Knowledge Retrieval on DailyDialog
84.29BERTScore Precision (avg)
MCTS-Driven Knowledge Retrieval
Updated 4d ago
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 84.29 | 85.05 | 84.65 | 89.1 | 89.43 | 88.9 | -4.19 | -2.85 | 80.32 | 83.78 | ||
| 84.29 | 85.05 | 84.65 | 89.1 | 89.43 | 88.9 | -4.19 | -2.85 | 80.32 | 83.78 | ||
| 84.23 | 85.04 | 84.62 | 88.19 | 88.91 | 88.31 | -4.02 | -2.98 | 80.15 | 83.06 | ||
| 84.23 | 85.04 | 84.62 | 88.19 | 88.91 | 88.31 | -4.02 | -2.98 | 80.15 | 83.06 | ||
2025.11 | 84.22 | 84.1 | 84.19 | 86.23 | 86.48 | 86.19 | -4.03 | -3.21 | 80.29 | 82.54 | |
2025.11 | 84.22 | 84.1 | 84.19 | 86.23 | 86.48 | 86.19 | -4.03 | -3.21 | 80.29 | 82.54 | |
2025.11 | 84.07 | 84.5 | 84.13 | 86.07 | 86.5 | 86.13 | -4.09 | -3.2 | 80.26 | 82.53 | |
2025.11 | 84.07 | 84.5 | 84.13 | 86.07 | 86.5 | 86.13 | -4.09 | -3.2 | 80.26 | 82.53 | |
2025.11 | 83.62 | 84.72 | 84.15 | 84.51 | 86.25 | 85.22 | -4.39 | -3.64 | 80.06 | 81.74 | |
2025.11 | 83.62 | 84.72 | 84.15 | 84.51 | 86.25 | 85.22 | -4.39 | -3.64 | 80.06 | 81.74 | |
2025.11 | 83.38 | 84.07 | 83.71 | 85.74 | 86.81 | 86.11 | -4.15 | -3.28 | 80.24 | 81.98 | |
2025.11 | 83.38 | 84.07 | 83.71 | 85.74 | 86.81 | 86.11 | -4.15 | -3.28 | 80.24 | 81.98 | |
| 80.76 | 84.79 | 82.73 | 81.92 | 85.63 | 83.57 | -4.63 | -4.27 | 77.23 | 78.08 | ||
| 80.76 | 84.79 | 82.73 | 81.92 | 85.63 | 83.57 | -4.63 | -4.27 | 77.23 | 78.08 | ||
2025.11 | 80.25 | 80.77 | 80.5 | 82.1 | 82.64 | 82.16 | -4.94 | -3.73 | 76.91 | 79.62 | |
2025.11 | 80.25 | 80.77 | 80.5 | 82.1 | 82.64 | 82.16 | -4.94 | -3.73 | 76.91 | 79.62 |