Hallucination Detection on IU-Xray
0.8992PR AUCVASE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| VASEModel Type=General-purpose, Base Model=Qwen2-3B2026.06 | 0.8992 | 0.6809 | |
| SEModel Type=General-purpose, Base Model=Qwen2-3B2026.06 | 0.892 | 0.6263 | |
| CoEVModel Type=General-purpose, Base Model=Qwen2-3B2026.06 | 0.8918 | 0.6461 | |
| RadFlagModel Type=General-purpose, Base Model=Qwen2-3B2026.06 | 0.8756 | 0.6282 | |
| CoEVModel Type=General-purpose, Base Model=InternVL3-2B2026.06 | 0.8021 | 0.6189 | |
| VASEModel Type=General-purpose, Base Model=InternVL3-2B2026.06 | 0.8 | 0.6176 | |
| CoEVModel Type=Medical-tuned, Base Model=Lingshu-7B2026.06 | 0.799 | 0.4969 | |
| SEModel Type=General-purpose, Base Model=InternVL3-2B2026.06 | 0.7862 | 0.5937 | |
| VASEModel Type=Medical-tuned, Base Model=Lingshu-7B2026.06 | 0.7789 | 0.4966 | |
| SEModel Type=Medical-tuned, Base Model=Lingshu-7B2026.06 | 0.7753 | 0.4468 | |
| RadFlagModel Type=General-purpose, Base Model=InternVL3-2B2026.06 | 0.7702 | 0.5797 | |
| CoEVModel Type=Medical-tuned, Base Model=LLaVA-Med2026.06 | 0.7617 | 0.5995 | |
| VASEModel Type=Medical-tuned, Base Model=LLaVA-Med2026.06 | 0.7594 | 0.565 | |
| RadFlagModel Type=Medical-tuned, Base Model=Lingshu-7B2026.06 | 0.7267 | 0.4021 | |
| RadFlagModel Type=Medical-tuned, Base Model=LLaVA-Med2026.06 | 0.7061 | 0.5402 | |
| SEModel Type=Medical-tuned, Base Model=LLaVA-Med2026.06 | 0.667 | 0.5254 |