让下一篇重要论文，不再错过。

原文摘要

Large vision-language models (LVLMs) are vulnerable to compositional harm: an image and a prompt that are benign in isolation become harmful through the model's cross-modal reasoning. Recent alignment methods report strong scores on compositional safety benchmarks, but an LLM judge only measures observed behavior and cannot reveal how robustly safety is integrated into the model. We argue that un-alignment provides a complementary audit of alignment robustness. We first show that minimal supervised fine-tuning reaches an LLM-judge score comparable to a multi-stage reinforcement-learning pipeline, so similar benchmark scores cannot establish robustness by themselves. We then show that recognition and refusal of compositional harm are decoupled: nine standard direction-finding methods detect compositional harm with up to AUC=0.99, yet ablating the recovered directions either leaves refusal intact or destroys model coherence. We therefore propose CMaG, a training-free un-alignment method for compositional safety. CMaG measures refusal intention with a refusal-versus-compliance log-probability margin, takes its gradient with respect to mid-layer activations, and contrasts it against partially benign pairs to isolate the cross-modal interaction term. A single backward pass over 80 examples yields a direction along which steering monotonically converts refusal into compliance. On Qwen2.5-VL-7B and LLaVA-1.5-7B, CMaG reduces compositional safety scores by up to 65 points while over 98% of outputs remain coherent, outperforming gradient-based baselines; the direction also transfers to text-explicit harm and un-aligns models hardened by defensive training. Compositional safety can thus appear behaviorally strong while remaining fragile to targeted internal intervention. Warning: this paper contains unsafe model outputs, including references to self-harm.