多语言模型真的在改进吗？隔离真正的跨语言迁移
Are Multilingual Models Actually Improving? Isolating True Cross-Lingual Transfer
AI总结：
提出硬度调整迁移（HAT）分数以准确衡量跨语言迁移强度，发现小模型迁移未失效、随模型大小迁移进步慢于预期、但随时间推移有明显进步。
摘要：
跨语言迁移是指模型将能力从资源丰富的源语言泛化到资源不足的目标语言的能力。现有的模型迁移强度度量将迁移的改进与源语言准确率的普遍改进混为一谈。我们提倡一种称为硬度调整迁移（HAT）分数的替代指标，它能可靠地捕捉迁移强度，并利用它推导出关于影响迁移强度因素的多个见解。我们对二十种不同的语言模型和三个主流的多语言基准数据集的分析表明：1）小模型中的迁移并未失效；2）随着模型规模的增大，我们在跨语言迁移方面的进展比预期的要慢；3）随着时间的推移，我们取得了明显的进步。
英文摘要：
Cross-lingual transfer is a model's ability to generalize capabilities from well-represented source languages to under-represented target languages. Existing measures of a model's transfer strength conflate improvements in transfer with general improvements to accuracy in the source language. We advocate for an alternate metric that reliably captures transfer strength called Hardness Adjusted Transfer (HAT) Score, and use it to derive multiple insights on factors influencing transfer strength. Our analysis across twenty diverse language models and three popular mainstream multilingual benchmarks argues that 1) transfer in small models is not broken, 2) we are making slower than expected progress in cross-lingual transfer with model size, and 3) we have made clear progress over time.
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。
