List your company
ResearchFormerly WizWand

Sentiment Classification on Tweet (test)

48AccuracyICL-gold
19.426.82534.2541.675Dec 19, 2022
Updated 8mo ago

Evaluation results

MethodLinks
ICL-goldModel=GPT-J, Prompting=Channel, Training data access=true2022.1248
ICL-goldModel=GPT-NeoX, Prompting=Channel, Training data access=true2022.1247.9
No-demosModel=GPT-J, Prompting=Channel, Training data access=false2022.1247.6
Z-ICLModel=GPT-J, Prompting=Channel, Training data access=false2022.1246.8
ICL-randomModel=GPT-J, Prompting=Channel, Training data access=true2022.1246.8
Z-ICLModel=GPT-NeoX, Prompting=Channel, Training data access=false2022.1246.7
ICL-randomModel=GPT-NeoX, Prompting=Channel, Training data access=true2022.1244
ICL-goldPrompting Method=Channel, Backbone=GPT-3, Oracle=true2022.1243.8
ICL-randomPrompting Method=Direct, Backbone=GPT-3, Oracle=true2022.1242.2
Naive Z-ICLModel=GPT-J, Prompting=Channel, Training data access=false2022.1242.2
Random inputsModel=GPT-J, Prompting=Channel, Training data access=false2022.1241.5
Z-ICLPrompting Method=Channel, Backbone=GPT-32022.1241.4
ICL-randomPrompting Method=Channel, Backbone=GPT-3, Oracle=true2022.1241.4
Naive Z-ICLModel=GPT-NeoX, Prompting=Direct, Training data access=false2022.1240.2
No-demosModel=GPT-J, Prompting=Direct, Training data access=false2022.1239.5
Naive Z-ICLModel=GPT-NeoX, Prompting=Channel, Training data access=false2022.1238.9
Majority2022.1238.1
MajorityTraining data access=false2022.1238.1
No-demosPrompting Method=Direct, Backbone=GPT-32022.1237.8
Random inputsModel=GPT-NeoX, Prompting=Direct, Training data access=false2022.1236.4
No-demosPrompting Method=Channel, Backbone=GPT-32022.1236.2
Z-ICLModel=GPT-NeoX, Prompting=Direct, Training data access=false2022.1235.2
ICL-goldModel=GPT-J, Prompting=Direct, Training data access=true2022.1235
Random inputsModel=GPT-NeoX, Prompting=Channel, Training data access=false2022.1234.6
ICL-randomModel=GPT-J, Prompting=Direct, Training data access=true2022.1233.4
ICL-randomModel=GPT-NeoX, Prompting=Direct, Training data access=true2022.1233.1
ICL-goldModel=GPT-NeoX, Prompting=Direct, Training data access=true2022.1232.8
Naive Z-ICLModel=GPT-J, Prompting=Direct, Training data access=false2022.1232.3
No-demosModel=GPT-NeoX, Prompting=Direct, Training data access=false2022.1230.8
ICL-goldPrompting Method=Direct, Backbone=GPT-3, Oracle=true2022.1230.5
Random inputsModel=GPT-J, Prompting=Direct, Training data access=false2022.1228.8
No-demosModel=GPT-NeoX, Prompting=Channel, Training data access=false2022.1228.7
Z-ICLPrompting Method=Direct, Backbone=GPT-32022.1228.3
Z-ICLModel=GPT-J, Prompting=Direct, Training data access=false2022.1220.5