EVADE-Bench: Multimodal Benchmark for Evaluating and Enhancing Evasive Content Detection

ArXi:2505.17654v4 Announce Type: replace-cross E-commerce platforms increasingly rely on Large Language Models (LLMs) and Vision Language Models (VLMs) to detect illicit or misleading product content. However, these models remain vulnerable to evasive content, which refers to inputs that have been deliberately modified through techniques such as word splitting, euphemistic language, or image cropping to conceal policy violations while still conveying prohibited claims.