| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| AnglE-optimized Text Embeddings | ✓ Link | 93.54 | AnglE-LLaMA-7B | 2023-09-22 |
| LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning | ✓ Link | 93.3 | LM-CPPF RoBERTa-base | 2023-05-29 |
| Entailment as Few-Shot Learner | ✓ Link | 92.5 | RoBERTa-large 355M + Entailment as Few-shot Learner | 2021-04-29 |
| GPU Kernels for Block-Sparse Weights | ✓ Link | 92.2 | Block-sparse LSTM | 2017-12-01 |
| A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors | ✓ Link | 90.6 | byte mLSTM7 | 2018-05-14 |
| Universal Sentence Encoder | ✓ Link | 87.45 | USE_T+CNN (w2v w.e.) | 2018-03-29 |
| Improved Sentence Modeling using Suffix Bidirectional LSTM | 86.5 | SuBiLSTM-Tied | 2018-05-18 | |
| Investigating Capsule Networks with Dynamic Routing for Text Classification | ✓ Link | 85.1 | Capsule-B | 2018-03-29 |
| The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding Distillation with Ensemble Learning | ✓ Link | 82.73 | STM+TSED+PT+2L | 2019-05-31 |