List your company
ResearchFormerly WizWand

Mathematical Reasoning on ASDiv (AUROC)

66.91AUROCCoT-UQ
46.442851.756457.0762.3836Feb 24, 2025
Updated 8mo ago

Evaluation results

MethodLinks
CoT-UQModel=Llama 3.1-8B, Strategy=AP, Base Aggregation=TOKENSAR2025.0266.91
CoT-UQModel=Llama 3.1-8B, Strategy=AP, Base Aggregation=Probas-min2025.0264.84
CoT-UQModel=Llama 3.1-8B, Strategy=AP, Base Aggregation=Probas-mean2025.0264.52
CoT-UQModel=Llama 2-13B, Strategy=AP, Base Aggregation=TOKENSAR2025.0261.23
CoT-UQModel=Llama 2-13B, Strategy=AP, Base Aggregation=Probas-min2025.0260.74
CoT-UQModel=Llama 2-13B, Strategy=AP, Base Aggregation=Probas-mean2025.0259.44
TOKENSARModel=Llama 3.1-8B, Strategy=AP2025.0258.71
Probas-minModel=Llama 3.1-8B, Strategy=AP2025.0258.69
TOKENSARModel=Llama 2-13B, Strategy=AP2025.0258.37
Probas-meanModel=Llama 3.1-8B, Strategy=AP2025.0258.34
Probas-meanModel=Llama 2-13B, Strategy=AP2025.0257.73
Probas-minModel=Llama 2-13B, Strategy=AP2025.0257.7
CoT-UQModel=Llama 2-13B, Strategy=SE, Base Strategy=Self-Probing, Refinement=KEYStep2025.0257.58
CoT-UQModel=Llama 2-13B, Strategy=SE, Base Strategy=P(True), Refinement=ALLSteps2025.0256.1
CoT-UQModel=Llama 3.1-8B, Strategy=SE, Base Strategy=Self-Probing, Refinement=KEYStep2025.0253.79
CoT-UQModel=Llama 3.1-8B, Strategy=SE, Base Strategy=P(True), Refinement=ALLSteps2025.0253.2
Self-ProbingModel=Llama 2-13B, Strategy=SE2025.0252.35
Self-ProbingModel=Llama 3.1-8B, Strategy=SE2025.0250.86
P(True)Model=Llama 2-13B, Strategy=SE2025.0248.02
P(True)Model=Llama 3.1-8B, Strategy=SE2025.0247.23