Yahoo
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Sequence Classification | Yahoo | Micro F157.13 | 64 | |
| Language Modeling | Yahoo (test) | NLL326.7 | 48 | |
| Topic Classification | Yahoo | Accuracy70.3 | 42 | |
| Topic Classification | Yahoo (test) | Accuracy77.1 | 36 | |
| Text Classification | Yahoo | Micro F1 Score72.5 | 33 | |
| Multi-label classification | Yahoo Arts 1 | Macro-AUC0.7512 | 32 | |
| Trigger inversion | Yahoo (test) | Trigger Inversion Success Rate30 | 26 | |
| Trigger inversion | Yahoo high poison rate | Success Rate29 | 26 | |
| Backdoor Detection | Yahoo | Tell me seriously10 | 24 | |
| Classification | Yahoo | Expected Calibration Error (ECE)3.53 | 24 | |
| Multi-label Classification | yahoo Business1 | Macro-AUC81.15 | 24 | |
| Multi-label Classification | yahoo Business1 | Ranking Loss0.1267 | 24 | |
| Multi-label classification | yahoo Business 1 | Macro-F136.82 | 24 | |
| Multi-label classification | Yahoo Arts1 | Macro-F128.31 | 24 | |
| Domain mixture recovery | Yahoo 10 cls. | MSE0.001 | 22 | |
| Trigger inversion | Yahoo | Trigger Inversion Success Rate30 | 22 | |
| Adversarial Attack | Yahoo | ASR93.5 | 22 | |
| Topic-oriented text understanding | Yahoo StandardCL (test) | Accuracy70.34 | 20 | |
| Anomaly Detection | YAHOO | PA-F186.9 | 18 | |
| Language Modeling | Yahoo | Prior LL-325.7 | 18 | |
| Anomaly Detection | Yahoo (test) | F1 Score88.5 | 17 | |
| Trigger Inversion | Yahoo mb - 1 token high poison rate (test) | Inversion Success Rate10 | 14 | |
| Trigger Inversion | Yahoo Tell me seriously - 3 tokens high poison rate (test) | Inversion Success Rate1 | 14 | |
| Text Clustering | Yahoo B (test) | Accuracy87.4 | 14 | |
| Text Clustering | Yahoo (F) (test) | Accuracy73.7 | 14 |
Showing 25 of 65 rows