conftrace_

physical safety

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) ai safety (2) command refusal (1) plan safety test (1) plan safety (1) unsafe command detection (1) unsafe text generation (1) commonsense physical safety (1) embodied decision-making (1) language model safety (1)

Papers

BadRobot: Jailbreaking Embodied LLM Agents in the Physical World ICLR 2025 Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making EMNLP 2025 SafeText: A Benchmark for Exploring Physical Safety in Language Models EMNLP 2022