List your company

Question Answering on HotpotQA D (eval)

46.2AccuracyBelief-SR
30.80834.80438.842.796Feb 28, 2025

Evaluation results

MethodLinks
Belief-SRModel=OLMo2025.0246.2
VanillaModel=OLMo2025.0242.9
Knowledge-SRModel=OLMo2025.0242.9
Answer-SRModel=OLMo2025.0239.6
Belief-SRModel=Pythia2025.0238.5
Belief-SRModel=RPJ2025.0238.5
VanillaModel=RPJ2025.0236.5
Knowledge-SRModel=RPJ2025.0235.6
VanillaModel=Pythia2025.0234.3
Answer-SRModel=RPJ2025.0234.1
Knowledge-SRModel=Pythia2025.0233.5
Answer-SRModel=Pythia2025.0231.4