List your company
ResearchFormerly WizWand

Selective Generation on CNN

75.8ROC-AUCTAD
46.26453.93261.669.268Aug 20, 2024
Updated 6mo ago

Evaluation results

MethodLinks
TADBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0875.8
TADBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0873.9
SheepsBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0872.1
LookBackLensBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0871.4
LookBackLensBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0869.8
CCPBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0869.7
TADBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0869.6
CCPBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0868.9
SATRMDBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0868.4
MSPBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0868.1
LookBackLensBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0868.1
SheepsBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0867.7
CCPBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0867.6
MSPBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0866.9
MSPBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0866.4
SheepsBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0866.3
MINDBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0865.8
SATRMDBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0863.4
Simple FocusBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0863.3
SATRMDBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0862.7
Mean Token EntropyBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0862.4
PerplexityBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0862.2
MINDBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0862.2
MINDBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0862
Simple FocusBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0861.8
Semantic DensityBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0861.1
Simple FocusBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0860.7
FocusBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0860.4
SARBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0859.6
LUQBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0859.1
Lexical Similarity Rouge-LBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0859
LUQBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0858.7
FocusBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0858.5
DegMat NLI Score entail.Base Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0858.3
EVL NLI Score entail.Base Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0858.1
PerplexityBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0857.3
LUQBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0857.1
EigenScoreBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0857
SAPLMABase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0856.9
Semantic DensityBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0856.1
Semantic DensityBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0855.3
EigenScoreBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0855.2
Semantic EntropyBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0855.1
FocusBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0854.8
SARBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0854.8
DegMat NLI Score entail.Backbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0854.7
Mean Token EntropyBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0854.7
Lexical Similarity Rouge-LBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0854.7
EVL NLI Score entail.Backbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0854.5
FactoscopeBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0854.3
Semantic EntropyBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0854.3
PerplexityBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0854.2
DegMat NLI Score entail.Backbone=Gemma-2 9b, Reference Metric=AlignScore2024.0853.9
Semantic EntropyBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0853.7
SAPLMABackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0853.4
EVL NLI Score entail.Backbone=Gemma-2 9b, Reference Metric=AlignScore2024.0853.4
SARBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0853.2
SAPLMABackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0852.7
Mean Token EntropyBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0852.3
Ecc. NLI Score entail.Backbone=Gemma-2 9b, Reference Metric=AlignScore2024.0851.8
Lexical Similarity Rouge-LBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0850.8
FactoscopeBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0850.6
Ecc. NLI Score entail.Base Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0850.5
FactoscopeBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0849.4
EigenScoreBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0849.1
Ecc. NLI Score entail.Backbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0847.4