Factuality Verification on Climate-Fever
78.91Correctness ScoreBERTScore
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| BERTScore2026.05 | 78.91 | 77.74 | 1.17 | — | |
| MAUVE2026.05 | 70.95 | 51.99 | 18.96 | — | |
| SimCSErescaled to [0, 1]=true2026.05 | 65.63 | 51.82 | 6.91 | — | |
| EmbSimrescaled to [0, 1]=true2026.05 | 60.56 | 55.74 | 2.41 | — | |
| MATCHArescaled to [0, 1]=true2026.05 | 52.92 | 12.57 | 20.18 | — | |
| R1-F12026.05 | 26.78 | 23.05 | 3.73 | — | |
| RL-F12026.05 | 19.62 | 18.12 | 1.5 | — | |
| METEOR2026.05 | 19.01 | 15.33 | 3.68 | — | |
| R2-F12026.05 | 7.55 | 5.67 | 1.88 | — | |
| BLEURTrescaled to [0, 1]=true2026.05 | -41.65 | -53.76 | 6.06 | — | |
| BERTScoreThreshold=fixed midpoint threshold2026.05 | — | — | — | 33.33 | |
| BLEURTThreshold=fixed midpoint threshold2026.05 | — | — | — | 40.23 | |
| EmbSimThreshold=fixed midpoint threshold2026.05 | — | — | — | 33.33 | |
| MATCHAThreshold=fixed midpoint threshold2026.05 | — | — | — | 64.08 | |
| METEORThreshold=fixed midpoint threshold2026.05 | — | — | — | 36.93 | |
| R1-F1Threshold=fixed midpoint threshold2026.05 | — | — | — | 37.11 | |
| R2-F1Threshold=fixed midpoint threshold2026.05 | — | — | — | 34.07 | |
| RL-F1Threshold=fixed midpoint threshold2026.05 | — | — | — | 34.48 | |
| SimCSEThreshold=fixed midpoint threshold2026.05 | — | — | — | 33.33 |