| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| XLNet: Generalized Autoregressive Pretraining for Language Understanding | ✓ Link | 98.63% | XLNet | 2019-06-19 |
| How to Fine-Tune BERT for Text Classification? | ✓ Link | 98.08% | BERT-ITPT-FiT | 2019-05-14 |
| Unsupervised Data Augmentation for Consistency Training | ✓ Link | 97.95% | BERT Finetune + UDA | 2019-04-29 |
| Sampling Bias in Deep Active Classification: An Empirical Study | ✓ Link | 97.1% | ULMFiT (Small data) | 2019-09-20 |
| Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach | ✓ Link | 95.97% | COSINE | 2020-10-15 |