Multi-hop Question Answering on 2WikiMultiHopQA (dev)
88.658Exact Match Accuracy
Dense-aware HKVM controller
Updated 25d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 88.658 | 88.846 | 100 | |
2026.06 | 88.205 | 88.415 | 100 | |
2026.06 | 88.181 | 88.391 | 99.03 | |
2026.06 | 77.195 | 77.763 | 100 | |
2026.06 | 77.107 | 77.679 | 100 | |
2023.04 | 68.6 | - | - | |
2023.04 | 67.9 | - | - | |
2026.06 | 67.19 | - | - | |
2026.06 | 66.81 | - | - | |
2023.04 | 65.2 | - | - | |
2026.06 | 65.2 | 69.38 | - | |
2023.04 | 63.8 | - | - | |
2026.06 | 63.69 | - | - | |
2026.06 | 63.4 | 67.95 | - | |
2026.06 | 63.25 | - | - | |
2026.06 | 62 | 67.19 | - | |
2026.06 | 62 | 65.32 | - | |
2026.06 | 61.4 | 67.06 | - | |
2026.06 | 61 | 66.06 | - | |
2026.06 | 59.6 | 63.67 | - | |
2026.06 | 59.4 | 65.77 | - | |
2026.06 | 58.2 | 62.17 | - | |
2026.06 | 57.8 | 61.48 | - | |
2026.06 | 53.8 | 57.88 | - | |
2023.04 | 52.6 | - | - | |
2026.06 | 51.6 | 58.15 | - | |
2026.06 | 50 | 55 | - | |
2026.06 | 49.6 | 54.63 | - | |
2026.06 | 47.8 | 53.95 | - | |
2022.10 | 40.1 | - | - | |
2022.10 | 30 | - | - | |
2022.10 | 29.8 | - | - | |
2022.10 | 26.3 | - | - | |
2026.06 | 26 | 32.54 | - | |
2022.10 | 25.4 | - | - | |
2022.10 | 2.2 | - | - |