Search papers, labs, and topics across Lattice.
4
0
8
8
It is shown the path to generalizing L2 reasoning to held-out languages goes through broader language coverage, readily available multilingual non-reasoning data, and a sufficient English reasoning backbone, indicating that reasoning is a language-agnostic behavior that can be transferred across typologically diverse languages through careful data mixing.
Smaller models can outperform larger counterparts in linguistic reasoning tasks, challenging assumptions about model size and capability.
Adaptive sampling can cut human evaluation costs while boosting the accuracy of model rankings in NLP tasks.
Forget brute-force scaling: Tiny Aya proves a 3B parameter model can achieve state-of-the-art multilingual performance with clever training and region-aware specialization.
