SafeText: A Benchmark for Exploring Physical Safety in Language Models
Understanding what constitutes safe text is an important issue in natural language processing and can often prevent the deployment of models deemed harmful and unsafe. One such type of safety that has been scarcely studied is commonsense physical safety, i.e. text that is not explicitly violent and requires additional commonsense knowledge to comprehend that it leads to physical harm. We create the first benchmark dataset, SafeText, comprising real-life scenarios with paired safe and physically unsafe pieces of advice. We utilize SafeText to empirically study commonsense physical safety across various models designed for text generation and commonsense reasoning tasks. We find that state-of-the-art large language models are susceptible to the generation of unsafe text and have difficulty rejecting unsafe advice. As a result, we argue for further studies of safety and the assessment of commonsense physical safety in models before release.
Code (0)
등록된 구현이 없습니다.
Tasks
Text GenerationSimilar Papers 제목 키워드 기반
SafeText: Safe Text-to-image Models via Aligning the Text Encoder
Text-to-image models can generate harmful images when presented with unsafe prompts, posing significant safety and societal risks. Alignment methods aim to modify these models to ensure they generate only non-harmful ima…
Image GenerationFoveate, Attribute, and Rationalize: Towards Physically Safe and Trustworthy AI
Users' physical safety is an increasing concern as the market for intelligent systems continues to grow, where unconstrained systems may recommend users dangerous actions that can lead to serious injury. Covertly unsafe …
AttributeDefining and Evaluating Physical Safety for Large Language Models
Large Language Models (LLMs) are increasingly used to control robotic systems such as drones, but their risks of causing physical threats and harm in real-world applications remain unexplored. Our study addresses the cri…
Code GenerationIn-Context LearningPrompt EngineeringSPOC: Safety-Aware Planning Under Partial Observability And Physical Constraints
Embodied Task Planning with large language models faces safety challenges in real-world environments, where partial observability and physical constraints must be respected. Existing benchmarks often overlook these criti…
ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models
In embodied intelligence, safety is a prerequisite for reliable robot deployment in the physical world. Current vision-language-action (VLA) models continue to advance toward general-purpose task capability, yet their em…