Factual Knowledge on KoLA WaterBench (test)
37.5GMAAR
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| AARModel=OPT-1.3B2025.12 | 37.5 | 1 | 0.695 | |
| DualGuardModel=OPT-1.3B2025.12 | 35.5 | 0.95 | 0.65 | |
| KGWModel=OPT-1.3B2025.12 | 35 | 0.945 | 0.68 | |
| SIRModel=OPT-1.3B2025.12 | 35 | 0.975 | 0.475 | |
| UnbiasedModel=OPT-1.3B2025.12 | 34.5 | 0.78 | 0.635 | |
| OriginalModel=OPT-1.3B2025.12 | 33 | — | — | |
| DIPmarkModel=OPT-1.3B2025.12 | 33 | 0.885 | 0.675 | |
| XSIRModel=OPT-1.3B2025.12 | 31.5 | 0.775 | 0.975 | |
| EWDModel=OPT-1.3B2025.12 | 29.5 | 0.96 | 0.78 | |
| SWEETModel=OPT-1.3B2025.12 | 28.5 | 0.825 | 0.89 | |
| SynthIDModel=OPT-1.3B2025.12 | 25.5 | 0.96 | 0.86 |