Hallucination Detection on VQA-RAD
92.16PR-AUCCoEV
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CoEVModel Type=General-purpose, Base Model=Qwen2-3B2026.06 | 92.16 | 69.25 | |
| CoEVModel Type=Medical-tuned, Base Model=Lingshu-7B2026.06 | 89.73 | 65.63 | |
| VASEModel Type=General-purpose, Base Model=Qwen2-3B2026.06 | 89.71 | 61.81 | |
| RadFlagModel Type=Medical-tuned, Base Model=Lingshu-7B2026.06 | 87.71 | 52.39 | |
| VASEModel Type=Medical-tuned, Base Model=Lingshu-7B2026.06 | 87.45 | 58.78 | |
| CoEVModel Type=Medical-tuned, Base Model=LLaVA-Med2026.06 | 86.57 | 68.94 | |
| SEModel Type=General-purpose, Base Model=Qwen2-3B2026.06 | 86.16 | 70.15 | |
| RadFlagModel Type=General-purpose, Base Model=Qwen2-3B2026.06 | 82.99 | 74.37 | |
| SEModel Type=Medical-tuned, Base Model=Lingshu-7B2026.06 | 81.85 | 52.47 | |
| CoEVModel Type=General-purpose, Base Model=InternVL3-2B2026.06 | 72.35 | 67.45 | |
| RadFlagModel Type=Medical-tuned, Base Model=LLaVA-Med2026.06 | 71.86 | 61.12 | |
| VASEModel Type=General-purpose, Base Model=InternVL3-2B2026.06 | 68.48 | 58.11 | |
| SEModel Type=General-purpose, Base Model=InternVL3-2B2026.06 | 66.51 | 52.58 | |
| RadFlagModel Type=General-purpose, Base Model=InternVL3-2B2026.06 | 65.32 | 54.09 | |
| VASEModel Type=Medical-tuned, Base Model=LLaVA-Med2026.06 | 63.02 | 67.01 | |
| SEModel Type=Medical-tuned, Base Model=LLaVA-Med2026.06 | 63 | 64.34 |