List your company

Medical Question Answering on CV-MedQA ambiguous (test)

0.7643AccuracyAU-Probe
0.3476760.4558380.5640.672162Jan 24, 2026

Evaluation results

MethodLinks
AU-ProbeModel=Bio-Medical-Llama-3-8B, Clarification Threshold=0.52026.010.764315.63
ASK4CONFModel=Bio-Medical-Llama-3-8B, Clarification Threshold=0.52026.010.6866—
No ClarificationModel=Bio-Medical-Llama-3-8B, Clarification Threshold=N/A2026.010.608—
AU-ProbeModel=Qwen2.5-7B, Clarification Threshold=0.52026.010.593910.84
AU-ProbeModel=Llama-3.1-8B, Clarification Threshold=0.52026.010.57199.03
ASK4CONFModel=Llama-3.1-8B, Clarification Threshold=0.52026.010.5232—
ASK4CONFModel=Qwen2.5-7B, Clarification Threshold=0.52026.010.5169—
No ClarificationModel=Qwen2.5-7B, Clarification Threshold=N/A2026.010.4855—
No ClarificationModel=Llama-3.1-8B, Clarification Threshold=N/A2026.010.4815—
AU-ProbeModel=BioMistral-7B, Clarification Threshold=0.52026.010.41164.79
ASK4CONFModel=BioMistral-7B, Clarification Threshold=0.52026.010.3841—
No ClarificationModel=BioMistral-7B, Clarification Threshold=N/A2026.010.3637—