List your company

Factuality Evaluation on NQ-Swap

43.7Science Category ScoreCoDA
32.46835.38438.341.216Feb 22, 2025

Evaluation results

MethodLinks
CoDABackbone=Mistral-7b2025.0243.7—27.7
CoTBackbone=Mistral-7b2025.0239—19.5
CoDABackbone=Llama-2-7b-chat2025.0238.9—26.8
DolaBackbone=Mistral-7b2025.0238.4—15.9
SRBackbone=Mistral-7b2025.0238.2—13.8
CoTBackbone=Llama-2-7b-chat2025.0236.7—19.2
GreedyBackbone=Mistral-7b2025.0236.7—12.6
USCBackbone=Mistral-7b2025.0235.9—11.4
SRBackbone=Llama-2-7b-chat2025.0235.8—14.2
GreedyBackbone=Llama-2-7b-chat2025.0233.4—8.5
DolaBackbone=Llama-2-7b-chat2025.0233—13.8
USCBackbone=Llama-2-7b-chat2025.0232.9—9.4