Knowledge Conflict Resolution on KID-Bench v2
97.6Performance (Difficulty A)
RAG
Updated 1mo ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.04 | 97.6 | 74 | 71.9 | 65.6 | 63.8 | |
2026.04 | 97.1 | 64 | 78.1 | 83.6 | 71 | |
2026.04 | 96.7 | 68 | 57.8 | 55.7 | 46.4 | |
2026.04 | 95.5 | 68 | 75 | 73.8 | 60.9 |
RAG
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.04 | 97.6 | 74 | 71.9 | 65.6 | 63.8 | |
2026.04 | 97.1 | 64 | 78.1 | 83.6 | 71 | |
2026.04 | 96.7 | 68 | 57.8 | 55.7 | 46.4 | |
2026.04 | 95.5 | 68 | 75 | 73.8 | 60.9 |