List your company

Uncertainty Quantification on XSum

0.806AUROCClustered Self-Assessment
0.35880.47490.5910.7071Jun 2, 2026

Evaluation results

MethodLinks
Clustered Self-AssessmentModel=Qwen3-14B2026.060.806
Clustered Self-AssessmentModel=Qwen2.5-32B2026.060.797
Clustered Self-AssessmentModel=Qwen3-30B-A3B2026.060.781
Clustered Self-AssessmentModel=Qwen2.5-7B2026.060.751
Clustered Self-AssessmentModel=Qwen2.5-14B2026.060.739
Clustered Self-AssessmentModel=Gemma-3-12B2026.060.728
Clustered Self-AssessmentModel=Gemma-3-27B2026.060.713
P(True)Model=Qwen2.5-32B2026.060.709
EigVModel=Qwen3-30B-A3B2026.060.709
Semantic EntropyModel=Qwen3-30B-A3B2026.060.707
EigVModel=Qwen2.5-32B2026.060.706
SARModel=Qwen2.5-7B2026.060.698
Semantic EntropyModel=Qwen2.5-32B2026.060.697
P(True)Model=Qwen3-14B2026.060.696
SARModel=Qwen3-14B2026.060.692
EigVModel=Qwen3-14B2026.060.692
SARModel=Qwen2.5-32B2026.060.691
tokenSARModel=Qwen2.5-32B2026.060.69
PerplexityModel=Qwen3-14B2026.060.689
EigVModel=Qwen2.5-7B2026.060.688
tokenSARModel=Qwen3-14B2026.060.687
tokenSARModel=Qwen2.5-7B2026.060.684
PerplexityModel=Qwen2.5-7B2026.060.681
EigVModel=Qwen2.5-14B2026.060.681
Semantic EntropyModel=Qwen3-14B2026.060.679
Semantic EntropyModel=Qwen2.5-7B2026.060.677
SARModel=Qwen2.5-14B2026.060.676
PerplexityModel=Qwen2.5-32B2026.060.67
LN EntropyModel=Qwen3-14B2026.060.663
Semantic EntropyModel=Qwen2.5-14B2026.060.662
LN EntropyModel=Qwen2.5-7B2026.060.659
DegModel=Qwen3-30B-A3B2026.060.656
PerplexityModel=Gemma-3-12B2026.060.648
DegModel=Qwen2.5-32B2026.060.648
P(True)Model=Qwen2.5-14B2026.060.647
DegModel=Qwen3-14B2026.060.647
tokenSARModel=Qwen2.5-14B2026.060.646
tokenSARModel=Qwen3-30B-A3B2026.060.645
SARModel=Qwen3-30B-A3B2026.060.644
tokenSARModel=Gemma-3-12B2026.060.641
DegModel=Qwen2.5-7B2026.060.64
LN EntropyModel=Qwen2.5-32B2026.060.638
DegModel=Qwen2.5-14B2026.060.637
PerplexityModel=Qwen2.5-14B2026.060.633
PerplexityModel=Gemma-3-27B2026.060.632
EccModel=Qwen3-30B-A3B2026.060.632
tokenSARModel=Gemma-3-27B2026.060.628
LN EntropyModel=Qwen2.5-14B2026.060.627
ProbabilityModel=Gemma-3-12B2026.060.624
EccModel=Qwen2.5-7B2026.060.624
EccModel=Qwen3-14B2026.060.624
Eigen ScoreModel=Qwen3-14B2026.060.623
P(True)Model=Qwen2.5-7B2026.060.62
ProbabilityModel=Gemma-3-27B2026.060.616
EccModel=Qwen2.5-14B2026.060.616
EccModel=Qwen2.5-32B2026.060.615
P(True)Model=Gemma-3-27B2026.060.606
P(True)Model=Qwen3-30B-A3B2026.060.598
PerplexityModel=Qwen3-30B-A3B2026.060.596
SARModel=Gemma-3-12B2026.060.596
SARModel=Gemma-3-27B2026.060.594
DegModel=Gemma-3-27B2026.060.592
DegModel=Gemma-3-12B2026.060.591
EigVModel=Gemma-3-12B2026.060.588
EigVModel=Gemma-3-27B2026.060.585
EccModel=Gemma-3-27B2026.060.579
EccModel=Gemma-3-12B2026.060.576
ProbabilityModel=Qwen3-14B2026.060.572
LN EntropyModel=Gemma-3-27B2026.060.57
sentenceSARModel=Gemma-3-12B2026.060.569
LN EntropyModel=Gemma-3-12B2026.060.568
sentenceSARModel=Qwen3-14B2026.060.568
sentenceSARModel=Gemma-3-27B2026.060.567
Predictive EntropyModel=Gemma-3-12B2026.060.566
Semantic EntropyModel=Gemma-3-12B2026.060.564
Predictive EntropyModel=Qwen3-14B2026.060.563
Predictive EntropyModel=Gemma-3-27B2026.060.563
Semantic EntropyModel=Gemma-3-27B2026.060.563
P(True)Model=Gemma-3-12B2026.060.562
LN EntropyModel=Qwen3-30B-A3B2026.060.558
ProbabilityModel=Qwen2.5-7B2026.060.553
sentenceSARModel=Qwen2.5-7B2026.060.545
Predictive EntropyModel=Qwen2.5-7B2026.060.541
sentenceSARModel=Qwen2.5-14B2026.060.533
Predictive EntropyModel=Qwen2.5-14B2026.060.529
Eigen ScoreModel=Gemma-3-27B2026.060.529
Eigen ScoreModel=Gemma-3-12B2026.060.524
ProbabilityModel=Qwen2.5-14B2026.060.523
ProbabilityModel=Qwen3-30B-A3B2026.060.521
Eigen ScoreModel=Qwen2.5-7B2026.060.519
sentenceSARModel=Qwen3-30B-A3B2026.060.506
Predictive EntropyModel=Qwen3-30B-A3B2026.060.501
sentenceSARModel=Qwen2.5-32B2026.060.498
ProbabilityModel=Qwen2.5-32B2026.060.493
Predictive EntropyModel=Qwen2.5-32B2026.060.492
Eigen ScoreModel=Qwen2.5-32B2026.060.443
Eigen ScoreModel=Qwen2.5-14B2026.060.431
Eigen ScoreModel=Qwen3-30B-A3B2026.060.376