Math Word Problem Reasoning on ASDiv (AUROC)
0.6818AUROCTOKENSAR + CoT-UQ
Evaluation Results
| Method | Links | |
|---|---|---|
| TOKENSAR + CoT-UQStrategy=AP, Backbone=Mistral 7B2025.02 | 0.6818 | |
| Probas-mean + CoT-UQStrategy=AP, Backbone=Mistral 7B2025.02 | 0.674 | |
| TOKENSARStrategy=AP, Backbone=Mistral 7B2025.02 | 0.5843 | |
| Probas-meanStrategy=AP, Backbone=Mistral 7B2025.02 | 0.5726 | |
| P(True) + CoT-UQStrategy=SE, Backbone=Mistral 7B2025.02 | 0.513 | |
| P(True)Strategy=SE, Backbone=Mistral 7B2025.02 | 0.4844 |