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

Targeted Refusal

Benchmarks

Task NameDataset NameSOTA ResultTrend
Targeted RefusalTargeted Refusal LLaMA2-13B-Chat (test)
BadNets100
11
Targeted RefusalTargeted Refusal LLaMA2-7B-Chat (test)
BadNets100
11
Showing 2 of 2 rows