List your company
ResearchFormerly WizWand

Knowledge Elicitation on KAssess

0.6984Success RatePGDC
-0.0044320.1780340.36050.542966Feb 18, 2024
Updated 8mo ago

Evaluation results

MethodLinks
PGDCModel=LLaMA2 (7B)2024.020.6984
PGDCModel=Vicuna (7B)2024.020.5763
Few-shotsModel=Vicuna (7B), Prompt Variant=paraphrased2024.020.5366
Zero-shotModel=Vicuna (7B), Prompt Variant=paraphrased2024.020.5115
Few-shotsModel=LLaMA2 (7B), Prompt Variant=paraphrased2024.020.5075
Zero-shotModel=LLaMA2 (7B), Prompt Variant=paraphrased2024.020.5
PGDCModel=GPT-J (6B)2024.020.4862
Zero-shotModel=GPT-J (6B), Prompt Variant=paraphrased2024.020.4023
DiscriminatorModel=Vicuna (7B), Prompt Variant=paraphrased2024.020.382
Few-shotsModel=GPT-J (6B), Prompt Variant=paraphrased2024.020.382
Few-shotsModel=Vicuna (7B), Prompt Variant=standard2024.020.3337
Few-shotsModel=LLaMA2 (7B), Prompt Variant=standard2024.020.3203
DiscriminatorModel=LLaMA2 (7B), Prompt Variant=paraphrased2024.020.2473
PGDCModel=GPT-2 (774M)2024.020.2471
Zero-shotModel=LLaMA2 (7B), Prompt Variant=standard2024.020.2369
Zero-shotModel=Vicuna (7B), Prompt Variant=standard2024.020.2321
Few-shotsModel=GPT-J (6B), Prompt Variant=standard2024.020.2047
Zero-shotModel=GPT-J (6B), Prompt Variant=standard2024.020.1595
DiscriminatorModel=GPT-2 (774M), Prompt Variant=paraphrased2024.020.1575
Zero-shotModel=GPT-2 (774M), Prompt Variant=paraphrased2024.020.1366
DiscriminatorModel=GPT-J (6B), Prompt Variant=standard2024.020.1267
Few-shotsModel=GPT-2 (774M), Prompt Variant=paraphrased2024.020.1144
DiscriminatorModel=Vicuna (7B), Prompt Variant=standard2024.020.099
DiscriminatorModel=LLaMA2 (7B), Prompt Variant=standard2024.020.0673
Zero-shotModel=GPT-2 (774M), Prompt Variant=standard2024.020.0403
Few-shotsModel=GPT-2 (774M), Prompt Variant=standard2024.020.0364
DiscriminatorModel=GPT-2 (774M), Prompt Variant=standard2024.020.0246
DiscriminatorModel=GPT-J (6B), Prompt Variant=paraphrased2024.020.0226