Multi-Hop Question Answering on LoCoMo Multi-Hop (test)
26.55F1 Score
Reproduced Baselines
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.02 | 26.55 | 17.99 | 0 | |
2026.02 | 25.95 | 18.25 | -7.2 | |
2026.02 | 25.32 | 18.89 | 0 | |
2026.02 | 24.48 | 18.83 | -6.1 | |
2026.02 | 22.29 | 12.83 | 0 | |
2026.02 | 19.8 | 14.67 | 0 | |
2026.02 | 19.51 | 13.6 | 0 | |
2026.02 | 19.5 | 13.1 | 0 | |
2026.02 | 19.34 | 14.16 | -13.1 | |
2026.02 | 19.1 | 12.02 | -13.4 | |
2026.02 | 18.46 | 12.81 | -7.1 | |
2026.02 | 18.33 | 13.75 | -4.2 | |
2026.02 | 15.28 | 11.71 | -48.4 | |
2026.02 | 13.5 | 10.46 | -55.5 | |
2026.02 | 12.59 | 11.68 | -48.4 | |
2026.02 | 11.25 | 10.26 | -46.8 | |
2026.02 | 11.17 | 10.24 | -40.2 | |
2026.02 | 10.95 | 10.07 | -44.1 | |
2026.02 | 10.85 | 10.16 | -53.6 | |
2026.02 | 10.62 | 7.14 | -46.5 | |
2026.02 | 10.47 | 9.02 | -51.6 | |
2026.02 | 10.22 | 9.39 | -53 | |
2026.02 | 8.88 | 7.91 | -56.7 | |
2026.02 | 7.28 | 5.56 | -61.6 |