List your company

Selective Generation on SamSum

82.1ROC-AUCLookBackLens
39.25250.37661.572.624Aug 20, 2024

Evaluation results

MethodLinks
LookBackLensBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0882.1
TADBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0881.4
TADBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0880.1
SATRMDBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0877.1
SheepsBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0876.6
Mean Token EntropyBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0876.5
LookBackLensBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0876.4
SAPLMABackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0876.3
LookBackLensBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0876
PerplexityBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0875.7
SATRMDBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0875.6
TADBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0875.2
SATRMDBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0872.1
FocusBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0872
MINDBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0871.9
Mean Token EntropyBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0871.3
Semantic DensityBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0870.7
MINDBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0870.4
SheepsBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0870.4
SAPLMABase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0870.4
PerplexityBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0870.3
DegMat NLI Score entail.Backbone=Gemma-2 9b, Reference Metric=AlignScore2024.0868.8
EVL NLI Score entail.Backbone=Gemma-2 9b, Reference Metric=AlignScore2024.0868.5
SAPLMABackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0868.2
FocusBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0866.5
LUQBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0865.6
SheepsBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0865.2
LUQBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0864.7
Semantic DensityBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0864.6
SARBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0863.8
Simple FocusBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0862.9
Mean Token EntropyBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0862.8
Simple FocusBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0862.6
PerplexityBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0861.2
Lexical Similarity Rouge-LBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0860.7
SARBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0858
DegMat NLI Score entail.Backbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0857.5
FactoscopeBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0857.5
FocusBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0857.1
EVL NLI Score entail.Backbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0857.1
Semantic DensityBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0856.5
Simple FocusBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0856.4
DegMat NLI Score entail.Base Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0856.4
MSPBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0856.3
Semantic EntropyBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0856.2
MINDBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0856.1
EVL NLI Score entail.Base Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0855.8
EigenScoreBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0854.8
MSPBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0854.7
SARBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0854.6
LUQBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0853.5
CCPBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0853.5
Ecc. NLI Score entail.Backbone=Gemma-2 9b, Reference Metric=AlignScore2024.0853.3
EigenScoreBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0853.2
Lexical Similarity Rouge-LBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0853.1
EigenScoreBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0852.9
CCPBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0852.5
Ecc. NLI Score entail.Base Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0852.4
Semantic EntropyBase Model=Llama-3.1 8b, Ground Truth Metric=AlignScore2024.0850.7
Ecc. NLI Score entail.Backbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0850.3
Lexical Similarity Rouge-LBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0849.9
Semantic EntropyBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0849.7
FactoscopeBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0847.2
CCPBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0844.5
MSPBackbone=Qwen-2.5 7b, UQ Level=Sequence-level, Reference Metric=AlignScore2024.0844.3
FactoscopeBackbone=Gemma-2 9b, Reference Metric=AlignScore2024.0840.9