Hallucination Detection on CoQA (PRR)
0.265PRRRAUQ
Evaluation Results
| Method | Links | |
|---|---|---|
| RAUQBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.265 | |
| SheepsBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.184 | |
| TADBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.143 | |
| SATRMD+MSPBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.142 | |
| LookBackLensBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.116 | |
| MINDBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.112 | |
| FactoscopeBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | 0.014 | |
| SAPLMABackbone=Llama-3.1 8B, Setup=out-of-domain2025.05 | -0.02 |