List your company

Syllogistic Reasoning on Syllogistic Reasoning (test)

89.9AccuracyContrastive Steering (Qwen 2.5)
28.300844.292960.28576.2771May 18, 2025

Evaluation results

MethodLinks
Contrastive Steering (Qwen 2.5)Size=7b, Setting=Zero-shot, Steering=Steered Model (αbest), αbest=-1.52025.0589.90.9693.6577.17468.26
Contrastive Steering (Qwen 2.5)Size=7b, Setting=Few-shot, Steering=Steered Model (αbest), αbest=0.92025.0589.94.8118.79.194.79
Qwen 2.5Size=7b, Setting=Few-shot, Steering=Base Model (α = 0)2025.0589.89.369.6——
Qwen 2.5Size=7b, Setting=Zero-shot, Steering=Base Model (α = 0)2025.0588.855.3916.48——
Contrastive Steering (Qwen 2.5)Size=3b, Setting=Few-shot, Steering=Steered Model (αbest), αbest=0.62025.0586.634.818.0211.81190.18
Qwen 2.5Size=3b, Setting=Few-shot, Steering=Base Model (α = 0)2025.0586.4413.916.21——
Qwen 2.5Size=3b, Setting=Zero-shot, Steering=Base Model (α = 0)2025.0585.297.1211.99——
Contrastive Steering (Qwen 2.5)Size=3b, Setting=Zero-shot, Steering=Steered Model (αbest), αbest=0.02025.0585.297.1211.9900
Contrastive Steering (Llama 3.1)Size=8b, Setting=Zero-shot, Steering=Steered Model (αbest), αbest=0.92025.0585.114.046.063.52138.58
Gemma 2Size=9b, Setting=Zero-shot, Steering=Base Model (α = 0)2025.05858.4610.05——
Gemma 2Size=9b, Setting=Few-shot, Steering=Base Model (α = 0)2025.0584.6115.255.54——
Contrastive Steering (Gemma 2)Size=9b, Setting=Zero-shot, Steering=Steered Model (αbest), αbest=0.62025.0583.271.9243.3733.32331.54
Contrastive Steering (Gemma 2)Size=9b, Setting=Few-shot, Steering=Steered Model (αbest), αbest=0.32025.0580.383.3324.1418.6335.74
Llama 3.1Size=8b, Setting=Zero-shot, Steering=Base Model (α = 0)2025.0578.2730.772.54——
Contrastive Steering (Llama 3.2)Size=3b, Setting=Few-shot, Steering=Steered Model (αbest), αbest=0.32025.0578.2722.313.510.9235.52
Llama 3.2Size=3b, Setting=Zero-shot, Steering=Base Model (α = 0)2025.0577.7917.54.45——
Contrastive Steering (Llama 3.2)Size=3b, Setting=Zero-shot, Steering=Steered Model (αbest), αbest=0.02025.0577.7917.54.4500
Contrastive Steering (Qwen 2.5)Size=1.5b, Setting=Zero-shot, Steering=Steered Model (αbest), αbest=0.32025.0577.7912.886.040.7915.05
Qwen 2.5Size=1.5b, Setting=Zero-shot, Steering=Base Model (α = 0)2025.0575.6714.425.25——
Contrastive Steering (Gemma 2)Size=2b, Setting=Zero-shot, Steering=Steered Model (αbest), αbest=1.82025.0574.1320.833.561.357.52
Contrastive Steering (Llama 3.2)Size=1b, Setting=Zero-shot, Steering=Steered Model (αbest), αbest=-0.92025.0573.566.3511.5810.26777.27
Gemma 2Size=2b, Setting=Zero-shot, Steering=Base Model (α = 0)2025.0573.2732.432.26——
Llama 3.2Size=3b, Setting=Few-shot, Steering=Base Model (α = 0)2025.0572.7928.142.59——
Contrastive Steering (Qwen 2.5)Size=1.5b, Setting=Few-shot, Steering=Steered Model (αbest), αbest=-1.22025.0572.6932.182.261.46182.5
Contrastive Steering (Gemma 2)Size=2b, Setting=Few-shot, Steering=Steered Model (αbest), αbest=-0.32025.057012.315.690.8116.6
Gemma 2Size=2b, Setting=Few-shot, Steering=Base Model (α = 0)2025.0569.4214.234.88——
Contrastive Steering (Llama 3.2)Size=1b, Setting=Few-shot, Steering=Steered Model (αbest), αbest=-1.52025.0566.446.084.943.69295.2
Llama 3.2Size=1b, Setting=Zero-shot, Steering=Base Model (α = 0)2025.0558.1744.041.32——
Llama 3.2Size=1b, Setting=Few-shot, Steering=Base Model (α = 0)2025.0557.2145.71.25——
Qwen 2.5Size=1.5b, Setting=Few-shot, Steering=Base Model (α = 0)2025.0551.9265.120.8——
Llama 3.1Size=8b, Setting=Few-shot, Steering=Base Model (α = 0)2025.0540.5820.262——
Contrastive Steering (Llama 3.1)Size=8b, Setting=Few-shot, Steering=Steered Model (αbest), αbest=0.32025.0530.6714.812.070.073.5