We systematically investigate cross-lingual ability transfer in language models through controlled experiments across three problem sets: algorithmic addition, graph navigation, and natural language modeling. Our experimental design creates high-resource and low-resource “language” pairs differing in vocabulary, grammar, and computational requirements. We show that training on mixed datasets consistently enables strong positive transfer, significantly improving low-resource language performance compared to training on low amount of data in isolation. We observe improvements from 0% to 100% accuracy in arithmetic tasks, from 24% to 98% accuracy in graph navigation tasks, and 69.6% perplexity reduction in natural language modeling. We demonstrate that transfer effectiveness depends on computational complexity and linguistic differences, where grammar modifications support stronger transfer than vocabulary modifications. These findings provide compelling evidence that cross-lingual ability transfer is a robust mechanism which contributes to the quality of large language models in low-resource languages.

Natural language understanding has recently seen a surge of progress with the use of sentence encoders like ELMo (Peters et al., 2018a) and BERT (Devlin et al., 2019) which are pretrained on variants of language modeling. We conduct the first large-scale systematic study of candidate pretraining tasks, comparing 19 different tasks both as alternatives and complements to language modeling. Our primary results support the use language modeling, especially when combined with pretraining on additional labeled-data tasks. However, our results are mixed across pretraining tasks and show some concerning trends: In ELMo’s pretrain-then-freeze paradigm, random baselines are worryingly strong and results vary strikingly across target tasks. In addition, fine-tuning BERT on an intermediate task often negatively impacts downstream transfer. In a more positive trend, we see modest gains from multitask training, suggesting the development of more sophisticated multitask and transfer learning techniques as an avenue for further research.