Question Answering on SQuAD 2.0 (Factual Accuracy & Relevance)
1.66Factual Accuracy
EmbGen
Updated 14d ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.05 | 1.66 | 2.06 | 2.84 | 2.99 | 28.8 | |
2026.05 | 1.65 | 2.14 | 2.9 | 2.98 | 28 | |
2026.05 | 1.65 | 2.09 | 2.94 | 3 | 28 | |
2026.05 | 1.6 | 2.06 | 2.88 | 3 | 23.2 | |
2026.05 | 1.4 | 2.02 | 2.68 | 2.98 | 6.4 | |
2026.05 | 1.39 | 1.97 | 2.56 | 2.98 | 3.6 | |
2026.05 | 1.37 | 2.04 | 2.24 | 2.91 | 4 | |
2026.05 | 1.29 | 1.95 | 2.35 | 2.9 | 3.6 | |
2026.05 | 1.28 | 1.99 | 2.3 | 2.89 | 0.8 | |
2026.05 | 1.28 | 1.99 | 2.3 | 2.89 | 0.8 |