Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Argument validity and novelty prediction on VALNOV (test)

45.16Joint F1

ST-1st (GPT-3)

-23.2824-5.513712.25530.0237May 15, 2023
Updated 4d ago

Evaluation Results

MethodLinks
2023.05
45.1674.6461.32
2023.05
43.9170.6963.3
2023.05
43.2769.862.43
2023.05
37.8264.7759.96
2023.05
37.7167.0763.53
2023.05
36.2267.6163.27
2023.05
35.9462.7452.97
2023.05
23.959.9636.12
2023.05
-2.27-0.27-3.73
2023.05
-3.25-4.451.76
2023.05
-5.6-4.01-0.6
2023.05
-6.51-3.8-1.69
2023.05
-6.71-3.230.55
2023.05
-11.65-3.4-5.12
2023.05
-20.65-20.74-17.69