MCBench: A Multicontext Safety Assessment Benchmark for Omni Large Language Models 事件

MCBench: A Multicontext Safety Assessment Benchmark for Omni Large Language Models arXiv:2606.05177v1 Announce Type: new Abstract: Existing multimodal safety benchmarks focus solely on visual inputs and cannot assess Omni Large Language Models (LLMs) that process vision, audio, and text. We introduce MCBench, a benchmark with 1196 scenarios spanning four safety categories that require integrating multiple modalities for accurate safety assessment. Each unsafe scenario is paired with a minimally