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

mixed-source

Benchmarks

Task NameDataset NameSOTA ResultTrend
AI-Generated Text Detectionmixed-source AI -> Human GPT-2, GPT-Neo, GPT-J, LLaMa, GPT-3
Overall Accuracy96.5
26
AI-Generated Text Detectionmixed-source Human -> AI GPT-2, GPT-Neo, GPT-J, LLaMa, GPT-3
Overall Accuracy96
13
AI-Generated Text DetectionMixed-source (test)
OA95.33
4
Illicit promotion detectionBalanced, Mixed-source (test)
Accuracy92.59
3
Showing 4 of 4 rows