评估视觉文本生成中的推理保真度
Evaluating Reasoning Fidelity in Visual Text Generation
AI总结：
通过长文本渲染、事实知识探测、上下文理解和多步推理等任务，评估当前文本到图像模型在视觉文本生成中是否忠实保持推理能力，发现其常产生语义错误和逻辑不一致，与纯文本模型存在显著差距。
摘要：
最近的文本到图像（T2I）模型能够在图像中渲染高度清晰且结构良好的文本，从而支持文档生成和幻灯片生成等应用。然而，当复杂解决方案必须直接通过渲染文本表达时，这些系统是否忠实地保留了推理能力，还是仅仅模仿表面模式，目前尚不清楚。我们通过评估视觉文本生成中的推理保真度来研究这一问题，其中模型必须将完整的推理过程表达为图像。我们的评估包括长文本渲染、事实知识探测、上下文理解和多步推理。在这些设置中，我们发现当前的T2I模型经常产生语义错误、逻辑不一致和错误的中间步骤，即使渲染的文本在视觉上清晰。这些失败与纯文本模型在相同任务上的强推理表现形成对比。我们的发现揭示了视觉文本生成与程序性推理之间的显著差距，促使更可靠的视觉文本推理。
英文摘要：
Recent text-to-image (T2I) models can render highly legible and well-structured text within images, enabling applications including document generation and slide generation. However, it remains unclear whether such systems faithfully preserve reasoning ability when complex solutions must be expressed directly through rendered text, or whether they merely imitate surface-level patterns. We investigate this question by evaluating reasoning fidelity in visual text generation, where models must express complete reasoning processes as images. Our evaluation includes long text rendering, factual knowledge probing, context understanding, and multi-step reasoning. Across these settings, we find that current T2I models frequently produce semantic errors, logical inconsistencies, and incorrect intermediate steps, even when the rendered text appears visually clear. These failures contrast with the strong reasoning performance of text-only models on the same tasks. Our findings reveal a substantial gap between visual text generation and procedural reasoning, motivating more reliable visual text reasoning.
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。
