用图像编辑的溢出现象，探测模型是否真懂世界关系。
Edit Spillover as a Probe: Do Image Editing Models Implicitly Understand World Relations?
- 将编辑溢出作为探针，系统分析模型对世界关系的理解能力。
- 不同模型溢出率差异达3.3倍，语义溢出量反映真实知识水平。
- 溢出虽随距离衰减，但语义相关性稳定，证明非随机噪声。
指令遵循的图像编辑模型本应仅修改指定区域，保持其余部分不变。然而实践中普遍存在‘编辑溢出’现象：模型会改变未指定但语义相关的外部内容。这引发根本问题——溢出是源于真实世界理解，还是仅注意力泄露？本文提出EditSpilloverProbe框架，将编辑溢出作为自然探针，用于探测图像编辑模型的世界知识。构建了包含空间、语义、混合、随机四类的溢出分类体系，设计自动化检测与分类流程，并基于真实中文文本编辑任务构建了基准数据集EditSpilloverBench。对5个代表性模型的系统评估发现：（1）不同架构的溢出率差异显著，从3.49%到11.46%，跨度达3.3倍；（2）绝对语义溢出量体现模型世界理解能力——nano_banana每图产生27.8处语义溢出，而qwen_2511虽控制更精准（16.3处），但语义溢出较少，揭示编辑控制与世界理解间的权衡；（3）空间衰减分析显示，溢出密度随距离指数下降，但语义相关溢出比例稳定在40%-58%，直接证明语义溢出反映真实世界理解，而非简单空间扩散。
原文摘要 · Abstract (English)
Instruction-following image editing models are expected to modify only the specified region while keeping the rest of the image unchanged. However, in practice, we observe a pervasive phenomenon -- edit spillover: models alter semantically related but unspecified content outside the edit region. This raises a fundamental question -- does spillover reflect genuine implicit world understanding, or is it merely attention leakage? We propose EditSpilloverProbe, a systematic framework that repurposes edit spillover as a natural probe for world knowledge in image editing models. We introduce a spillover taxonomy (spatial, semantic, mixed, random), an automated detection-and-classification pipeline, and a benchmark dataset constructed from real-world Chinese text editing tasks, EditSpilloverBench. Systematic evaluation of 5 representative editing models reveals three core findings: (1) spillover rates vary dramatically across architectures, from 3.49% to 11.46%, with a 3.3x ratio; (2) absolute semantic spillover quantity reveals models' world understanding capability -- nano_banana produces the most semantic spillover (27.8 per image), while qwen_2511 has the most precise editing control but lower semantic spillover (16.3 per image), revealing a trade-off between editing control and world understanding; (3) spatial decay analysis shows spillover area density decays exponentially with distance, but the proportion of semantically relevant spillover remains constant (40%-58%), providing direct evidence that semantic spillover reflects genuine world understanding rather than spatial diffusion.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。