Factual Answering on TruthfulQA (Truth, URR)
62.6Truthfulness Score
DualEdit
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.04 | 62.6 | 86.2 | |
2026.04 | 62.4 | 100 | |
2026.04 | 62.3 | 97.7 | |
2026.04 | 62.2 | 97.2 | |
2026.04 | 58.8 | 92.2 | |
2026.04 | 56.6 | 69.3 | |
2026.04 | 52.2 | 100 | |
2026.04 | 52.2 | 98.6 | |
2026.04 | 52.1 | 95.7 | |
2026.04 | 49.3 | 85.9 | |
2026.04 | 49 | 81.2 | |
2026.04 | 48 | 70.1 | |
2026.04 | 47.6 | 100 | |
2026.04 | 47.6 | 95.7 | |
2026.04 | 47.5 | 97 | |
2026.04 | 47.2 | 90.9 | |
2026.04 | 46.9 | 86.7 | |
2026.04 | 45.1 | 70.7 |