When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space

Large language models (LLMs) increasingly serve as high-level planners for embodied agents, where linguistically benign instructions can become unsafe once grounded in the physical world. We study whether this physically grounded danger is the same safety problem as ordinary text-level content danger. Through hidden-state direction analysis and random-split null tests, we show that content danger (CD) and physical danger (PD) form separable signals in LLM representations across Qwen2.5-3B/7B/14B/32B, Phi-3.5 and SmolLM2. Building on the CD/PD separability, we propose PRISM, a single-layer L2-regularized logistic probe over full hidden states. PRISM achieves 86.2--87.7\% accuracy on SafeAgentBench with 11.7--13.7\% FPR, while same-scale LLM judges over-block safe tasks at 24.7--39.0\% FPR. We further introduce PhysicalSafetyBench-1K (PSB-1K), a contrastive benchmark of 1{,}000 physical-risk pairs without direct harm keywords, to test whether methods detect physically grounded danger rather than explicit unsafe wording. On PSB-1K, PRISM reaches 99.6\% accuracy and 0.7\% FPR, whereas a Qwen2.5-3B judge rejects 67.8\% of safe tasks. PRISM also replicates on SafeText and EARBench, supporting hidden-state probing as a representation-level method for physical safety beyond text moderation.

Evaluating and Calibrating LLM Confidence on Questions with Multiple Correct Answers

Confidence calibration is essential for making large language models (LLMs) reliable, yet existing training-free methods have been primarily studied under single-answer question answering. In this paper, we show that these methods break down in the presence of multiple valid answers, where disagreement among equally correct responses leads to systematic underestimation of confidence. To enable a systematic study of this phenomenon, we introduce MACE, a benchmark of 12,000 factual questions spanning six domains with varying numbers of correct answers. Experiments across 15 representative calibration methods and four LLM families (7B-72B) reveal that while accuracy increases with answer cardinality, estimated confidence consistently decreases, causing severe miscalibration for questions with mixed answer counts. To address this issue, we propose Semantic Confidence Aggregation (SCA), which aggregates confidence over multiple high-probability sampled responses. SCA achieves state-of-the-art calibration performance under mixed-answer settings while preserving strong calibration on single-answer questions.