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

SBIC

Benchmarks

Task NameDataset NameSOTA ResultTrend
Hate-speech detectionSBIC (test)
Avg Exit12
12
Bias DetectionSBIC (test)
Accuracy93.6
12
Hate speech detectionSBIC
Total F157
11
Text ClassificationSBIC
Total Metric-0.0071
11
Natural Language Explanation GenerationSBIC
Human Evaluation Score71.11
7
Natural Language Explanation GenerationSBIC (test)
Accuracy66.99
6
Natural Language Explanation GenerationSBIC 60-shot
Accuracy63.86
3
Showing 7 of 7 rows