Distribution Alignment on UK Dataset Even Setting (test)
0.05Alignment Error
Steering Token Calibration
Updated 11d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.04 | 0.05 | |
2026.04 | 0.061 | |
2026.04 | 0.085 | |
2026.04 | 0.101 | |
2026.04 | 0.12 | |
2026.04 | 0.134 | |
2026.04 | 0.154 | |
2026.04 | 0.189 | |
2026.04 | 0.5 | |
2026.04 | 0.5 | |
2026.04 | 0.5 | |
2026.04 | 0.5 |