Collusion Detection on NARCBENCH OOD Mean
86AUROCAsymmetry Probe
Evaluation Results
| Method | Links | |
|---|---|---|
| Asymmetry ProbeTraining Split=CORE, Layers=26–30, Evaluation Protocol=Zero-shot2026.04 | 86 | |
| Peak SuspicionTraining Split=CORE, Layers=26–30, Evaluation Protocol=Zero-shot2026.04 | 84 | |
| Deception SplitTraining Split=CORE, Layers=26–30, Evaluation Protocol=Zero-shot2026.04 | 81 | |
| Sorted ConcatenationTraining Split=CORE, Layers=26–30, Evaluation Protocol=Zero-shot2026.04 | 69 | |
| Activation AlignmentTraining Split=CORE, Layers=26–30, Evaluation Protocol=Zero-shot2026.04 | 60 |