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

Safety Detection on Alpaca and AdvBench Conversation Level (test)

100MCA Accuracy

ReGA

90.6493.0795.597.93Jun 2, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.06
100100100
2025.06
100100100
2025.06
99100100
2025.06
9899100
2025.06
979298.5
2025.06
959498.4
2025.06
916192.5