Litcius/Paper detail

Machine Translation with Large Language Models: Prompting, Few-shot Learning, and Fine-tuning with QLoRA

Xuan Zhang, Navid Rajabi, Kevin Duh, Philipp Koehn

202334 citationsDOIOpen Access PDF

Abstract

While large language models have made remarkable advancements in natural language generation, their potential in machine translation, especially when fine-tuned, remains under-explored. In our study, we conduct comprehensive experiments, evaluating 15 publicly available language models on machine translation tasks. We compare the performance across three methodologies: zero-shot prompting, few-shot learning, and fine-tuning. Central to our approach is the use of QLoRA, an efficient fine-tuning method. On French-English, QLoRA fine-tuning outperforms both few-shot learning and models trained from scratch. This superiority is highlighted in both sentence-level and document-level translations, with a significant BLEU score improvement of 28.93 over the prompting method. Impressively, with QLoRA, the enhanced performance is achieved by fine-tuning a mere 0.77% of the model's parameters.

Topics & Concepts

Computer scienceMachine translationFine-tuningArtificial intelligenceSentenceScratchShot (pellet)Language modelNatural language processingTranslation (biology)Natural language generationNatural languageProgramming languageChemistryQuantum mechanicsPhysicsMessenger RNAGeneOrganic chemistryBiochemistryNatural Language Processing TechniquesTopic ModelingText Readability and Simplification