# From LLM to NMT: Advancing Low-Resource Machine Translation with Claude

arXiv: https://arxiv.org/abs/2404.13813 · HTML: https://mlsanity.com/paper/2404.13813/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 22 Apr 2024.

## Builds on (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/1606.07947/) (2016)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [Prompting Large Language Model for Machine Translation: A Case Study](https://mlsanity.com/paper/2301.07069/) (2023)
- [Large language models effectively leverage document-level context for literary translation, but critical errors persist](https://mlsanity.com/paper/2304.03245/) (2023)
- [The FLoRes Evaluation Datasets for Low-Resource Machine Translation: Nepali-English and Sinhala-English](https://mlsanity.com/paper/1902.01382/) (2019)
- [The Effect of Domain and Diacritics in Yor`ub'a-English Neural Machine Translation](https://mlsanity.com/paper/2103.08647/) (2021)
- [Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model](https://mlsanity.com/paper/2212.09811/) (2022)
- [MT-PATCHER: Selective and Extendable Knowledge Distillation from Large Language Models for Machine Translation](https://mlsanity.com/paper/2403.09522/) (2024)
- [MASRI-HEADSET: A Maltese Corpus for Speech Recognition](https://mlsanity.com/paper/2008.05760/) (2020)

## Built on by (most cited first, 30 of 58)

- [TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability](https://mlsanity.com/paper/2411.18211/) (2024)
- [Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context](https://mlsanity.com/paper/2406.05972/) (2024)
- [MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection](https://mlsanity.com/paper/2410.14731/) (2024)
- [NADI 2024: The Fifth Nuanced Arabic Dialect Identification Shared Task](https://mlsanity.com/paper/2407.04910/) (2024)
- [Data Contamination Report from the 2024 CONDA Shared Task](https://mlsanity.com/paper/2407.21530/) (2024)
- [Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation](https://mlsanity.com/paper/2503.04554/) (2025)
- [Scaling Low-Resource MT via Synthetic Data Generation with LLMs](https://mlsanity.com/paper/2505.14423/) (2025)
- [Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models](https://mlsanity.com/paper/2407.18999/) (2024)
- [Geneverse: A collection of Open-source Multimodal Large Language Models for Genomic and Proteomic Research](https://mlsanity.com/paper/2406.15534/) (2024)
- [Benchmarking GPT-4 against Human Translators: A Comprehensive Evaluation Across Languages, Domains, and Expertise Levels](https://mlsanity.com/paper/2411.13775/) (2024)
- [Evaluating Mathematical Reasoning Across Large Language Models: A Fine-Grained Approach](https://mlsanity.com/paper/2503.10573/) (2025)
- [LogicCat: A Chain-of-Thought Text-to-SQL Benchmark for Complex Reasoning](https://mlsanity.com/paper/2505.18744/) (2025)
- [Multi-Document Financial Question Answering using LLMs](https://mlsanity.com/paper/2411.07264/) (2024)
- [Cross-Lingual and Cross-Cultural Variation in Image Descriptions](https://mlsanity.com/paper/2409.16646/) (2024)
- [Truth Knows No Language: Evaluating Truthfulness Beyond English](https://mlsanity.com/paper/2502.09387/) (2025)
- [Dysfluent WFST: A Framework for Zero-Shot Speech Dysfluency Transcription and Detection](https://mlsanity.com/paper/2505.16351/) (2025)
- [EvoEmpirBench: Dynamic Spatial Reasoning with Agent-ExpVer](https://mlsanity.com/paper/2509.12718/) (2025)
- [What talking you?: Translating Code-Mixed Messaging Texts to English](https://mlsanity.com/paper/2411.05253/) (2024)
- [Mufu: Multilingual Fused Learning for Low-Resource Translation with LLM](https://mlsanity.com/paper/2409.13949/) (2024)
- [DiDOTS: Knowledge Distillation from Large-Language-Models for Dementia Obfuscation in Transcribed Speech](https://mlsanity.com/paper/2410.04188/) (2024)
- [Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in Thai](https://mlsanity.com/paper/2411.15484/) (2024)
- ["See the World, Discover Knowledge": A Chinese Factuality Evaluation for Large Vision Language Models](https://mlsanity.com/paper/2502.11718/) (2025)
- [Towards Large Language Model Aided Program Refinement](https://mlsanity.com/paper/2406.18616/) (2024)
- [Towards Robust Knowledge Representations in Multilingual LLMs for Equivalence and Inheritance based Consistent Reasoning](https://mlsanity.com/paper/2410.14235/) (2024)
- [Critique of Impure Reason: Unveiling the reasoning behaviour of medical Large Language Models](https://mlsanity.com/paper/2412.15748/) (2024)
- [Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-resource Language Translation](https://mlsanity.com/paper/2412.19522/) (2024)
- [Decoding Machine Translationese in English-Chinese News: LLMs vs. NMTs](https://mlsanity.com/paper/2506.22050/) (2025)
- [Astrolabe: Balancing Load in LLM Serving with Randomized Prediction-Guided Scheduling](https://mlsanity.com/paper/2508.03611/) (2025)
- [The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models](https://mlsanity.com/paper/2510.23652/) (2025)
- [Hermes the Polyglot: A Unified Framework to Enhance Expressiveness for Multimodal Interlingual Subtitling](https://mlsanity.com/paper/2602.00597/) (2026)

## Abstract (arXiv)

We show that Claude 3 Opus, a large language model (LLM) released by Anthropic in March 2024, exhibits stronger machine translation competence than other LLMs. Though we find evidence of data contamination with Claude on FLORES-200, we curate new benchmarks that corroborate the effectiveness of Claude for low-resource machine translation into English. We find that Claude has remarkable textitresource efficiency -- the degree to which the quality of the translation model depends on a language pair's resource level. Finally, we show that advancements in LLM translation can be compressed into traditional neural machine translation (NMT) models. Using Claude to generate synthetic data, we demonstrate that knowledge distillation advances the state-of-the-art in Yoruba-English translation, meeting or surpassing strong baselines like NLLB-54B and Google Translate.