Test-Time Personalization on Truthful QA
99.6Creative Win Rate
T-POP
Updated 1d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2025.09 | 99.6 | 95.4 | 72.3 | 96.5 | |
2025.09 | 99.5 | 93.2 | 85.5 | 92.8 | |
2025.09 | 98.5 | 96 | 79 | 99.1 | |
2025.09 | 97.3 | 95.4 | 68.8 | 93.5 | |
2025.09 | 97.2 | 96.5 | 74.7 | 95.3 | |
2025.09 | 94.5 | 90.1 | 70.3 | 91.9 | |
2025.09 | 94.1 | 87.3 | 71.9 | 82.7 | |
2025.09 | 93.3 | 78.7 | 70.8 | 88.2 | |
2025.09 | 92.3 | 86.7 | 76.9 | 82.6 | |
2025.09 | 90.1 | 78.2 | 88.9 | 81.9 | |
2025.09 | 88.2 | 84.3 | 92.2 | 80.8 | |
2025.09 | 85.4 | 79.1 | 77.4 | 85.8 | |
2025.09 | 85.4 | 79.5 | 90.1 | 81.2 | |
2025.09 | 83.9 | 78.9 | 91.2 | 93 | |
2025.09 | 83 | 77.5 | 80.5 | 82.9 |