Search papers, labs, and topics across Lattice.
This paper introduces Multilingual GSM-Symbolic, a novel, extensible dataset of 30,000 item-matched mathematical reasoning problems across 15 languages, utilizing symbolic templates to ensure generalization and prevent overfitting. The study quantifies the primary determinants of cross-lingual capability transfer, finding model size, language resource level, and reasoning ability to be positive predictors, while typological distance is a negative one, with these factors exhibiting interdependencies. The proposed analysis framework explains a significant portion of between-language variation and enables accurate performance prediction on unseen languages with minimal data.
A 32B model in Marathi performs like a 10B model in English, revealing how model size and reasoning can bridge language resource gaps in cross-lingual transfer.
We understand little about how capabilities acquired in one language carry over to another, or what governs this transfer: evaluations rely on incomparable, saturation-prone datasets and rarely examine its determinants jointly. Identifying what predicts transfer would let us avoid exhaustive evaluation across all language pairs and let developers target the factors that limit performance in low-resource languages. To evaluate cross-lingual capability transfer, we introduce Multilingual GSM-Symbolic, an extensible multilingual mathematical dataset covering 30,000 item-matched question-answer pairs and spanning 15 languages. It utilises symbolic templates to prevent overfitting and ensure generalisation by allowing generation of millions of high-quality variations from a single sample. Using Multilingual GSM-Symbolic, we quantify the largest determinants of capability as model size ($\beta = 1.77$), language resource level ($\beta = 0.77$), reasoning ($\beta = 0.67$) and typological distance ($\beta = -0.25$). This joint estimation allows these determinants to be expressed in terms of one another: a 32B model evaluated in Marathi performs like a 10B model in English. Our findings have important implications for model developers, showing that model size and reasoning narrow the performance gap between low- and high-resource languages ($\beta = -0.27$ and $\beta = -0.20$, respectively), while similar levers have little or no effect on typologically distant languages. Overall, our analysis framework explains 92% of between-language variation, but only 23% of the model-by-language variation, and predicts a model's performance on an unseen language within 6.0pp (r=.96). Incorporating measurements from just 10 templates in the target language reduces this to 4.19pp, enabling reasonable estimates of performance with little or no downstream dataset.
