Truthful Question Answering on TruthfulQA f_con o=5
100Acc (Exact)
W/O Decontamination
Updated 1mo ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.01 | 100 | 44.5 | 98.1 | 45 | 92.8 | 35.6 | |
2026.01 | 100 | 44.5 | 98.1 | 45 | 92.8 | 35.6 | |
2026.01 | 99.5 | 70.8 | 100 | 75.1 | 88.5 | 61.6 | |
2026.01 | 99.5 | 70.8 | 100 | 75.1 | 88.5 | 61.6 | |
2026.01 | 99.5 | 52.2 | 99 | 52.4 | 92.3 | 47.1 | |
2026.01 | 91.9 | 63.2 | 91.4 | 66.5 | 73.6 | 46.7 | |
2026.01 | 90.9 | 43.5 | 92.8 | 46.2 | 87 | 41.8 | |
2026.01 | 86.6 | 39.2 | 86.6 | 39.9 | 87 | 41.8 | |
2026.01 | 85.2 | 37.8 | 85.6 | 39 | 72.6 | 27.4 | |
2026.01 | 79 | 23.5 | 79.9 | 26.8 | 71.8 | 14.6 | |
2026.01 | 66 | 18.7 | 56.2 | 9.6 | 57.2 | 12 | |
2026.01 | 65 | 9.5 | 63.6 | 10.5 | 67.7 | 10.5 | |
2026.01 | 62.1 | 33.4 | 60.1 | 35.2 | 64 | 37.1 | |
2026.01 | 59.5 | 30.8 | 55.1 | 30.2 | 57 | 30.1 | |
2026.01 | 58.9 | 11.5 | 62.2 | 15.5 | 60.6 | 15.4 | |
2026.01 | 51.7 | 3.8 | 50.7 | 2.4 | 44.2 | 13 | |
2026.01 | 19.1 | 36.4 | 63.2 | 10.1 | 78.8 | 21.6 | |
2026.01 | 8.6 | 20.1 | 24.4 | 0.5 | 71.2 | 44.3 |