List your company

Uncertainty Quantification on Aggregate All 11 Datasets

55.7Mean PRRTAD
13.47624.43835.446.362Aug 20, 2024

Evaluation results

MethodLinks
TADBackbone=Gemma-2 9b2024.0855.72.36
TADBackbone=Llama-3.1 8b2024.0854.51.82
LookBackLensBackbone=Gemma-2 9b2024.08534.64
SheepsBackbone=Llama-3.1 8b2024.08513.09
LookBackLensBackbone=Llama-3.1 8b2024.0849.94.45
SATRMDBackbone=Gemma-2 9b2024.0848.44
SATRMDBackbone=Llama-3.1 8b2024.0848.14.45
MINDBackbone=Gemma-2 9b2024.0846.47.55
SheepsBackbone=Gemma-2 9b2024.0845.78.09
MINDBackbone=Llama-3.1 8b2024.08456.36
SAPLMABackbone=Gemma-2 9b2024.0840.29.36
FocusBackbone=Gemma-2 9b2024.0838.410.18
Simple FocusBackbone=Gemma-2 9b2024.0836.69.45
Mean Token EntropyBackbone=Gemma-2 9b2024.0835.610.45
PerplexityBackbone=Gemma-2 9b2024.0834.810.91
MSPBackbone=Gemma-2 9b2024.0834.310.27
MSPBackbone=Llama-3.1 8b2024.0833.610.55
Simple FocusBackbone=Llama-3.1 8b2024.0833.510.45
PerplexityBackbone=Llama-3.1 8b2024.0833.411.36
CCPBackbone=Gemma-2 9b2024.083212.64
Semantic DensityBackbone=Gemma-2 9b2024.083211.64
Mean Token EntropyBackbone=Llama-3.1 8b2024.0831.311.55
SARBackbone=Gemma-2 9b2024.0831.111.73
SAPLMABackbone=Llama-3.1 8b2024.0830.811.82
FocusBackbone=Llama-3.1 8b2024.0830.512.55
LUQBackbone=Gemma-2 9b2024.0830.213.82
CCPBackbone=Llama-3.1 8b2024.0828.713.64
DegMat NLI Score entail.Backbone=Gemma-2 9b2024.0828.313.91
EVL NLI Score entail.Backbone=Gemma-2 9b2024.0827.914.91
Semantic DensityBackbone=Llama-3.1 8b2024.0827.311.82
SARBackbone=Llama-3.1 8b2024.0825.812.45
Lexical Similarity Rouge-LBackbone=Gemma-2 9b2024.0825.414.82
LUQBackbone=Llama-3.1 8b2024.0824.613.55
DegMat NLI Score entail.Backbone=Llama-3.1 8b2024.0824.413
Semantic EntropyBackbone=Gemma-2 9b2024.0823.716.64
Ecc. NLI Score entail.Backbone=Gemma-2 9b2024.0823.617.45
EVL NLI Score entail.Backbone=Llama-3.1 8b2024.0823.214.55
FactoscopeBackbone=Llama-3.1 8b2024.0822.217.45
Lexical Similarity Rouge-LBackbone=Llama-3.1 8b2024.0821.616.18
Semantic EntropyBackbone=Llama-3.1 8b2024.0821.216.91
Ecc. NLI Score entail.Backbone=Llama-3.1 8b2024.0820.516.82
EigenScoreBackbone=Gemma-2 9b2024.082019.18
EigenScoreBackbone=Llama-3.1 8b2024.0819.118.18
FactoscopeBackbone=Gemma-2 9b2024.0815.119