Truthfulness Evaluation on TruthfulQA (Adversarial Robustness)
100Accuracy under Attack
Reporting-and-penalty mechanism
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| 100 | 100 | ||
2026.04 | 70 | 92 |
Reporting-and-penalty mechanism
| Method | Links | ||
|---|---|---|---|
| 100 | 100 | ||
2026.04 | 70 | 92 |