Hallucination assessment on Object-HalBench
2.6Mention Hallucination Rate
OmniLMM + RLAIF-V BoN
Updated 3d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2024.05 | 2.6 | 4.5 | - | - | |
2024.05 | 2.9 | 4.5 | - | - | |
2024.05 | 3.8 | 6.8 | - | - | |
2024.08 | 5 | - | - | 10.3 | |
2024.05 | 5.2 | 10.5 | - | - | |
2024.05 | 6.4 | 12.6 | - | - | |
2024.08 | 6.5 | - | - | 11.4 | |
2024.08 | 7.3 | - | - | 13.6 | |
2024.05 | 7.3 | 13.6 | - | - | |
2023.12 | 7.3 | - | - | 13.6 | |
2024.05 | 7.5 | 12.2 | - | - | |
2023.12 | 7.5 | - | - | 12.2 | |
2024.08 | 7.8 | - | - | 14.5 | |
2024.05 | 8 | 14.5 | - | - | |
2024.08 | 9.6 | - | - | 16.7 | |
2024.05 | 10.9 | 19.4 | - | - | |
2024.08 | 11.5 | - | - | 21.6 | |
2024.08 | 11.7 | - | - | 19.4 | |
2024.08 | 12.6 | - | - | 26.4 | |
2024.05 | 13.4 | 27.1 | - | - | |
2024.08 | 14 | - | - | 20.7 | |
2023.12 | 14.3 | - | - | 25.9 | |
2024.05 | 17.8 | 40.3 | - | - | |
2024.05 | 18.9 | 38.1 | - | - | |
2023.12 | 18.9 | - | - | 38.1 | |
2024.05 | 19.9 | 39.9 | - | - | |
2024.08 | 20 | - | - | 43.8 | |
2023.12 | 20 | - | - | 43.8 | |
2024.05 | 20.6 | 31.7 | - | - | |
2024.05 | 20.7 | 40.4 | - | - | |
2024.05 | 22.3 | 45.1 | - | - | |
2023.12 | 22.3 | - | - | 32.3 | |
2023.12 | 22.6 | - | - | 46.3 | |
2024.05 | 23.8 | 46.7 | - | - | |
2024.05 | 24.3 | 48.8 | - | - | |
2024.05 | 24.4 | 48.1 | - | - | |
2023.12 | 24.5 | - | - | 50.5 | |
2024.05 | 27.8 | 54.5 | - | - | |
2023.12 | 29.5 | - | - | 63 | |
2024.03 | - | 63 | 29.5 | - | |
2024.03 | - | 45.9 | 23.7 | - | |
2024.03 | - | 45.2 | 21.8 | - | |
2024.03 | - | 31.9 | 15.1 | - | |
2024.03 | - | 27.3 | 12.9 | - |