Ladder:一种将基于大语言模型的机器翻译提升至新水平的模型无关框架
Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level
AI总结:
针对通用大语言模型机器翻译算力/数据成本高、专用模型标注投入大的问题,提出模型无关的MT-Ladder框架,基于伪修正三元组和由易到难分层微调策略,可低成本提升通用LLM翻译性能至顶尖水平。
摘要:
通用大语言模型(LLM,如GPT-4)借助海量网页内容,已在机器翻译(MT)领域取得显著进展。另一方面,翻译专用LLM则通过在领域特定单语语料上预训练、再用人工标注翻译数据微调构建而成。尽管这类方法性能优异,但它们要么需要规模空前的算力与数据,要么需要大量人工编辑与标注工作。本文提出了MT-Ladder,这是一种新型模型无关且高性价比的工具,用于优化通用LLM的机器翻译性能。MT-Ladder基于伪修正三元组训练,这类三元组可从现有LLM中轻松获取,无需额外人工成本。训练过程中,我们提出了一种遵循由易到难模式的分层微调策略,逐步提升MT-Ladder的修正性能。训练完成的MT-Ladder可与任意通用LLM无缝集成,提升其翻译性能。以Gemma-2B/7B为骨干模型时,MT-Ladder-2B可将原始译文提升至顶级开源模型水平(例如,对BigTranslate-13B的XX-En方向翻译进行修正,BLEU值提升+6.91,COMET值提升+3.52),而MT-Ladder-7B可进一步将模型性能提升至与当前最优的GPT-4相当的水平。大量消融实验与分析验证了MT-Ladder在多种场景下的有效性。我们的代码已发布于https://github.com/fzp0424/MT-Ladder。
英文摘要:
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
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。