混合NMT与LLM翻译，按需调用大模型提升效率
Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation
- 根据源句特征决定是否调用LLM，智能调度翻译流程
- 在多语言测试集上实现媲美LLM的译文质量，但大幅减少使用次数
- 适合追求高性价比翻译系统的开发者和部署团队
大型语言模型（LLM）在机器翻译等下游任务中表现优异，但直接用于翻译存在计算开销大、延迟高的问题。我们评估发现，多数情况下LLM的翻译效果与神经机器翻译（NMT）系统相当；仅在特定场景下，两者各有优势。因此，结合二者并仅在必要时启用LLM是一种合理方案。为此，我们比较了多种调度策略，提出一种基于源句特征的简单高效决策机制。在多语言测试集上的大量实验表明，该方法能在保证最优翻译性能的同时，最小化LLM的使用次数，验证了其有效性。
原文摘要 · Abstract (English)
Large language model (LLM) shows promising performances in a variety of downstream tasks, such as machine translation (MT). However, using LLMs for translation suffers from high computational costs and significant latency. Based on our evaluation, in most cases, translations using LLMs are comparable to that generated by neural machine translation (NMT) systems. Only in particular scenarios, LLM and NMT models show respective advantages. As a result, integrating NMT and LLM for translation and using LLM only when necessary seems to be a sound solution. A scheduling policy that optimizes translation result while ensuring fast speed and as little LLM usage as possible is thereby required. We compare several scheduling policies and propose a novel and straightforward decider that leverages source sentence features. We conduct extensive experiments on multilingual test sets and the result shows that we can achieve optimal translation performance with minimal LLM usage, demonstrating effectiveness of our decider.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。