List your company
ResearchFormerly WizWand

Knowledge Elicitation on CFACT

3,646Success RateDiscriminator
-31.44923.281,8782,832.72Feb 18, 2024
Updated 8mo ago

Evaluation results

MethodLinks
DiscriminatorModel=LLaMA2 (7B), Prompt Variant=paraphrased2024.023,646
DiscriminatorModel=Vicuna (7B), Prompt Variant=paraphrased2024.021,428
DiscriminatorModel=LLaMA2 (7B), Prompt Variant=standard2024.021,388
DiscriminatorModel=GPT-2 (774M), Prompt Variant=paraphrased2024.02932
Few-shotsModel=LLaMA2 (7B), Prompt Variant=paraphrased2024.02931
Few-shotsModel=Vicuna (7B), Prompt Variant=paraphrased2024.02691
DiscriminatorModel=GPT-J (6B), Prompt Variant=paraphrased2024.02674
Few-shotsModel=GPT-J (6B), Prompt Variant=paraphrased2024.02612
DiscriminatorModel=Vicuna (7B), Prompt Variant=standard2024.02495
PGDCModel=GPT-J (6B)2024.02482
Few-shotsModel=LLaMA2 (7B), Prompt Variant=standard2024.02456
Few-shotsModel=GPT-2 (774M), Prompt Variant=paraphrased2024.02392
Zero-shotModel=GPT-J (6B), Prompt Variant=paraphrased2024.02375
PGDCModel=Vicuna (7B)2024.02350
PGDCModel=LLaMA2 (7B)2024.02341
Zero-shotModel=Vicuna (7B), Prompt Variant=paraphrased2024.02336
Zero-shotModel=LLaMA2 (7B), Prompt Variant=paraphrased2024.02330
DiscriminatorModel=GPT-2 (774M), Prompt Variant=standard2024.02328
Few-shotsModel=GPT-J (6B), Prompt Variant=standard2024.02318
Few-shotsModel=Vicuna (7B), Prompt Variant=standard2024.02308
Zero-shotModel=GPT-2 (774M), Prompt Variant=paraphrased2024.02300
PGDCModel=GPT-2 (774M)2024.02281
DiscriminatorModel=GPT-J (6B), Prompt Variant=standard2024.02230
Few-shotsModel=GPT-2 (774M), Prompt Variant=standard2024.02177
Zero-shotModel=Vicuna (7B), Prompt Variant=standard2024.02140
Zero-shotModel=GPT-J (6B), Prompt Variant=standard2024.02139
Zero-shotModel=LLaMA2 (7B), Prompt Variant=standard2024.02132
Zero-shotModel=GPT-2 (774M), Prompt Variant=standard2024.02110