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

Explanation Evaluation on FEVER (test)

9.72Sufficiency

Int-Grad

-4.1952-0.58263.036.6426Jun 1, 2021
Updated 4d ago

Evaluation Results

MethodLinks
2021.06
9.7217.81
2021.06
6.3611.94
2021.06
6.1920.82
2021.06
4.9913.69
2021.06
4.215.62
2021.06
4.1724.51
2021.06
2.6311.44
2021.06
0.6619.26
2021.06
0.3922.06
2021.06
-0.0118.9
2021.06
-0.2433.86
2021.06
-1.2418.84
2021.06
-1.2631.79
2021.06
-1.5132.47
2021.06
-2.0437.72
2021.06
-3.6624.07