsanity.com/paper/2309.11674/) (2023)
- [Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus](https://mlsanity.com/paper/2010.14571/) (2020)
- [A Benchmark for Learning to Translate a New Language from One Grammar Book](https://mlsanity.com/paper/2309.16575/) (2023)
- [Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation](https://mlsanity.com/paper/2302.07856/) (2023)
- [Building Machine Translation Systems for the Next Thousand Languages](https://mlsanity.com/paper/2205.03983/) (2022)
- [PolyLM: An Open Source Polyglot Large Language Model](https://mlsanity.com/paper/2307.06018/) (2023)
- [From LLM to NMT: Advancing Low-Resource Machine Translation with Claude](https://mlsanity.com/paper/2404.13813/) (2024)
- [Leveraging GPT-4 for Automatic Translation Post-Editing](https://mlsanity.com/paper/2305.14878/) (2023)
- [LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages](https://mlsanity.com/paper/2407.05975/) (2024)

## Built on by (most cited first, 3 of 3)

- [A Survey of Multilingual Reasoning in Language Models](https://mlsanity.com/paper/2502.09457/) (2025)
- [VietMix: A Naturally-Occurring Parallel Corpus and Augmentation Framework for Vietnamese-English Code-Mixed Machine Translation](https://mlsanity.com/paper/2505.24472/) (2025)
- [PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement Learning](https://mlsanity.com/paper/2602.03352/) (2026)

## Abstract (arXiv)

Multilingual large language models (LLMs) are great translators, but this is largely limited to high-resource languages. For many LLMs, translating in and out of low-resource languages remains a challenging task. To maximize data efficiency in this low-resource setting, we introduce Mufu, which includes a selection of automatically generated multilingual candidates and an instruction to correct inaccurate translations in the prompt. Mufu prompts turn a translation task into a postediting one, and seek to harness the LLM's reasoning capability with auxiliary translation candidates, from which the model is required to assess the input quality, align the semantics cross-lingually, copy from relevant inputs and override instances that are incorrect. Our experiments on En-XX translations over the Flores-200 dataset show LLMs finetuned against Mufu-style prompts are robust to poor quality auxiliary translation candidates, achieving performance superior to NLLB 1.3B distilled model in 64% of low- and very-low-resource language pairs. We then distill these models to reduce inference cost, while maintaining on average 3.1 chrF improvement over finetune-only baseline in low-resource translations.