Crosslingual Generalization through Multitask Finetuning

Open paper
Benchmark Model Rank Results
question-answering-on-storyclozeBLOOMZ#1Accuracy: 96.3
cross-lingual-transfer-on-xcopamT0-13B#2Accuracy: 84.45
cross-lingual-transfer-on-xcopaBLOOMZ#4Accuracy: 75.5

Rank counts only results with a code link.