osunlp/AmpleGCG-plus-llama2-sourced-vicuna-7b13b-guanaco-7b13b
Text Generation • 7B • Updated
Natural language processing, language models, language agents
When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents
When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents