List your company
ResearchFormerly WizWand

Knowledge Elicitation on PARAREL (test)

71.36Success RatePGDC
-0.358418.260836.8855.4992Feb 18, 2024
Updated 8mo ago

Evaluation results

MethodLinks
PGDCModel=LLaMA2 (7B)2024.0271.36
Few-shotsModel=Vicuna (7B), Prompt Variant=paraphrased2024.0269.69
PGDCModel=Vicuna (7B)2024.0269.63
Few-shotsModel=LLaMA2 (7B), Prompt Variant=paraphrased2024.0266.95
Few-shotsModel=Vicuna (7B), Prompt Variant=standard2024.0259.56
Few-shotsModel=LLaMA2 (7B), Prompt Variant=standard2024.0258.23
PGDCModel=GPT-J (6B)2024.0255.95
Zero-shotModel=Vicuna (7B), Prompt Variant=paraphrased2024.0254.97
Zero-shotModel=LLaMA2 (7B), Prompt Variant=paraphrased2024.0254.78
Few-shotsModel=GPT-J (6B), Prompt Variant=paraphrased2024.0254.06
PGDCModel=GPT-2 (774M)2024.0247.68
Few-shotsModel=GPT-J (6B), Prompt Variant=standard2024.0244.84
DiscriminatorModel=LLaMA2 (7B), Prompt Variant=paraphrased2024.0244.16
Zero-shotModel=GPT-J (6B), Prompt Variant=paraphrased2024.0240.78
Zero-shotModel=LLaMA2 (7B), Prompt Variant=standard2024.0234.43
Zero-shotModel=Vicuna (7B), Prompt Variant=standard2024.0234.19
Zero-shotModel=GPT-J (6B), Prompt Variant=standard2024.0223.23
DiscriminatorModel=Vicuna (7B), Prompt Variant=paraphrased2024.0223.06
Few-shotsModel=GPT-2 (774M), Prompt Variant=paraphrased2024.0220.46
Zero-shotModel=GPT-2 (774M), Prompt Variant=paraphrased2024.0218.18
DiscriminatorModel=LLaMA2 (7B), Prompt Variant=standard2024.0217.96
Few-shotsModel=GPT-2 (774M), Prompt Variant=standard2024.0212.61
Zero-shotModel=GPT-2 (774M), Prompt Variant=standard2024.029.27
DiscriminatorModel=GPT-2 (774M), Prompt Variant=paraphrased2024.029.01
DiscriminatorModel=Vicuna (7B), Prompt Variant=standard2024.028.4
DiscriminatorModel=GPT-J (6B), Prompt Variant=paraphrased2024.027.25
DiscriminatorModel=GPT-2 (774M), Prompt Variant=standard2024.023.13
DiscriminatorModel=GPT-J (6B), Prompt Variant=standard2024.022.4