List your company

Fact Verification on FEVER-S

54AccuracyCPO
43.91246.53149.1551.769Jun 13, 2024

Evaluation results

MethodLinks
CPOBackbone=Mistral-7B2024.065453
ToTBackbone=LLAMA2-13B2024.0651.33,433.2
CPOBackbone=LLAMA2-13B2024.0650.768.2
ToTBackbone=Mistral-7B2024.0650.55,537.8
CoTBackbone=LLAMA2-13B2024.065061.1
TS-SFTBackbone=Mistral-7B2024.0649.749.5
CPOBackbone=LLAMA2-7B2024.064941.2
TS-SFTBackbone=LLAMA2-13B2024.0648.858
CoTBackbone=Mistral-7B2024.064851
ToTBackbone=LLAMA2-7B2024.0647.52,539.5
TS-SFTBackbone=LLAMA2-7B2024.064640.4
CoTBackbone=LLAMA2-7B2024.0644.340.6