Knowledge Conflict Resolution on KID-Bench Category C v2
78.1Accuracy (C-Light)
Conflict-Aware
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 78.1 | 83.6 | 71 | |
2026.04 | 75 | 73.8 | 60.9 | |
2026.04 | 57.8 | 55.7 | 46.4 |
Conflict-Aware
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 78.1 | 83.6 | 71 | |
2026.04 | 75 | 73.8 | 60.9 | |
2026.04 | 57.8 | 55.7 | 46.4 |