Reasoning Factuality on FELM
99.19CoverageCF
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| CFalpha=0.012026.04 | 99.19 | 11.1 | — | — | |
| DCFalpha=0.012026.04 | 99.15 | 17.9 | 61.3 | — | |
| CFalpha=0.022026.04 | 98.08 | 22.4 | — | — | |
| DCFalpha=0.022026.04 | 97.75 | 35.7 | 59.4 | — | |
| DCFalpha=0.032026.04 | 97.32 | 36.4 | 23.4 | — | |
| CFalpha=0.032026.04 | 97.11 | 29.5 | — | — | |
| DCFalpha=0.042026.04 | 96.47 | 42 | 16 | — | |
| CFalpha=0.042026.04 | 95.89 | 36.2 | — | — | |
| DCFalpha=0.052026.04 | 95.35 | 46.3 | 11.6 | — | |
| CFalpha=0.052026.04 | 95.1 | 41.5 | — | — | |
| DCFalpha=0.062026.04 | 94.92 | 48.1 | -2.2 | — | |
| DCFalpha=0.072026.04 | 94.21 | 49.6 | -9.8 | — | |
| CFalpha=0.062026.04 | 93.94 | 49.2 | — | — | |
| DCFalpha=0.082026.04 | 93.64 | 52.7 | -14 | — | |
| CFalpha=0.072026.04 | 93.13 | 55 | — | — | |
| CFalpha=0.082026.04 | 92.15 | 61.3 | — | — | |
| DCFalpha=0.092026.04 | 91.39 | 69 | 3.9 | — | |
| CFalpha=0.092026.04 | 90.8 | 66.4 | — | — | |
| DCFalpha=0.102026.04 | 90.54 | 71.2 | 3.3 | — | |
| CFalpha=0.102026.04 | 90.08 | 68.9 | — | — |