Medical Question Answering on CV-MedExQA ambiguous (test)
73.09AccuracyAU-Probe
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| AU-ProbeModel=Qwen2.5-7B, Clarification Threshold=0.52026.01 | 73.09 | 8.94 | |
| AU-ProbeModel=Bio-Medical-Llama-3-8B, Clarification Threshold=0.52026.01 | 69.57 | 10.32 | |
| AU-ProbeModel=Llama-3.1-8B, Clarification Threshold=0.52026.01 | 68.3 | 7.55 | |
| ASK4CONFModel=Qwen2.5-7B, Clarification Threshold=0.52026.01 | 65.85 | — | |
| ASK4CONFModel=Bio-Medical-Llama-3-8B, Clarification Threshold=0.52026.01 | 65.21 | — | |
| No ClarificationModel=Qwen2.5-7B, Clarification Threshold=N/A2026.01 | 64.15 | — | |
| ASK4CONFModel=Llama-3.1-8B, Clarification Threshold=0.52026.01 | 61.7 | — | |
| No ClarificationModel=Llama-3.1-8B, Clarification Threshold=N/A2026.01 | 60.74 | — | |
| No ClarificationModel=Bio-Medical-Llama-3-8B, Clarification Threshold=N/A2026.01 | 59.26 | — | |
| AU-ProbeModel=BioMistral-7B, Clarification Threshold=0.52026.01 | 57.87 | 11.91 | |
| ASK4CONFModel=BioMistral-7B, Clarification Threshold=0.52026.01 | 52.77 | — | |
| No ClarificationModel=BioMistral-7B, Clarification Threshold=N/A2026.01 | 45.96 | — |