| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Object Hallucination Probing | Style-POPE Popular | F1 Score80.2 | 72 | |
| Object Hallucination Probing | Style-POPE (Random) | Accuracy88.2 | 63 | |
| Object Hallucination Probing | Style-POPE Adversarial | Accuracy75.2 | 63 | |
| Hallucination Evaluation | Style-POPE Overall Average | F1 Score79.1 | 9 | |
| Hallucination Evaluation | Style-POPE Random | F1 Score0.844 | 9 | |
| Hallucination Evaluation | Style-POPE Adversarial | F1 Score75.3 | 9 |