List your company

Factuality and Uncertainty Estimation on Bios (test)

71.4FALOGU-DPO
36.97645.91354.8563.787Oct 18, 2024

Evaluation results

MethodLinks
LOGU-DPOBackbone=Llama3-8B-Instruct, Method Category=Training-Based2024.1071.470.94.84
LOGU-DPOBackbone=Mistral-7B-Instruct, Method Category=Training-Based2024.1065.480.76.54
Pair-FewBackbone=Llama3-8B-Instruct, Method Category=Prompt-Based2024.1060.646.39.86
Unc-FewBackbone=Llama3-8B-Instruct, Method Category=Prompt-Based2024.1058.769.111.7
LOGU-SFTBackbone=Llama3-8B-Instruct, Method Category=Training-Based2024.1058.569.711.5
LOGU-SFTBackbone=Mistral-7B-Instruct, Method Category=Training-Based2024.1054.577.111.4
Unc-ZeroBackbone=Llama3-8B-Instruct, Method Category=Prompt-Based2024.1053.865.414.9
Orig.Backbone=Llama3-8B-Instruct, Method Category=Original Model2024.1051.9—20.4
Self-RefineBackbone=Llama3-8B-Instruct, Method Category=Prompt-Based2024.1051.840.518.8
Unc-ZeroBackbone=Mistral-7B-Instruct, Method Category=Prompt-Based2024.1043.676.622.3
Unc-FewBackbone=Mistral-7B-Instruct, Method Category=Prompt-Based2024.1041.774.822.8
Pair-FewBackbone=Mistral-7B-Instruct, Method Category=Prompt-Based2024.1040.366.725.9
Orig.Backbone=Mistral-7B-Instruct, Method Category=Original Model2024.1038.8—27.9
Self-RefineBackbone=Mistral-7B-Instruct, Method Category=Prompt-Based2024.1038.357.427.2