文本轉圖像模型是否為歸納主義的火雞？一個用於因果推理的反事實基準

摘要

文字生成图像（T2I）模型在根据自然语言提示生成视觉逼真图像方面取得了显著进展。然而，尚不清楚它们的成功究竟是反映了真正的因果理解，还是对视觉-文本关联的复杂模式匹配。受罗素归纳火鸡的启发，我们提出了反事实世界（CF-World），这是一个反事实基准，旨在探究文本生成图像模型是否能在系统性地违背现实世界先验的规则下生成图像。CF-World 将每个场景组织为三个递进层次：基于普通世界知识的事实生成、带有直接视觉指令的显式反事实生成，以及需要从改变的规则中进行因果推理的隐式反事实生成。我们使用基于视觉语言模型（VLM）的评估器（CF-Eval）评估了开源和闭源 T2I 模型。此外，我们引入了两个指标：先验抵抗率（PRR），用于衡量模型克服根深蒂固的现实世界先验的能力；以及推理保持率（RRR），用于评估模型在缺乏明确视觉提示的情况下，是否能够维持依赖推理的反事实生成。实验表明，所有模型从事实场景到反事实场景均表现出显著性能下降。进一步分析表明，这些失败源于当前的 T2I 模型将世界知识与视觉外观编码为紧密耦合的模式。因此，当被要求生成反事实世界时，它们严重依赖训练数据中频繁出现的视觉共现现象，从而不得不默认采用熟悉的常识先验。

English

Text-to-image (T2I) generation models have achieved remarkable progress in producing visually realistic images from natural language prompts. Yet it remains unclear whether their success reflects genuine causal understanding or sophisticated pattern matching over visual-textual correlations. Inspired by Russell's inductivist turkey, we introduce Counterfactual-World (CF-World), a counterfactual benchmark designed to investigate whether text-to-image models can generate images under rules that systematically contradict real-world priors. CF-World organizes each scenario into three progressive levels: factual generation under ordinary world knowledge, explicit counterfactual generation with direct visual instructions, and implicit counterfactual generation requiring causal deduction from altered rules. We evaluate both open-source and closed-source T2I models using a Vision Language Model (VLM)-based evaluator (CF-Eval). Furthermore, we introduce two metrics: Prior Resistance Rate (PRR), which measures a model's ability to overcome entrenched real-world priors, and Reasoning Retention Rate (RRR), which assesses whether models can maintain reasoning-dependent counterfactual generation without explicit visual cues. Experiments show that all models exhibit sharp degradation from factual to counterfactual settings. Further analyses suggest that these failures arise because current T2I models encode world knowledge and visual appearances as tightly coupled patterns. Consequently, their heavy reliance on frequent visual co-occurrences within the training data forces them to default to familiar commonsense priors when tasked with rendering counterfactual worlds.