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

Natural Language Inference on QNLI few-shot zero-shot

71.6Accuracy

RETROPROMPT

35.09644.57354.0563.527May 29, 2022
Updated 1mo ago

Evaluation Results

MethodLinks
2022.05
71.6
2022.05
69.2
2022.05
64.6
2022.05
62.2
2022.05
61.7
2022.05
61.5
2022.05
61.1
2022.05
60.2
2022.05
59.2
2022.05
56.2
2022.05
55.3
2022.05
54.2
2022.05
53.5
2022.05
50.5
2022.05
49.5
2022.05
36.5