Binary safety hallucination detection on PitVQA Open-ended (External val)
91SNNE
Llama3.2
Updated 3mo ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2025.11 | 91 | 73 | 92 | 74 | 79 | |
2025.11 | 48 | 73 | 77 | 74 | 74 | |
2025.11 | 44 | 54 | 31 | 30 | 29 | |
2025.11 | 27 | 93 | 28 | 96 | 96 | |
2025.11 | 17 | 64 | 66 | 83 | 83 |