Correctness Assessment on UltraFeedback Property Constraints Satisfaction (test)
0.07Worst-case Size Distortion (Helpfulness & Instruction-following)naive (1)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| naive (1)Score=naive (1)2025.10 | 0.07 | 0.09 | |
| e-score (2)Score=e-score (2)2025.10 | 0.8 | 0.97 | |
| e-score (combined)Score=e-score (combined)2025.10 | 0.94 | 1.01 | |
| e-score (1)Score=e-score (1)2025.10 | 1 | 1 | |
| e-score (3)Score=e-score (3)2025.10 | 1 | 1.05 | |
| naive (3)Score=naive (3)2025.10 | 1.8 | 4.82 | |
| naive (2)Score=naive (2)2025.10 | 2.25 | 5.42 | |
| p-scoreScore=p-score2025.10 | 9.6 | 7.55 | |
| p-score (randomized)Score=p-score (randomized)2025.10 | 15.91 | 14.92 |