Sycophancy Evaluation on TruthfulQA (adversarial)
1Sycophantic Response Count
Silicon Mirror
Updated 17d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.04 | 1 | 2 | 0.1 | 83.3 | |
2026.04 | 2 | 4 | 0.5 | 66.7 | |
2026.04 | 6 | 12 | 4.5 | - |
Silicon Mirror
| Method | Links | ||||
|---|---|---|---|---|---|
2026.04 | 1 | 2 | 0.1 | 83.3 | |
2026.04 | 2 | 4 | 0.5 | 66.7 | |
2026.04 | 6 | 12 | 4.5 | - |