Selective Generation on TriviaQA (PRR AlignScore)
0.714PRR (AlignScore)DegMat NLI Score Entail.
Evaluation Results
| Method | Links | |
|---|---|---|
| DegMat NLI Score Entail.Model=Llama 8b v3.12025.02 | 0.714 | |
| SARModel=Llama 8b v3.12025.02 | 0.71 | |
| SentenceSARModel=Llama 8b v3.12025.02 | 0.703 | |
| SATRMD+MSPModel=Llama 8b v3.12025.02 | 0.702 | |
| PerplexityModel=Llama 8b v3.12025.02 | 0.689 | |
| Maximum Sequence ProbabilityModel=Llama 8b v3.12025.02 | 0.687 | |
| EigValLaplacian NLI Score Entail.Model=Llama 8b v3.12025.02 | 0.669 | |
| Semantic EntropyModel=Llama 8b v3.12025.02 | 0.669 | |
| Eccentricity NLI Score Entail.Model=Llama 8b v3.12025.02 | 0.654 | |
| HUQ-SATRMDModel=Llama 8b v3.12025.02 | 0.646 | |
| Lexical Similarity ROUGE-LModel=Llama 8b v3.12025.02 | 0.621 | |
| EigenScoreModel=Llama 8b v3.12025.02 | 0.619 | |
| SAPLMAModel=Llama 8b v3.12025.02 | 0.522 | |
| FactoscopeModel=Llama 8b v3.12025.02 | -0.046 |