As AI models grow more complex, explainability is essential for building trust, yet concept-based counterfactual methods still face a trade-off between expressivity and efficiency. Representing underlying concepts as atomic sets is fast but misses relational context, whereas full graph representations are more faithful but require solving the NP-hard Graph Edit Distance (GED) problem. We propose U-CECE, a unified, model-agnostic multi-resolution framework for conceptual counterfactual explanations that adapts to data regime and compute budget. U-CECE spans three levels of expressivity: atomic concepts for broad explanations, relational sets-of-sets for simple interactions, and structural graphs for full semantic structure. At the structural level, both a precision-oriented transductive mode based on supervised Graph Neural Networks (GNNs) and a scalable inductive mode based on unsupervised graph autoencoders (GAEs) are supported. Experiments on the structurally divergent CUB and Visual Genome datasets characterize the efficiency-expressivity trade-off across levels, while human surveys and LVLM-based evaluation show that the retrieved structural counterfactuals are semantically equivalent to, and often preferred over, exact GED-based ground-truth explanations.

翻译：随着AI模型日趋复杂，可解释性对于建立信任至关重要，但基于概念的反事实方法仍面临表达能力与效率之间的权衡。将底层概念表示为原子集合虽然快速，却缺乏关系上下文；而完整的图表示虽更忠实，却需要解决NP难的图编辑距离问题。我们提出U-CECE——一个统一且模型无关的多分辨率概念反事实解释框架，可根据数据规模和计算预算自适应调整。U-CECE覆盖三个表达能力层级：用于宽泛解释的原子概念、用于简单交互的关系集合之集合，以及用于完整语义结构的结构化图。在结构层级上，我们同时支持基于监督图神经网络的精确导向转导模式与基于无监督图自编码器的可扩展归纳模式。在结构不同的CUB与Visual Genome数据集上的实验刻画了各层级间的效率-表达能力权衡，而人工调查与基于LVLM的评估表明，所检索的结构化反事实在语义上等价于、甚至常常优于基于精确GED的基准解释。