List your company

Sycophancy on Sycophancy dataset

75.5Behavioral Alignment Score (Baseline)System Prompt
68.84470.57272.374.028Aug 11, 2025

Evaluation results

MethodLinks
System PromptModel=Idefics22025.0875.574.475.9
Steering VectorModel=Idefics22025.0875.575.636.7
VISORModel=Idefics22025.0875.575.639.4
System PromptModel=LLaVA-1.52025.0869.167.967.4
Steering VectorModel=LLaVA-1.52025.0869.172.639.4
VISORModel=LLaVA-1.52025.0869.169.839.3