Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Uncertainty Estimation on Natural Questions (NQ)
Loading...
0.77
AUROC
Proposed
0.4788
0.5544
0.63
0.7056
Apr 30, 2026
AUROC
AUPRC
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUROC
AUPRC
Proposed
Backbone Model=LLaMA-3...
2026.04
0.77
0.81
SAR
Backbone Model=LLaMA-3...
2026.04
0.75
0.8
Perplexity
Backbone Model=LLaMA-3...
2026.04
0.67
0.73
Focus
Backbone Model=LLaMA-3...
2026.04
0.64
0.69
Semantic
Backbone Model=LLaMA-3...
2026.04
0.63
0.68
P(True)
Backbone Model=LLaMA-3...
2026.04
0.61
0.65
Eigen
Backbone Model=LLaMA-3...
2026.04
0.57
0.64
ATRMD
Backbone Model=LLaMA-3...
2026.04
0.54
0.62
Attention
Backbone Model=LLaMA-3...
2026.04
0.49
0.57
Feedback
Search any
task
Search any
task