List your company

Question Answering on TruthfulQA (Factuality, TTR)

57.89FactualityMin-k + VCM
54.333255.256656.1857.1034Jun 21, 2026

Evaluation results

MethodLinks
Min-k + VCMSampler=Min-k, VCM=Enabled, Base Model=LLaMA-3-8B-Instruct2026.0657.8978.17
η-sampling + VCMSampler=η-sampling, VCM=Enabled, Base Model=LLaMA-3-8B-Instruct2026.0657.2878.85
Top-p + VCMSampler=Top-p, VCM=Enabled, Base Model=LLaMA-3-8B-Instruct2026.0657.1678.85
p-less + VCMSampler=p-less, VCM=Enabled, Base Model=LLaMA-3-8B-Instruct2026.0657.1679.35
ϵ-sampling + VCMSampler=ϵ-sampling, VCM=Enabled, Base Model=LLaMA-3-8B-Instruct2026.0657.0478.85
Top-k + VCMSampler=Top-k, VCM=Enabled, Base Model=LLaMA-3-8B-Instruct2026.0656.7979.32
Top-nσ + VCMSampler=Top-nσ, VCM=Enabled, Base Model=LLaMA-3-8B-Instruct2026.0656.7978.53
Typical + VCMSampler=Typical, VCM=Enabled, Base Model=LLaMA-3-8B-Instruct2026.0656.4379.12
Min-p + VCMSampler=Min-p, VCM=Enabled, Base Model=LLaMA-3-8B-Instruct2026.0656.4378.8
p-lessSampler=p-less, VCM=Disabled, Base Model=LLaMA-3-8B-Instruct2026.0656.376.6
TypicalSampler=Typical, VCM=Disabled, Base Model=LLaMA-3-8B-Instruct2026.0656.0676.88
η-samplingSampler=η-sampling, VCM=Disabled, Base Model=LLaMA-3-8B-Instruct2026.0656.0677.04
ϵ-samplingSampler=ϵ-sampling, VCM=Disabled, Base Model=LLaMA-3-8B-Instruct2026.0655.9477.04
Top-pSampler=Top-p, VCM=Disabled, Base Model=LLaMA-3-8B-Instruct2026.0655.8177.04
Top-kSampler=Top-k, VCM=Disabled, Base Model=LLaMA-3-8B-Instruct2026.0655.5777.59
Min-kSampler=Min-k, VCM=Disabled, Base Model=LLaMA-3-8B-Instruct2026.0655.5777.09
Min-pSampler=Min-p, VCM=Disabled, Base Model=LLaMA-3-8B-Instruct2026.0654.5977.11
Top-nσSampler=Top-nσ, VCM=Disabled, Base Model=LLaMA-3-8B-Instruct2026.0654.4777.06