Rome
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
ROME Shortcut Decision-Making 1.0
94.53F1-Score
24
ROME Contextual Ambiguity 1.0
91.92F1 Score
24
ROME Implicit Risks 1.0 (IR)
86.81F1-Score
24
ROME Original 1.0 (Seed)
94.53F1-Score
24
Rome 20
-0.603Xing
4
ROME IR unsafe
95.74F1 Score
4
ROME CA unsafe subset
97.35F1 Score
4
ROME SDM unsafe
100F1 Score
4
Rome
2.088RMSE
2