List your company

Question Answering on SciQ (train)

100AccuracyVanilla
-4235077Feb 28, 2025

Evaluation results

MethodLinks
VanillaModel=OLMo2025.02100
VanillaModel=Pythia2025.02100
VanillaModel=RPJ2025.02100
Belief-SRModel=OLMo2025.0295.4
Belief-SRModel=OLMo2025.0295.2
VanillaModel=OLMo2025.0294.5
Belief-SRModel=Pythia2025.0293.4
Belief-SRModel=Pythia2025.0293.2
Belief-SRModel=OLMo2025.0292.8
Answer-SRModel=Pythia2025.0292
VanillaModel=Pythia2025.0291.8
Belief-SRModel=Pythia2025.0291.7
Answer-SRModel=Pythia2025.0291.7
Belief-SRModel=RPJ2025.0291.4
Answer-SRModel=OLMo2025.0291.1
Belief-SRModel=RPJ2025.0291.1
Answer-SRModel=RPJ2025.0291
Answer-SRModel=OLMo2025.0291
Answer-SRModel=RPJ2025.0290.7
Answer-SRModel=OLMo2025.0290.6
Knowledge-SRModel=OLMo2025.0290.2
Knowledge-SRModel=Pythia2025.0290.1
Knowledge-SRModel=OLMo2025.0290
Knowledge-SRModel=Pythia2025.0289.7
VanillaModel=RPJ2025.0289.6
Belief-SRModel=RPJ2025.0289.3
Answer-SRModel=RPJ2025.0289
Answer-SRModel=Pythia2025.0288.5
Knowledge-SRModel=OLMo2025.0287.1
Knowledge-SRModel=RPJ2025.0287.1
Knowledge-SRModel=RPJ2025.0286.4
Knowledge-SRModel=Pythia2025.0285.4
Knowledge-SRModel=RPJ2025.0280.5
VanillaModel=OLMo2025.020
VanillaModel=Pythia2025.020
VanillaModel=RPJ2025.020