语言通才 vs 专才：对多语言迁移能力的实证重审
Language Versatilists vs. Specialists: An Empirical Revisiting on Multilingual Transfer Ability
AI总结：
该研究针对以英语为中心的模型的多语言迁移能力开展实证研究，通过四类推理任务实验发现其迁移能力不弱于甚至可能超越多语言预训练模型，为提升这类模型的多语言推理能力提供了参考。
摘要：
多语言迁移能力反映了在一种源语言上微调的模型应用于其他语言的效果，该能力已在多语言预训练模型（如BLOOM）中得到充分研究，但针对以英语为中心的模型（如LLaMA）的这类能力尚未被探究。为填补这一空白，我们研究了以下问题：第一，以英语为中心的模型是否存在多语言迁移能力，与多语言预训练模型相比表现如何？第二，对于以英语为中心的模型，该能力是否仅在英语作为源语言时才显现？第三，该能力在不同任务中如何变化？我们以多语言推理能力为研究重点，在四类推理任务上开展了大量实验。研究发现，多语言预训练模型并不总是优于以英语为中心的模型。此外，英语似乎是不太合适的源语言，且当以英语为中心的模型规模扩大时，源语言的选择变得不那么重要。另外，不同类型的任务展现出不同的多语言迁移能力。这些发现表明，以英语为中心的模型不仅具备多语言迁移能力，若训练得当，其迁移能力甚至可能超越多语言预训练模型。通过展示优势与不足，这些实验也为提升以英语为中心的模型的多语言推理能力提供了宝贵见解。
英文摘要：
Multilingual transfer ability, which reflects how well the models fine-tuned on one source language can be applied to other languages, has been well studied in multilingual pre-trained models (e.g., BLOOM). However, such ability has not been investigated for English-centric models (e.g., LLaMA). To fill this gap, we study the following research questions. First, does multilingual transfer ability exist in English-centric models and how does it compare with multilingual pretrained models? Second, does it only appears when English is the source language for the English-centric model? Third, how does it vary in different tasks? We take multilingual reasoning ability as our focus and conduct extensive experiments across four types of reasoning tasks. We find that the multilingual pretrained model does not always outperform an English-centric model. Furthermore, English appears to be a less suitable source language, and the choice of source language becomes less important when the English-centric model scales up. In addition, different types of tasks exhibit different multilingual transfer abilities. These findings demonstrate that English-centric models not only possess multilingual transfer ability but may even surpass the transferability of multilingual pretrained models if well-trained. By showing the strength and weaknesses, the experiments also provide valuable insights into enhancing multilingual reasoning abilities for the English-centric models.
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。
