视觉-语言模型理解视觉说服力吗？
Do Vision-Language Models Understand Visual Persuasiveness? A Diagnosis via Visual Persuasive Factors
AI总结：
本文研究视觉-语言模型对视觉说服力的理解，发现模型在链接说服对象与沟通意图方面存在局限。
摘要：
近年来，视觉-语言模型（VLMs）的进步使多模态推理和理解变得令人印象深刻。然而，这些模型是否真正理解视觉说服力——即视觉线索如何塑造人类态度和决策——仍不清楚。为了探讨这个问题，我们构建了一个高共识数据集，用于二元说服力判断，并引入了视觉说服因素（VPFs）的分类，涵盖低级感知、中级组成和高级语义线索。我们还探索了认知引导和知识注入策略，用于与说服相关的推理。跨VLMs的实证分析揭示了记忆导向偏差——模型过度预测高说服力——以及低/中级特征的弱判别能力。相反，信息与对象存在之间的高级语义对齐成为人类判断最强的预测因素。在干预策略中，简单的指令或无指导的推理支架产生边际或负面影响，而简洁、基于对象的推理理由显著提高了精度和F1分数。这些结果表明，VLMs的核心限制不在于识别说服性对象，而在于将它们与沟通意图联系起来。
英文摘要：
Visual persuasion uses images to shape cognition, emotion, and behavior, with its effects depending on both visual attributes and semantic context. Despite recent progress, it remains unclear whether Vision-Language Models (VLMs) understand visual persuasiveness. This motivates us to ask: can VLMs assess whether an image persuasively supports an intended message, which visual factors shape this judgment, and do they align with human judgments? Through empirical analyses on image-message pairs where human raters consistently agree on the persuasiveness judgment, we show that VLMs exhibit a recall-oriented bias: they over-predict images as persuasive while achieving high recall. We introduce Visual Persuasive Factors (VPFs), a taxonomy informed by cognitive psychology for quantifying visual cues that shape persuasive judgments. Our factor-level analysis reveals that VPFs distinguish human persuasiveness judgments, whereas VLMs only partially reproduce these patterns, often generating false positives by treating persuasion-relevant cues as sufficient evidence. Building on this insight, we evaluate VPF-guided interventions and find that properly framed VPF knowledge can improve performance, but merely specifying visual cues or adding step-by-step reasoning is insufficient. By analyzing model rationales at the level of functional reasoning steps, we further identify a central bottleneck in connecting object identification to semantic message alignment.
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。
