Hallucination Detection on WMT 19
0.509PRRRAUQ
Evaluation Results
| Method | Links | |
|---|---|---|
| RAUQBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.509 | |
| SATRMD+MSPBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.364 | |
| MINDBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.158 | |
| TADBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.087 | |
| FactoscopeBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.083 | |
| SheepsBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.013 | |
| LookBackLensBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | -0.018 | |
| SAPLMABackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | -0.029 |