Hallucination Detection on DualityVidQA (test)
76.8Pairwise AccuracyDNA-Train-7B
Evaluation Results
| Method | Links | |
|---|---|---|
| DNA-Train-7B2025.12 | 76.8 | |
| GPT-4o2025.12 | 65.8 | |
| Qwen2.5-VL-7B2025.12 | 52.8 | |
| Video-LLaVA-7B2025.12 | 17.7 | |
| LLaVA-Next-Video2025.12 | 16.9 | |
| VideoChat2-HD2025.12 | 0.7 |