List your company

Commonsense Reasoning on BoolQ (Inter/Intra-Layer Filtering)

67Accuracy (Inter-Layer Filtering)CRFT
50.04854.44958.8563.251Jul 14, 2025

Evaluation results

MethodLinks
CRFTBackbone=LLaMA-3-8B, Identify=MSF2025.076767.9—
CRFTBackbone=LLaMA-3-8B, Identify=SSF2025.076466.6—
CRFTBackbone=LLaMA-3-8B, Identify=SAF2025.076366.4—
CRFTBackbone=Mistral-7B, Identify=SAF2025.076366.5—
ReFTBackbone=Mistral-7B, Identify=p7+s72025.0762.562.5—
CRFTBackbone=Mistral-7B, Identify=MSF2025.0762.565—
CRFTBackbone=LLaMA-3-8B, Identify=MAF2025.0762.466.2—
CRFTBackbone=Mistral-7B, Identify=SSF2025.0762.364.8—
ReFTBackbone=LLaMA-3-8B, Identify=p7+s72025.0762.162.1—
CRFTBackbone=Mistral-7B, Identify=MAF2025.0762.160.8—
CRFTBackbone=LLaMA-2-7B, Identify=SSF2025.076254.3—
CRFTBackbone=LLaMA-2-7B, Identify=MAF2025.0760.561.8—
CRFTBackbone=LLaMA-2-7B, Identify=SAF2025.076053.7—
CRFTBackbone=LLaMA-2-7B, Identify=MSF2025.076059.7—
ReFTBackbone=LLaMA-2-7B, Identify=p7+s72025.0750.750.7—
ArrowZero-shot=true, Base Model=Phi-32025.05——80
GenKnowSubSetting=En, Zero-shot=true, Base Model=Phi-32025.05——81.96
GenKnowSubSetting=De, Zero-shot=true, Base Model=Phi-32025.05——82.01
GenKnowSubSetting=Fr, Zero-shot=true, Base Model=Phi-32025.05——82.11
GenKnowSubSetting=Avg, Zero-shot=true, Base Model=Phi-32025.05——82.45
Mean NormZero-shot=true, Base Model=Phi-32025.05——80.89
Phi-3Zero-shot=true, Base Model=Phi-32025.05——81.47
SharedZero-shot=true, Base Model=Phi-32025.05——63.39