Hallucination Detection on counterfact
0.84AUROCLatent Debate Detector
Evaluation results
| Method | Links | |
|---|---|---|
| Latent Debate Detector2025.12 | 0.84 | |
| SAPLMA2025.12 | 0.66 | |
| VarInit2025.12 | 0.56 | |
| SelfCheckGPT2025.12 | 0.53 | |
| AvgInit2025.12 | 0.52 | |
| VarFin2025.12 | 0.52 | |
| AvgFin2025.12 | 0.49 | |
| NumAtk2025.12 | 0.4 |