Binary Classification on jigsaw
0.97ROC AUCResNet
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ResNetText Model=ROBERTa-large, Text Processing=text_tokenized2024.03 | 0.97 | — | |
| FTTransformerText Model=ROBERTa-large, Text Processing=text_tokenized2024.03 | 0.968 | — | |
| Best single model (Shi et al., 2021)2024.03 | 0.967 | — | |
| TromptText Model=text-embedding-3-large (OpenAI), Text Processing=text_embedded2024.03 | 0.947 | 4,285.1 | |
| ResNetText Model=text-embedding-3-large (OpenAI), Text Processing=text_embedded2024.03 | 0.945 | 56.5 | |
| FTTransformerText Model=text-embedding-3-large (OpenAI), Text Processing=text_embedded2024.03 | 0.945 | 337.4 | |
| LightGBMText Model=text-embedding-3-large (OpenAI), Text Processing=text_embedded2024.03 | 0.926 | 1,732.9 | |
| TromptText Model=all-roberta-large-v1 (Sentence Transformer), Text Processing=text_embedded2024.03 | 0.885 | 480.4 | |
| ResNetText Model=all-roberta-large-v1 (Sentence Transformer), Text Processing=text_embedded2024.03 | 0.883 | 36.1 | |
| FTTransformerText Model=all-roberta-large-v1 (Sentence Transformer), Text Processing=text_embedded2024.03 | 0.882 | 100.8 | |
| LightGBMText Model=all-roberta-large-v1 (Sentence Transformer), Text Processing=text_embedded2024.03 | 0.865 | 571.1 |