List your company

Question Answering on QASC (Cohen's d)

0.803Cohen's dDebiased-Plausibility
-0.365544-0.0621720.24120.544572May 12, 2026

Evaluation results

MethodLinks
Debiased-PlausibilityCategory=Entropy-Plausibility, alpha=0.61, N=122026.050.803
PlausibilityCategory=Entropy-Plausibility, N=102026.050.5614
Debiased-PlausibilityCategory=Avg-Plausibility, alpha=0.53, N=132026.050.4784
PlausibilityCategory=Avg-Plausibility, N=102026.050.2724
Retrieval ComplexityCategory=Retriever-based2026.050.2225
LLaMA 3.3 70bCategory=Uncertainty-based2026.050.2119
LLaMA 3.3 70bCategory=Prompt-based2026.050.2032
LLaMA 3.1 8bCategory=Uncertainty-based2026.050.1543
Flesch-KincaidCategory=Readability2026.050.1496
LLaMA 3.1 8bCategory=Prompt-based2026.050.1065
Gunning-FogCategory=Readability2026.05-0.0944
PopQACategory=Popularity, N=42026.05-0.3206