MAD-X Base

Reported on 2 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Cross-LingualonXCOPA
Accuracy· uses extra data· 2020-04-30
60.94
best: 94.4 (PaLM 2 (few-shot))
SOTA
MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer arXiv:2005.00052
Cross-Lingual TransferonXCOPA
Accuracy· uses extra data· 2020-04-30
60.94
best: 94.4 (PaLM 2 (few-shot))
SOTA
MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer arXiv:2005.00052