Benchmarking the safety of large language models for robotic health attendant control
Abstract Large language models (LLMs) are increasingly considered for deployment as the control component of robotic health attendants (RHAs), yet their safety in this context remains poorly characterized. We introduce a dataset of 270 harmful instructions spanning nine prohibited behaviour categories grounded in the A...
Mahiro Nakao, Kazuhiro Takemoto
· Royal Society Open Science · 0 citations