SST2
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Sentiment Analysis | SST2 | ASR99 | 131 | |
| Sentiment Analysis | SST2 | Accuracy94.9541 | 47 | |
| Image Classification | SST2 Rendered | Top-1 Accuracy68.4 | 47 | |
| Trigger Inversion | SST2 | Recall100 | 44 | |
| Trigger inversion | SST2 | Success Rate1 | 44 | |
| Counterfactual Generation | SST2 (test) | SLFR29 | 29 | |
| Sentiment Analysis | SST2 | Spearman Rho (x100)93.32 | 23 | |
| Text embedding | SST2 | T-Value24.69 | 20 | |
| Sentiment Classification | SST2 | Deletion Robustness0.2943 | 20 | |
| Sentiment Analysis | SST2 | Accuracy94.04 | 20 | |
| Backdoor Detection | SST2 high poison rate (test) | Clean Performance Score10 | 18 | |
| Feature Attribution | SST2 | LO-0.199 | 18 | |
| Out-of-Distribution Detection | SST2 (test) | AUROC0.7327 | 17 | |
| Sentiment Classification | SST2 phrase | Accuracy93.96 | 16 | |
| Text Classification | SST2 | Macro-F195.07 | 15 | |
| Sentiment Analysis | SST2 POLISHED Attack (test) | ASR99 | 14 | |
| Sentiment Analysis | SST2 BadNets Attack (test) | ASR97 | 14 | |
| Sentiment Analysis | SST2 UJB Attack (test) | ASR98 | 14 | |
| Graph Classification | SST2 length OOD | Accuracy81.9 | 14 | |
| Sentiment Analysis | SST2 (test) | HS Score54.4 | 14 | |
| Graph Classification | SST2 GraphOOD (test) | Accuracy83.52 | 13 | |
| Sentiment Analysis | SST2 | Accuracy (Pred)100 | 12 | |
| Sentiment Analysis | SST2 Sleeper Attack (test) | ASR99 | 12 | |
| Sentiment Analysis | SST2 CBA Attack (test) | ASR98 | 12 | |
| Text Classification | SST2 | Accuracy93.42 | 10 |
Showing 25 of 59 rows