Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level

TL;DR

This paper introduces MT-Ladder, a model-agnostic, cost-effective framework that enhances general-purpose LLMs for machine translation through hierarchical fine-tuning on pseudo-refinement data, achieving performance comparable to top-tier models.

Contribution

The paper presents MT-Ladder, a novel hierarchical fine-tuning method that improves LLM-based machine translation without additional human annotation or large-scale training.

Findings

MT-Ladder improves translation BLEU scores significantly.

MT-Ladder-2B matches top open-source models' performance.

MT-Ladder-7B approaches GPT-4-level translation quality.

Abstract

General-purpose Large Language Models (LLMs) like GPT-4 have achieved remarkable advancements in machine translation (MT) by leveraging extensive web content. On the other hand, translation-specific LLMs are built by pre-training on domain-specific monolingual corpora and fine-tuning with human-annotated translation data. Despite the superior performance, these methods either demand an unprecedented scale of computing and data or substantial human editing and annotation efforts. In this paper, we develop MT-Ladder, a novel model-agnostic and cost-effective tool to refine the performance of general LLMs for MT. MT-Ladder is trained on pseudo-refinement triplets which can be easily obtained from existing LLMs without additional human cost. During training, we propose a hierarchical fine-tuning strategy with an easy-to-hard schema, improving MT-Ladder's refining performance progressively. The trained MT-Ladder can be seamlessly integrated with any general-purpose LLMs to boost their translation performance. By utilizing Gemma-2B/7B as the backbone, MT-Ladder-2B can elevate raw translations to the level of top-tier open-source models (e.g., refining BigTranslate-13B with +6.91 BLEU and +3.52 COMET for XX-En), and MT-Ladder-7B can further enhance model performance to be on par with the state-of-the-art GPT-4. Extensive ablation and analysis corroborate the effectiveness of MT-Ladder in diverse settings. Our code is available at https://github.com/fzp0424/MT-Ladder