Hallucination Detection on Movies (test)
94.15AuROCMarginal Em
Evaluation Results
| Method | Links | |
|---|---|---|
| Marginal EmModel=Gemma-Instruct 1B, Pool=Max2026.02 | 94.15 | |
| Spilled ΔEModel=Gemma-Instruct 4B, Pool=Min2026.02 | 86.13 | |
| Marginal EmModel=Gemma-Instruct 4B, Pool=Max2026.02 | 83.02 | |
| Spilled ΔEModel=Gemma-Instruct 1B, Pool=Min2026.02 | 82.82 | |
| Logit EℓModel=Gemma-Instruct 4B, Pool=Max2026.02 | 60.88 | |
| Marginal EmModel=Gemma-Instruct 4B, Pool=Min2026.02 | 51.29 | |
| Spilled ΔEsModel=Gemma-Instruct 4B, Pool=Max2026.02 | 50.77 | |
| Logit EℓModel=Gemma-Instruct 1B, Pool=Max2026.02 | 48.12 | |
| Spilled ΔEsModel=Gemma-Instruct 1B, Pool=Max2026.02 | 33.27 | |
| Marginal EmModel=Gemma-Instruct 1B, Pool=Min2026.02 | 28.93 |