Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Semantic Textual Similarity on STS-B (Accuracy/Bias evaluation)

0.595Accuracy

EAR

0.45460.491050.52750.56395Jun 6, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.06
0.5950.333
2024.06
0.5910.304
2024.06
0.5780.33
2024.06
0.570.181
2024.06
0.5180.314
2024.06
0.5090.233
2024.06
0.5070.197
2024.06
0.4940.28
2024.06
0.4730.184
2024.06
0.460.169