Selective Risk Control on GSM8K
0RiskCoFact
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| CoFactalpha=0.052026.05 | 0 | 0 | 0 | |
| Conf-Arbitragealpha=0.052026.05 | 0.3 | 9 | 0 | |
| CSAalpha=0.052026.05 | 2.6 | 71.7 | 0 |
Loading the SOTA2 catalog…
| Method | Links | |||
|---|---|---|---|---|
| CoFactalpha=0.052026.05 | 0 | 0 | 0 | |
| Conf-Arbitragealpha=0.052026.05 | 0.3 | 9 | 0 | |
| CSAalpha=0.052026.05 | 2.6 | 71.7 | 0 |