Multi-hop Question Answering on Average (MuSiQue, 2WikiMQA, HotpotQA)
43.3EM
Graph + LLM
Updated 8d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2024.10 | 43.3 | 56.9 | - | - | - | - | |
2024.10 | 41.3 | 54.8 | - | - | - | - | |
2024.10 | 40.3 | 54.6 | - | - | - | - | |
2024.10 | 39.4 | 53.6 | - | - | - | - | |
2024.10 | 39 | 49.1 | - | - | - | - | |
2024.10 | 38.4 | 51.3 | - | - | - | - | |
2026.05 | 37.1 | - | - | 44.2 | 51.3 | 15.8 | |
2024.10 | 36.7 | 48.5 | - | - | - | - | |
2024.10 | 36.3 | 50.5 | - | - | - | - | |
2024.10 | 35.4 | 49 | - | - | - | - | |
2026.05 | 35.4 | - | - | 39.1 | 41.5 | 26.7 | |
2024.10 | 34.7 | 45.9 | - | - | - | - | |
2026.05 | 34.6 | - | - | 37.8 | 40.5 | 25.5 | |
2026.05 | 33.6 | - | - | 38.2 | 47.8 | 14.9 | |
2026.05 | 33.4 | - | - | 36.6 | 39 | 24.6 | |
2026.05 | 31 | - | - | 37 | 41.4 | 14.6 | |
2024.10 | 30.8 | 42.5 | - | - | - | - | |
2024.10 | 30.3 | 41.5 | - | - | - | - | |
2026.05 | 29.8 | - | - | 38.6 | 34.6 | 16.2 | |
2026.05 | 29.8 | - | - | 38.6 | 34.6 | 16.2 | |
2026.05 | 28.2 | - | - | 34.8 | 36.3 | 13.4 | |
2024.10 | 28.1 | 40.2 | - | - | - | - | |
2024.10 | 23.8 | 36.5 | - | - | - | - | |
2026.05 | 19.7 | - | - | 29.9 | 23.5 | 5.8 | |
2024.10 | 19.3 | 33.3 | - | - | - | - | |
2026.05 | 18.1 | - | - | 21.7 | 25.9 | 6.6 | |
2026.05 | 11.8 | - | - | 13.3 | 14.9 | 7.2 | |
2026.03 | - | 12.97 | 23.88 | - | - | - | |
2026.03 | - | 14.51 | 23.35 | - | - | - | |
2026.03 | - | 53.51 | 56.71 | - | - | - | |
2026.03 | - | 24.15 | 30.16 | - | - | - | |
2026.03 | - | 44.7 | 46.97 | - | - | - | |
2026.03 | - | 50.73 | 52.94 | - | - | - | |
2026.03 | - | 25.56 | 27.17 | - | - | - | |
2026.03 | - | 47.74 | 49.92 | - | - | - | |
2026.03 | - | 60.5 | 64.4 | - | - | - | |
2026.03 | - | 43.29 | 48.65 | - | - | - | |
2026.03 | - | 63.02 | 66.63 | - | - | - |