List your company

Long-form Question Answering on LongFact

75.9VeriScore F1EWE
42.82851.4146068.586Dec 24, 2024

Evaluation results

MethodLinks
EWEBase Model=Llama-3.1 70B2024.1275.950.1
RABase Model=Llama-3.1 70B2024.1272.741.2
DRAGINBase Model=Llama-3.1 70B2024.1271.538.2
COVE w/ RetrievalBase Model=Llama-3.1 70B2024.1267.431.8
EWEBase Model=Llama-3.1 8B2024.1267.340.5
RABase Model=Llama-3.1 8B2024.1265.928.1
Llama-3.1Base Model=Llama-3.1 70B2024.1264.3—
DRAGINBase Model=Llama-3.1 8B2024.1263.915.9
COVEBase Model=Llama-3.1 70B2024.1263.839.3
NESTBase Model=Llama-3.1 70B2024.1263.29.1
Llama-3.1Base Model=Llama-3.1 8B2024.1263.140.6
NESTBase Model=Llama-3.1 8B2024.1262.34.2
COVE w/ RetrievalBase Model=Llama-3.1 8B2024.1253.512.2
COVEBase Model=Llama-3.1 8B2024.1244.18.8