List your company
ResearchFormerly WizWand

Multiple-choice task on COSE_KRE

60.23AccuracyOpin
23.798833.256942.71552.1731Jun 26, 2024
Updated 8mo ago

Evaluation results

MethodLinks
OpinBackbone=LLaMA-3-8B-Instruct2024.0660.2330.11
IRCAN-CADBackbone=LLaMA-2-13B-Chat2024.0657.7722.09
CADBackbone=LLaMA-2-13B-Chat2024.0656.9622.59
CADBackbone=LLaMA-3-8B-Instruct2024.0652.8635.52
Based_on_FormattedBackbone=LLaMA-3-8B-Instruct2024.0651.5537.81
IRCAN-CADBackbone=LLaMA-3-8B-Instruct2024.0651.5531.42
Based_onBackbone=LLaMA-2-13B-Chat2024.0650.5729.46
ITI (Probe Weight Direction)Backbone=LLaMA-2-13B-Chat2024.0650.4125.37
Utilizing_FormattedBackbone=LLaMA-3-8B-Instruct2024.0650.0840.1
OriginalBackbone=LLaMA-2-13B-Chat2024.0649.7529.13
IRCANBackbone=LLaMA-2-13B-Chat2024.0649.2630.11
IRCAN-CADBackbone=LLaMA-2-7B-Chat2024.0648.6119.48
IRCANBackbone=LLaMA-2-7B-Chat2024.0645.0124.88
OpinBackbone=LLaMA-2-13B-Chat2024.0643.2122.91
Based_onBackbone=LLaMA-3-8B-Instruct2024.0642.8845.34
IRCANBackbone=LLaMA-3-8B-Instruct2024.0642.7237.64
IRCAN-CADBackbone=Gemma-2B-it2024.0641.917.35
CADBackbone=LLaMA-2-7B-Chat2024.0641.5719.8
Utilizing_FormattedBackbone=LLaMA-2-13B-Chat2024.0641.5721.93
Based_on_FormattedBackbone=LLaMA-2-13B-Chat2024.0641.2423.57
ITI (Probe Weight Direction)Backbone=LLaMA-3-8B-Instruct2024.0640.7545.01
OriginalBackbone=LLaMA-3-8B-Instruct2024.0639.9347.79
IRCANBackbone=Gemma-2B-it2024.0639.1218.99
Utilizing_FormattedBackbone=Gemma-2B-it2024.0638.9522.26
ITI (Mass Mean Shift)Backbone=LLaMA-3-8B-Instruct2024.0638.9543.04
Based_on_FormattedBackbone=Gemma-2B-it2024.0638.4622.42
CADBackbone=Gemma-2B-it2024.0637.9719.64
ITI (Probe Weight Direction)Backbone=LLaMA-2-7B-Chat2024.0637.3217.51
OriginalBackbone=LLaMA-2-7B-Chat2024.0636.6623.4
OpinBackbone=Gemma-2B-it2024.0635.1919.97
OpinBackbone=LLaMA-2-7B-Chat2024.0635.1917.35
OriginalBackbone=Gemma-2B-it2024.0635.0221.28
Based_onBackbone=Gemma-2B-it2024.0634.722.42
Based_onBackbone=LLaMA-2-7B-Chat2024.0633.2220.29
Utilizing_FormattedBackbone=LLaMA-2-7B-Chat2024.0633.0618
Based_on_FormattedBackbone=LLaMA-2-7B-Chat2024.0632.4118.49
ITI (Probe Weight Direction)Backbone=Gemma-2B-it2024.0631.5923.57
ITI (Mass Mean Shift)Backbone=Gemma-2B-it2024.0629.4623.73
ITI (Mass Mean Shift)Backbone=LLaMA-2-7B-Chat2024.0626.3518.66
ITI (Mass Mean Shift)Backbone=LLaMA-2-13B-Chat2024.0625.219.15