Sentiment Classification on Amz (test)
95.8AccuracyICL-gold
Evaluation results
| Method | Links | |
|---|---|---|
| ICL-goldModel=GPT-J, Prompting=Direct, Training data access=true2022.12 | 95.8 | |
| ICL-goldModel=GPT-NeoX, Prompting=Direct, Training data access=true2022.12 | 95.6 | |
| Z-ICLModel=GPT-J, Prompting=Direct, Training data access=false2022.12 | 94.9 | |
| Z-ICLModel=GPT-NeoX, Prompting=Direct, Training data access=false2022.12 | 94 | |
| ICL-randomModel=GPT-NeoX, Prompting=Direct, Training data access=true2022.12 | 92.9 | |
| ICL-randomModel=GPT-J, Prompting=Channel, Training data access=true2022.12 | 91.3 | |
| Random inputsModel=GPT-J, Prompting=Direct, Training data access=false2022.12 | 91.2 | |
| ICL-goldModel=GPT-J, Prompting=Channel, Training data access=true2022.12 | 90.9 | |
| ICL-goldModel=GPT-NeoX, Prompting=Channel, Training data access=true2022.12 | 90.3 | |
| Naive Z-ICLModel=GPT-J, Prompting=Direct, Training data access=false2022.12 | 89.3 | |
| Z-ICLModel=GPT-J, Prompting=Channel, Training data access=false2022.12 | 88.9 | |
| ICL-randomModel=GPT-NeoX, Prompting=Channel, Training data access=true2022.12 | 88.5 | |
| ICL-randomModel=GPT-J, Prompting=Direct, Training data access=true2022.12 | 87.8 | |
| Naive Z-ICLModel=GPT-NeoX, Prompting=Direct, Training data access=false2022.12 | 87.5 | |
| No-demosModel=GPT-J, Prompting=Direct, Training data access=false2022.12 | 87.3 | |
| No-demosModel=GPT-J, Prompting=Channel, Training data access=false2022.12 | 86.1 | |
| Z-ICLModel=GPT-NeoX, Prompting=Channel, Training data access=false2022.12 | 84.3 | |
| Random inputsModel=GPT-NeoX, Prompting=Direct, Training data access=false2022.12 | 83.5 | |
| Random inputsModel=GPT-J, Prompting=Channel, Training data access=false2022.12 | 81.8 | |
| Naive Z-ICLModel=GPT-J, Prompting=Channel, Training data access=false2022.12 | 81.6 | |
| Naive Z-ICLModel=GPT-NeoX, Prompting=Channel, Training data access=false2022.12 | 78.8 | |
| Random inputsModel=GPT-NeoX, Prompting=Channel, Training data access=false2022.12 | 70.4 | |
| No-demosModel=GPT-NeoX, Prompting=Channel, Training data access=false2022.12 | 63.2 | |
| No-demosModel=GPT-NeoX, Prompting=Direct, Training data access=false2022.12 | 50.8 | |
| MajorityTraining data access=false2022.12 | 50 |