Sentiment and Topic Classification on SST-2 (test)
96.4Macro F1GPT-3 (CC)
Evaluation results
| Method | Links | |
|---|---|---|
| GPT-3 (CC)Backbone=GPT-3, Prompting=CC, Shots=8-shot2023.05 | 96.4 | |
| GPT-3 (DC)Backbone=GPT-3, Prompting=DC, Shots=8-shot2023.05 | 96.3 | |
| GPT-3 (Original)Backbone=GPT-3, Prompting=Original, Shots=8-shot2023.05 | 96 | |
| GPT-J (DC)Backbone=GPT-J, Prompting=DC, Shots=8-shot2023.05 | 94 | |
| GPT-J (Original)Backbone=GPT-J, Prompting=Original, Shots=8-shot2023.05 | 91 | |
| GPT-J (CC)Backbone=GPT-J, Prompting=CC, Shots=8-shot2023.05 | 90.8 | |
| RoBERTa-large (Domain-context Calibration)Model=RoBERTa-large, Setting=DC, Evaluation protocol=Zero-shot prompting2023.05 | 87.2 | |
| RoBERTa-large (Original)Model=RoBERTa-large, Setting=Original, Evaluation protocol=Zero-shot prompting2023.05 | 82.5 | |
| RoBERTa-large (Context Calibration)Model=RoBERTa-large, Setting=CC, Evaluation protocol=Zero-shot prompting2023.05 | 79.4 |