Binary Classification on fake
97.9ROC AUCResNet
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ResNetText Model=ROBERTa-large, Text Processing=text_tokenized2024.03 | 97.9 | 5.5 | |
| TromptText Model=text-embedding-3-large (OpenAI), Text Processing=text_embedded2024.03 | 97.6 | 40.8 | |
| Best single model (Shi et al., 2021)2024.03 | 96.7 | — | |
| LightGBMText Model=text-embedding-3-large (OpenAI), Text Processing=text_embedded2024.03 | 96.6 | 131 | |
| FTTransformerText Model=ROBERTa-large, Text Processing=text_tokenized2024.03 | 96 | 5.5 | |
| TromptText Model=all-roberta-large-v1 (Sentence Transformer), Text Processing=text_embedded2024.03 | 95.8 | 18.8 | |
| LightGBMText Model=all-roberta-large-v1 (Sentence Transformer), Text Processing=text_embedded2024.03 | 95.4 | 15.5 | |
| FTTransformerText Model=all-roberta-large-v1 (Sentence Transformer), Text Processing=text_embedded2024.03 | 93.6 | 19.7 | |
| ResNetText Model=all-roberta-large-v1 (Sentence Transformer), Text Processing=text_embedded2024.03 | 93.4 | 7.3 | |
| ResNetText Model=text-embedding-3-large (OpenAI), Text Processing=text_embedded2024.03 | 92.3 | 10.4 | |
| FTTransformerText Model=text-embedding-3-large (OpenAI), Text Processing=text_embedded2024.03 | 91.1 | 23.6 |