First-error detection on TruthfulQA
96.8Accuracy
Student
Updated 20d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.05 | 96.8 | |
2026.05 | 93.2 | |
2026.05 | 89.3 | |
2026.05 | 78.2 | |
2026.05 | 68.5 | |
2026.05 | 50 |
Student
| Method | Links | |
|---|---|---|
2026.05 | 96.8 | |
2026.05 | 93.2 | |
2026.05 | 89.3 | |
2026.05 | 78.2 | |
2026.05 | 68.5 | |
2026.05 | 50 |