Hallucination Detection on MIMIC-CXR
94.26PR-AUCVASE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| VASEModel Type=Medical-tuned, Base Model=LLaVA-Med2026.06 | 94.26 | 59.34 | |
| CoEVModel Type=Medical-tuned, Base Model=LLaVA-Med2026.06 | 93.94 | 61.97 | |
| SEModel Type=Medical-tuned, Base Model=LLaVA-Med2026.06 | 92.76 | 54.94 | |
| RadFlagModel Type=Medical-tuned, Base Model=LLaVA-Med2026.06 | 91.53 | 53.13 | |
| VASEModel Type=Medical-tuned, Base Model=Lingshu-7B2026.06 | 87.59 | 61.87 | |
| CoEVModel Type=Medical-tuned, Base Model=Lingshu-7B2026.06 | 87.1 | 63.67 | |
| SEModel Type=Medical-tuned, Base Model=Lingshu-7B2026.06 | 84.73 | 59.48 | |
| RadFlagModel Type=Medical-tuned, Base Model=Lingshu-7B2026.06 | 83.29 | 55.31 | |
| CoEVModel Type=General-purpose, Base Model=InternVL3-2B2026.06 | 82.35 | 56.75 | |
| VASEModel Type=General-purpose, Base Model=InternVL3-2B2026.06 | 81.66 | 54.43 | |
| CoEVModel Type=General-purpose, Base Model=Qwen2-3B2026.06 | 79.2 | 60.04 | |
| SEModel Type=General-purpose, Base Model=Qwen2-3B2026.06 | 78.74 | 58.96 | |
| SEModel Type=General-purpose, Base Model=InternVL3-2B2026.06 | 76.96 | 52.54 | |
| VASEModel Type=General-purpose, Base Model=Qwen2-3B2026.06 | 75.18 | 52.19 | |
| RadFlagModel Type=General-purpose, Base Model=Qwen2-3B2026.06 | 73.41 | 56.68 | |
| RadFlagModel Type=General-purpose, Base Model=InternVL3-2B2026.06 | 70.61 | 54.02 |