IRON-Meme: A Benchmark for Structured Understanding of Identities and Roles in Online Meme Narratives

Title: IRON-Meme: A Benchmark for Structured Understanding of Identities and Roles in Online Meme Narratives

标题：IRON-Meme：一个用于结构化理解在线模因叙事中身份与角色的基准

Computer Science > Artificial Intelligence arXiv:2610.33097 (cs) [Submitted on 22 Oct 2026] Title: IRON-Meme: A Benchmark for Structured Understanding of Identities and Roles in Online Meme Narratives Authors: Gabriella Bollici, Stefano De Giorgis, Wouter Van Atteveldt, Filip Ilievski

计算机科学 > 人工智能 arXiv:2610.33097 (cs) [提交于 2026 年 10 月 22 日] 标题：IRON-Meme：一个用于结构化理解在线模因叙事中身份与角色的基准 作者：Gabriella Bollici, Stefano De Giorgis, Wouter Van Atteveldt, Filip Ilievski

Abstract: As polarization grows on social media, understanding how political memes shape online narratives has become increasingly important. Previous research has relied on either qualitative frameworks that are hard to scale or computational methods that lack theoretical grounding. Both approaches treat narrative categories in isolation and focus exclusively on moral portrayals of identity.

摘要：随着社交媒体上两极分化的加剧，理解政治模因如何塑造在线叙事变得愈发重要。先前的研究要么依赖难以扩展的定性框架，要么依赖缺乏理论基础的计算方法。这两种方法都将叙事类别孤立对待，且仅关注身份的道德刻画。

To address these limitations, we introduce a framework grounded in social science theories, encompassing three categories: social identities (such as gender, politics, and ethnicity), viewpoints (ingroup and outgroup perspectives), and narrative roles (moral character, intelligence, status, and power). Building on this framework, we present IRON-Meme, a human-annotated benchmark comprising 1,110 political memes across substantially more templates than existing benchmarks.

为了解决这些局限性，我们引入了一个基于社会科学理论的框架，涵盖三个类别：社会身份（如性别、政治和种族）、观点（内群体和外群体视角）以及叙事角色（道德品质、智力、地位和权力）。基于此框架，我们提出了 IRON-Meme，这是一个由人工标注的基准，包含 1,110 个政治模因，其涵盖的模板数量远超现有基准。

Our analysis of IRON-Meme shows that most memes assign derogatory roles and that identities, roles, and templates are systematically interconnected. Evaluation of nine vision-language models indicates that frontier-scale and reasoning models achieve the highest performance, while accuracy on social identities and narrative roles decreases for less frequent labels.

我们对 IRON-Meme 的分析表明，大多数模因分配了贬义角色，且身份、角色和模板之间存在系统性的相互关联。对九种视觉语言模型的评估显示，前沿规模模型和推理模型表现最佳，而对于出现频率较低的标签，社会身份和叙事角色的准确率则有所下降。

Incorporating template background knowledge does not enhance narrative role classification, suggesting that meme interpretation relies on how memes are adapted for specific communicative purposes. We make IRON-Meme and our code publicly available.

整合模板背景知识并不能增强叙事角色分类的效果，这表明模因的解读依赖于模因为特定交流目的所做的调整方式。我们将 IRON-Meme 和我们的代码公开。