Math Word Problems on GSM8K
53Comparable SC RateP(True)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| P(True)Confidence Method=P(True), Budget=102025.02 | 53 | 60 | |
| P(True)Confidence Method=P(True), Budget=52025.02 | 43 | 90 | |
| Response ProbabilityConfidence Method=Response Probability, Budget=102025.02 | 33 | 50 | |
| Verbal 1-100Confidence Method=Verbal 1-100, Budget=102025.02 | 32 | 10 | |
| Verbal 1-100Confidence Method=Verbal 1-100, Budget=52025.02 | 22 | 30 | |
| Response ProbabilityConfidence Method=Response Probability, Budget=52025.02 | 21 | 70 | |
| Verbal BinaryConfidence Method=Verbal Binary, Budget=52025.02 | 18 | 20 | |
| Verbal BinaryConfidence Method=Verbal Binary, Budget=102025.02 | 7 | 10 |