| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Factual Consistency Evaluation | FRANK CNNDM | Spearman Correlation61.8 | 30 | |
| Factual Consistency Evaluation | FRANK-XSum (FRK-X) | Spearman Correlation32.1 | 30 | |
| Factual Consistency Evaluation | FRANK CNNDM (test) | PCC67.7 | 22 | |
| Factual Consistency Evaluation | FRANK-XSum (test) | Pearson Correlation Coefficient38.3 | 22 | |
| Hallucination Detection | FRANK | Balanced Acc77.2 | 18 | |
| Faithfulness evaluation | FRANK | Pearson Corr0.841 | 10 | |
| Factual Consistency Evaluation | FRANK CNNDM | Pearson R68.9 | 8 | |
| Factual Consistency Evaluation | FRANK XSum | Pearson Correlation Coefficient38.9 | 8 | |
| Factuality Error Localization | FRANK | Accuracy (OutE)56.7 | 3 |