HyperAI

Fact Verification On Kilt Fever

Metrics

Accuracy
KILT-AC
R-Prec
Recall@5

Results

Performance results of various models on this benchmark

Comparison Table
Model NameAccuracyKILT-ACR-PrecRecall@5
Model 185.5864.4175.684.95
Model 289.5471.2881.4589.56
Model 366.141.8849.2470.16
Model 469.410.00.00.0
Model 570.710.00.00.0
Model 612.570.00.00.0
Model 778.930.00.00.0
Model 871.420.00.00.0
Model 988.9965.6874.7787.89
Model 1072.340.00.00.0
kilt-a-benchmark-for-knowledge-intensive76.30.00.00.0
kilt-a-benchmark-for-knowledge-intensive86.3153.4561.9475.55
Model 1371.380.00.00.0
Model 1469.6858.5872.9373.52
re2g-retrieve-rerank-generate-289.5578.5388.9292.52
Model 1623.010.00.00.0
Model 1786.7447.6855.3374.29
Model 1871.120.00.00.0
Model 1986.3263.9474.4887.52
Model 200.00.074.4887.52
Model 210.00.083.6488.15
Model 2288.450.00.00.0
Model 2361.60.00.00.0
Model 2471.240.00.00.0
Model 2571.580.00.00.0
Model 2667.980.00.00.0
Model 2768.430.00.00.0
Model 280.00.084.4588.62
Model 2933.580.00.00.0
Model 3069.710.00.00.0
Model 3189.120.00.00.0
Model 3276.260.00.00.0
Model 330.00.084.0789.41