List your company

Long-form Question Answering on AlpacaFact

66.9VeriScore F1EWE
50.67654.88859.163.312Dec 24, 2024

Evaluation results

MethodLinks
EWEBase Model=Llama-3.1 70B2024.1266.949.9
RABase Model=Llama-3.1 70B2024.126643.1
EWEBase Model=Llama-3.1 8B2024.1265.528
DRAGINBase Model=Llama-3.1 70B2024.1265.331.5
Llama-3.1Base Model=Llama-3.1 8B2024.1265.326.7
COVE w/ RetrievalBase Model=Llama-3.1 70B2024.126428.8
RABase Model=Llama-3.1 8B2024.1263.918.5
Llama-3.1Base Model=Llama-3.1 70B2024.1263.8—
COVEBase Model=Llama-3.1 70B2024.1261.533.3
DRAGINBase Model=Llama-3.1 8B2024.1261.311.1
NESTBase Model=Llama-3.1 70B2024.1258.130.2
NESTBase Model=Llama-3.1 8B2024.1257.89.1
COVE w/ RetrievalBase Model=Llama-3.1 8B2024.1254.612.5
COVEBase Model=Llama-3.1 8B2024.1251.315.1