Summarization on WaterBench (test)
22.03GMOriginal
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| OriginalModel=OPT-1.3B2025.12 | 22.03 | — | — | |
| DIPmarkModel=OPT-1.3B2025.12 | 21.96 | 0.99 | 0.995 | |
| KGWModel=OPT-1.3B2025.12 | 21.66 | 0.995 | 1 | |
| AARModel=OPT-1.3B2025.12 | 21.35 | 0.78 | 0.98 | |
| UnbiasedModel=OPT-1.3B2025.12 | 21.17 | 1 | 0.995 | |
| SIRModel=OPT-1.3B2025.12 | 21.02 | 0.98 | 0.99 | |
| SWEETModel=OPT-1.3B2025.12 | 20.74 | 1 | 1 | |
| SynthIDModel=OPT-1.3B2025.12 | 20.71 | 1 | 1 | |
| EWDModel=OPT-1.3B2025.12 | 20.6 | 1 | 1 | |
| XSIRModel=OPT-1.3B2025.12 | 20 | 0.88 | 0.955 | |
| DualGuardModel=OPT-1.3B2025.12 | 19.64 | 1 | 1 |