用多语言候选翻译+纠错指令，提升低资源语言翻译效果
Mufu: Multilingual Fused Learning for Low-Resource Translation with LLM
- 将翻译任务转为基于候选译文的后编辑任务
- 在 Flores-200 上超 64% 低资源对表现优于 NLLB 1.3B
- 适合追求低成本高效率低资源翻译的研究者
多语言大模型在高资源语言上表现优异，但在低资源语言翻译中仍面临挑战。为提高数据效率，本文提出 Mufu：通过自动构建的多语言候选译文与纠错指令组合，将翻译任务转化为后编辑任务。该方法利用大模型的推理能力，评估候选译文质量，跨语言对齐语义，选择正确内容并覆盖错误部分。在 Flores-200 数据集上的实验表明，经 Mufu 提示微调的模型对低质量候选译文具有鲁棒性，在 64% 的低资源及极低资源语言对上超越了 NLLB 1.3B 蒸馏模型。进一步蒸馏这些模型可降低推理开销，同时在低资源翻译中平均提升 3.1 的 chrF 分数。
原文摘要 · Abstract (English)
Multilingual large language models (LLMs) are great translators, but this is largely limited to high-resource languages. For many LLMs, translating in and out of low-resource languages remains a challenging task. To maximize data efficiency in this low-resource setting, we introduce Mufu, which includes a selection of automatically generated multilingual candidates and an instruction to correct inaccurate translations in the prompt. Mufu prompts turn a translation task into a postediting one, and seek to harness the LLM's reasoning capability with auxiliary translation candidates, from which the model is required to assess the input quality, align the semantics cross-lingually, copy from relevant inputs and override instances that are incorrect. Our experiments on En-XX translations over the Flores-200 dataset show LLMs finetuned against Mufu-style prompts are robust to poor quality auxiliary translation candidates, achieving performance superior to NLLB 1.3B distilled model in 64% of low- and very-low-resource language pairs. We then distill these models to reduce inference cost, while maintaining on average 3.1 chrF improvement over finetune-only baseline in low-resource translations.
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。