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

Dialogue Evaluation on Ice-breaker human evaluation 1.0 (test)

0.552Overall Score

Model A

-0.29976-0.078630.14250.36363Mar 11, 2022
Updated 4d ago

Evaluation Results

MethodLinks
2022.03
0.5520.5650.5270.8731.0181.011-0.2870.156
2022.03
0.4220.5890.560.5180.7180.5270.0090.034
2022.03
0.3760.3790.340.6340.7690.82-0.221-0.087
2022.03
0.3220.6150.5370.190.6310.061-0.3440.565
2022.03
0.2730.4060.340.4140.6330.423-0.3690.063
2022.03
0.2220.4020.3370.0890.654-0.068-0.3760.514
2022.03
-0.139-0.277-0.2040.1230.3490.295-0.6380.62
2022.03
-0.198-0.172-0.203-0.0540.316-0.343-0.533-0.396
2022.03
-0.24-0.125-0.161-0.1960.318-0.393-0.631-0.489
2022.03
-0.267-0.426-0.402-0.0110.2340-0.628-0.636