List your company

Robustness on Robustness

87.97RRSAC Multi-task
37.47850.586563.69576.8035Nov 4, 2024

Evaluation results

MethodLinks
SAC Multi-taskModel=Qwen2-72B (Instruct)2024.1187.97
SAC Single-taskModel=Qwen2-7B (Instruct)2024.1185.89
SAC Single-taskModel=Qwen2-72B (Instruct)2024.1184.23
SAC Multi-taskModel=Qwen2-7B (Instruct)2024.1182.16
SAC Single-taskModel=Llama2-13B (Chat)2024.1178.42
SAC Multi-taskModel=Llama2-13B (Chat)2024.1175.93
No ControlModel=Qwen2-72B (Instruct)2024.1158.51
No ControlModel=Qwen2-7B (Instruct)2024.1157.68
No ControlModel=Llama2-13B (Chat)2024.1139.42