List your company

Uncertainty Quantification on NQ 16 additional samples (test)

85.6AUROCClustered Self-Assessment
59.91266.58173.2579.919Jun 2, 2026

Evaluation results

MethodLinks
Clustered Self-AssessmentBackbone=Qwen3-14B2026.0685.6
Clustered Self-AssessmentBackbone=Qwen2.5-7B2026.0685.1
Clustered Self-AssessmentBackbone=Qwen2.5-32B2026.0685.1
Clustered Self-AssessmentBackbone=Gemma-3-12B2026.0684.1
Clustered Self-AssessmentBackbone=Qwen3-30B-A3B2026.0684
Clustered Self-AssessmentBackbone=Qwen2.5-14B2026.0683.9
EigVBackbone=Qwen2.5-7B2026.0683.4
Semantic EntropyBackbone=Qwen3-14B2026.0682.9
EigVBackbone=Qwen3-14B2026.0682.7
Semantic EntropyBackbone=Qwen2.5-7B2026.0682
Clustered Self-AssessmentBackbone=Gemma-3-27B2026.0682
EigVBackbone=Qwen2.5-32B2026.0681.8
Semantic EntropyBackbone=Qwen2.5-32B2026.0681.2
Semantic EntropyBackbone=Qwen3-30B-A3B2026.0681
EigVBackbone=Qwen3-30B-A3B2026.0681
DegBackbone=Gemma-3-12B2026.0680.8
DegBackbone=Qwen2.5-7B2026.0680.3
EigVBackbone=Qwen2.5-14B2026.0680.2
P(True)Backbone=Qwen3-14B2026.0679.9
Semantic EntropyBackbone=Qwen2.5-14B2026.0679.6
DegBackbone=Qwen3-14B2026.0679.6
SARBackbone=Qwen2.5-7B2026.0679
SARBackbone=Qwen3-14B2026.0679
DegBackbone=Gemma-3-27B2026.0678.9
DegBackbone=Qwen2.5-32B2026.0678.6
P(True)Backbone=Qwen2.5-32B2026.0678.5
P(True)Backbone=Qwen3-30B-A3B2026.0678.3
sentenceSARBackbone=Qwen2.5-7B2026.0677.9
ProbabilityBackbone=Qwen2.5-7B2026.0677.6
DegBackbone=Qwen3-30B-A3B2026.0677.5
ProbabilityBackbone=Qwen3-14B2026.0677.4
SARBackbone=Qwen2.5-32B2026.0677.4
SARBackbone=Qwen3-30B-A3B2026.0677.4
DegBackbone=Qwen2.5-14B2026.0677.3
Predictive EntropyBackbone=Qwen2.5-7B2026.0677
Eigen ScoreBackbone=Qwen2.5-7B2026.0676.9
sentenceSARBackbone=Qwen3-14B2026.0676.9
EccBackbone=Qwen2.5-7B2026.0676.9
ProbabilityBackbone=Qwen2.5-32B2026.0676.3
Predictive EntropyBackbone=Qwen3-14B2026.0676.3
SARBackbone=Qwen2.5-14B2026.0676.2
EccBackbone=Gemma-3-27B2026.0676
sentenceSARBackbone=Qwen2.5-32B2026.0675.9
EccBackbone=Qwen2.5-32B2026.0675.9
EccBackbone=Qwen3-14B2026.0675.9
LN EntropyBackbone=Qwen2.5-7B2026.0675.7
Eigen ScoreBackbone=Qwen3-14B2026.0675.6
EccBackbone=Gemma-3-12B2026.0675.6
ProbabilityBackbone=Gemma-3-27B2026.0675.5
tokenSARBackbone=Gemma-3-12B2026.0675.4
LN EntropyBackbone=Qwen3-14B2026.0675.2
Predictive EntropyBackbone=Qwen2.5-32B2026.0675.1
sentenceSARBackbone=Qwen2.5-14B2026.0675.1
EigVBackbone=Gemma-3-12B2026.0675.1
Eigen ScoreBackbone=Qwen2.5-32B2026.0675
tokenSARBackbone=Gemma-3-27B2026.0675
PerplexityBackbone=Gemma-3-27B2026.0674.9
sentenceSARBackbone=Qwen3-30B-A3B2026.0674.9
PerplexityBackbone=Qwen2.5-7B2026.0674.8
ProbabilityBackbone=Qwen3-30B-A3B2026.0674.8
ProbabilityBackbone=Qwen2.5-14B2026.0674.7
PerplexityBackbone=Gemma-3-12B2026.0674.5
Predictive EntropyBackbone=Qwen2.5-14B2026.0674.3
EccBackbone=Qwen2.5-14B2026.0674.3
Predictive EntropyBackbone=Qwen3-30B-A3B2026.0674.1
LN EntropyBackbone=Qwen3-30B-A3B2026.0673.9
EccBackbone=Qwen3-30B-A3B2026.0673.9
LN EntropyBackbone=Qwen2.5-32B2026.0673.8
PerplexityBackbone=Qwen3-14B2026.0673.7
Eigen ScoreBackbone=Qwen2.5-14B2026.0673.5
EigVBackbone=Gemma-3-27B2026.0673.5
Eigen ScoreBackbone=Qwen3-30B-A3B2026.0673.3
tokenSARBackbone=Qwen2.5-7B2026.0673.2
P(True)Backbone=Qwen2.5-14B2026.0673.1
PerplexityBackbone=Qwen3-30B-A3B2026.0672.9
ProbabilityBackbone=Gemma-3-12B2026.0672.9
P(True)Backbone=Qwen2.5-7B2026.0672.9
PerplexityBackbone=Qwen2.5-32B2026.0672.8
Semantic EntropyBackbone=Gemma-3-12B2026.0672.8
tokenSARBackbone=Qwen3-14B2026.0672.5
LN EntropyBackbone=Qwen2.5-14B2026.0672
tokenSARBackbone=Qwen2.5-32B2026.0671.4
tokenSARBackbone=Qwen3-30B-A3B2026.0671.4
SARBackbone=Gemma-3-12B2026.0671
Semantic EntropyBackbone=Gemma-3-27B2026.0671
PerplexityBackbone=Qwen2.5-14B2026.0670.6
tokenSARBackbone=Qwen2.5-14B2026.0670.1
sentenceSARBackbone=Gemma-3-12B2026.0669.5
Predictive EntropyBackbone=Gemma-3-12B2026.0668.8
sentenceSARBackbone=Gemma-3-27B2026.0668.3
Predictive EntropyBackbone=Gemma-3-27B2026.0668.1
SARBackbone=Gemma-3-27B2026.0667.8
LN EntropyBackbone=Gemma-3-12B2026.0667.3
Eigen ScoreBackbone=Gemma-3-12B2026.0666.1
P(True)Backbone=Gemma-3-27B2026.0665.9
Eigen ScoreBackbone=Gemma-3-27B2026.0665.6
LN EntropyBackbone=Gemma-3-27B2026.0664.9
P(True)Backbone=Gemma-3-12B2026.0660.9