关系破裂：在旋转和噪声下的视觉语言模型关系幻觉分析
When Relations Break: Analyzing Relation Hallucination in Vision-Language Model Under Rotation and Noise
AI总结：
研究探讨了旋转和噪声对视觉语言模型关系推理的影响，发现轻微扰动显著降低模型性能，提示需更鲁棒的几何感知模型。
摘要：
视觉语言模型（VLMs）在多模态任务中表现优异，但易出现关系幻觉，即对物体间交互的不准确推理。本文研究了视觉扰动（旋转和噪声）的影响，发现即使轻微的扭曲也会显著降低不同模型和数据集上的关系推理能力。进一步评估了基于提示的增强和预处理策略（方向校正和去噪），发现这些方法提供部分改进，但无法完全解决幻觉问题。我们的结果揭示了感知鲁棒性与关系理解之间的差距，强调了需要更鲁棒、几何感知的VLMs。
英文摘要：
Vision-language models (VLMs) achieve strong multimodal performance but remain prone to relation hallucination, which requires accurate reasoning over inter-object interactions. We study the impact of visual perturbations, specifically rotation and noise, and show that even mild distortions significantly degrade relational reasoning across models and datasets. We further evaluate prompt-based augmentation and preprocessing strategies (orientation correction and denoising), finding that while they offer partial improvements, they do not fully resolve hallucinations. Our results reveal a gap between perceptual robustness and relational understanding, highlighting the need for more robust, geometry-aware VLMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
