ResearchBenchmarksLLM Safety Defense on CoSafeFollow15.42ASRMTSA-T314.388821.349428.3135.2706May 22, 2025Evaluation ResultsMethodMethodLinksASRMTSA-T3Target Model=Llama2-7B...Target Model=Llama2-7B-Chat, Iteration=32025.0515.42MTSA-T3Target Model=Zephyr-7B...Target Model=Zephyr-7B-Beta, Iteration=32025.0518.78BaselineTarget Model=Llama2-7B...Target Model=Llama2-7B-Chat2025.0539.4BaselineTarget Model=Zephyr-7B...Target Model=Zephyr-7B-Beta2025.0541.2