List your company
ResearchFormerly WizWand

Safety Evaluation on O2M Harmful Clinical Queries

13.43ASRH-R Demon
10.971227.568144.16560.7619Jun 8, 2025
Updated 6mo ago

Evaluation results

MethodLinks
H-R DemonModel=Llava-Med-v1, Demonstration budget (n)=42025.0613.43
H-R DemonModel=Llava-Med-v1, Demonstration budget (n)=22025.0617.88
H-R DemonModel=Llava-Med-v1, Demonstration budget (n)=82025.0621.31
H-R DemonModel=Llava-Med-v1, Demonstration budget (n)=162025.0632.63
H-R DemonModel=Llava-Med-v1.5, Demonstration budget (n)=42025.0642.61
H-R DemonModel=Llava-Med-v1.5, Demonstration budget (n)=22025.0644.75
H-R DemonModel=Llava-Med-v1.5, Demonstration budget (n)=82025.0645.1
H-R DemonModel=Llava-Med-v1.5, Demonstration budget (n)=162025.0647.32
B-A DemonModel=Llava-Med-v1.5, Demonstration budget (n)=22025.0656.82
B-A DemonModel=Llava-Med-v1.5, Demonstration budget (n)=162025.0656.92
B-A DemonModel=Llava-Med-v1.5, Demonstration budget (n)=42025.0657.53
B-A DemonModel=Llava-Med-v1.5, Demonstration budget (n)=82025.0657.68
B-A DemonModel=Llava-Med-v1, Demonstration budget (n)=162025.0660.76
Baseline (No Demon)Model=Llava-Med-v1.5, Demonstration budget (n)=02025.0661.52
B-A DemonModel=Llava-Med-v1, Demonstration budget (n)=82025.0665.05
B-A DemonModel=Llava-Med-v1, Demonstration budget (n)=42025.0668.79
Baseline (No Demon)Model=Llava-Med-v1, Demonstration budget (n)=02025.0672.58
B-A DemonModel=Llava-Med-v1, Demonstration budget (n)=22025.0674.9