Hallucination Detection on BEGIN Out-of-Distribution
54.3Macro F1GPT-4 (Internal)
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4 (Internal)Training Data=OpenDialKG2024.07 | 54.3 | |
| HaluGenTraining Data=OpenDialKG2024.07 | 51.8 | |
| Random baselineTraining Data=OpenDialKG2024.07 | 45.5 |