Hallucination Detection on CNN
0.477PRRSATRMD+MSP
Evaluation Results
| Method | Links | |
|---|---|---|
| SATRMD+MSPBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.477 | |
| RAUQBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.452 | |
| MINDBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.074 | |
| LookBackLensBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0 | |
| SAPLMABackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | -0.009 | |
| SheepsBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | -0.056 | |
| FactoscopeBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | -0.065 | |
| TADBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | -0.101 |