Hallucination Detection on XSum (PRR)
0.37PRRRAUQ
Evaluation Results
| Method | Links | |
|---|---|---|
| RAUQBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.37 | |
| SATRMD+MSPBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.362 | |
| TADBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.269 | |
| LookBackLensBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.171 | |
| SheepsBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.122 | |
| FactoscopeBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.105 | |
| SAPLMABackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | -0.035 | |
| MINDBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | -0.077 |