ELECTRA (single model)

Reported on 3 benchmarks across 2 tasks · 1 paper

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

Natural Language Processing2 results

Question AnsweringonSQuAD2.0
EM
88.716
best: 90.939 (IE-Net (ensemble))
Question AnsweringonSQuAD2.0
F1
91.365
best: 93.214 (IE-Net (ensemble))

Adversarial1 result

Adversarial RobustnessonAdvGLUE
Accuracy· 2021-11-04
0.4169
best: 0.6086 (DeBERTa (single model))
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models arXiv:2111.02840