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

Maxim Enis, Mark Hopkins
4/22/2024
cs.CLcs.AI

No confident code implementation found for this paper. 5 possible matches can be shown below.

Abstract

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 \textit{resource 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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 5 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Quality or Quantity? On Data Scale and Diversity in Adapting Large Language Models for Low-Resource Translation

88% match2024

Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation

88% match1 repo302025

Can General-Purpose Large Language Models Generalize to English-Thai Machine Translation ?

87% match2024

Beyond Vanilla Fine-Tuning: Leveraging Multistage, Multilingual, and Domain-Specific Methods for Low-Resource Machine Translation

87% match2025

Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models

87% match1 repo92024

Scaling Low-Resource MT via Synthetic Data Generation with LLMs

87% match2025

Cite this paper

@article{enis2024from,
  title  = {From LLM to NMT: Advancing Low-Resource Machine Translation with Claude},
  author = {Maxim Enis and Mark Hopkins},
  year   = {2024},
  eprint = {2404.13813},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2404.13813v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2404.13813.svg)](https://codeofpaper.com/paper/2404.13813)

Discussion