Benchmarking Identity-Sensitive LLM Outputs for Surveillance and Security Robots

Abstract

Large language models (LLMs) are increasingly used to generate textual robot design specifications, interaction policies, and risk assessments during early-stage robot development. Such outputs may influence how surveillance and security robots are conceptualized, documented, and ultimately implemented. This paper evaluates whether identity-conditioned prompts produce systematic differences in LLM-generated surveillance and security robot design descriptions. Using 236 demographic identity label

Categories

@misc{hyman2026benchmarking,
  title = {{Benchmarking Identity-Sensitive LLM Outputs for Surveillance and Security Robots}},
  author = {Nneka Hyman and Jasmine Khan and Raj Korpan},
  year = {2026},
  month = aug,
  eprint = {2608.16030},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.16030}
}