Fact-checking on Fact-checking
75ROC-AUCHUQ-SATRMD
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| HUQ-SATRMDBase Model=Mistral 7b v0.1 Instruct2025.02 | 75 | 41 | |
| SATRMD+CCPBase Model=Mistral 7b v0.1 Instruct2025.02 | 73.9 | 41.4 | |
| CCPBase Model=Mistral 7b v0.1 Instruct2025.02 | 71.6 | 38.8 | |
| SATRMDBase Model=Mistral 7b v0.1 Instruct2025.02 | 64.7 | 27.5 | |
| P(True)Base Model=Mistral 7b v0.1 Instruct2025.02 | 63.8 | 27.6 | |
| Maximum Claim ProbabilityBase Model=Mistral 7b v0.1 Instruct2025.02 | 62 | 27.1 | |
| SAPLMABase Model=Mistral 7b v0.1 Instruct2025.02 | 48.9 | 16.6 |