Reading Comprehension on AdversarialQA

Metric: D(BiDAF): F1 (higher is better)

LeaderboardDataset
Loading chart...
#ModelD(BiDAF): F1Extra DataPaperDateCode
1RoBERTa-Large74.1YesBeat the AI: Investigating Adversarial Human Ann...2020-02-02Code
2BERT-Large71.3YesBeat the AI: Investigating Adversarial Human Ann...2020-02-02Code
3BiDAF28.6YesBeat the AI: Investigating Adversarial Human Ann...2020-02-02Code