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

Entertainment

Benchmarks

Task NameDataset NameSOTA ResultTrend
AI-generated text detectionEntertainment
AUC1
24
Machine-generated text detectionEntertainment Llama-3-70B-Instruct (test)
AUC1
12
AI-generated text detectionEntertainment GPT-3.5 Turbo
AUC0.983
12
Multi-label ClassificationEntertainment
Ranking Loss0.8247
11
Multi-label Feature SelectionEntertainment
Macro-F125.44
11
Multi-label Feature SelectionEntertainment
CV Score7.238
11
Multi-label Feature SelectionEntertainment (test)
HL0.0665
11
Multi-label feature selectionEntertainment
OE Score0.95
11
Multi-label Feature SelectionEntertainment
AP13.31
11
Prompt Injection DetectionEntertainment Direct Prompt Injection
FPR0
7
Showing 10 of 10 rows