EuroAlpaca提升欧洲语言指令数据质量，避免翻译导致的任务失真。
EuroAlpaca: Task-Preserving Localisation of Instruction Data for European Languages
- 分领域翻译+任务等价重构，确保关键内容不丢失
- 相比直接翻译，准确率提升12.9%，跨语言一致性更强
- 适配多语言大模型训练，特别适合欧洲语种研究者
机器翻译可规模化扩展英语指令数据至多语言，但常扭曲任务关键约束和输出要求，导致训练样本污染并降低模型性能。本文提出EuroAlpaca——一套任务保持的本地化流程与近平行数据资源，覆盖50种欧洲语言及地区变体，并构建了European-IFEval多语言验证基准。针对不同样本，该流程采用领域级翻译或重建任务等价的目标语言实例，再验证跨领域一致性和目标语言内部一致性。在四款LLM的LoRA实验中，直接翻译数据使Aya Evaluation Suite的ROUGE-L和F-BERT得分提升，但European-IFEval准确率相对未适配基线下降29.8%。而使用EuroAlpaca适配后，European-IFEval准确率反超基线12.9%，同时在Aya上取得最高ROUGE-L与F-BERT分数。结果表明，任务语义保持对多语言指令微调至关重要。
原文摘要 · Abstract (English)
Machine translation (MT) offers a scalable way to extend English instruction-tuning data to multiple languages, but it can distort task-critical constraints and required outputs, creating corrupted training examples and degrading models trained on such data. We introduce EuroAlpaca, a task-preserving localisation pipeline and near-parallel resource covering 50 European languages and regional varieties, together with European-IFEval, a multilingual benchmark for verifiable instruction following. Depending on the example, our pipeline applies field-wise MT while preserving task-critical content or reconstructs a task-equivalent target-language instance, followed by validation of cross-field coherence and target-language consistency. Across LoRA experiments with four LLMs, training on directly translated data improves ROUGE-L and F-BERT on the Aya Evaluation Suite, but reduces accuracy on European-IFEval by 29.8% relative to the unadapted baseline. In contrast, adaptation with EuroAlpaca improves accuracy by 12.9% over the same baseline, reversing the degradation caused by direct MT, while also achieving the highest ROUGE-L and F-BERT scores on Aya. These results show that preserving task semantics is essential for multilingual instruction tuning.
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。