EXIST 2026上的AI巫师：用于模因中多模态性别歧视识别的层次化软标签学习

AI Wizards at EXIST 2026: Hierarchical Soft-Label Learning for Multimodal Sexism Identification in Memes

July 5, 2026

作者: Matteo Fasulo, Antonio Gravina, Luca Tedeschini, Luca Babboni

cs.AI

摘要

我们提出AI魔法师团队在EXIST 2026多模态梗图性别歧视识别任务中的提交方案。该任务包含三个难度递增的子任务。我们将其建模为基于经验标注者分布的条件软标签预测层级结构。系统通过轻量级门控多层感知机（Gated MLP）映射固定的Gemini Embedding 2.0视觉-语言表示，该感知机采用KL散度和同方差不确定性加权进行训练。我们的提交在官方Soft-Soft排行榜上，任务2.3排名第一，任务2.1和2.2排名第四。代码已开源至https://github.com/NLP-AI-Wizards/EXIST-2026。

English

We present the AI Wizards submission to EXIST 2026 for multimodal sexism identification in memes. The task is composed of three, increasingly harder subtasks. We model them hierarchically as conditional soft-label prediction over empirical annotator distributions. Our system maps fixed Gemini Embedding 2 vision-language representations through a lightweight Gated MLP trained with KL divergence and homoscedastic uncertainty weighting. Our submissions ranked first on Task 2.3 and fourth on Tasks 2.1 and 2.2 on the official Soft-Soft leaderboards. The code is available at https://github.com/NLP-AI-Wizards/EXIST-2026