{"ID":5937747,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-08T16:57:24.029979796Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04410","arxiv_id":"2607.04410","title":"AI Wizards at EXIST 2026: Hierarchical Soft-Label Learning for Multimodal Sexism Identification in Memes","abstract":"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","short_abstract":"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-languag...","url_abs":"https://arxiv.org/abs/2607.04410","url_pdf":"https://arxiv.org/pdf/2607.04410v1","authors":"[\"Matteo Fasulo\",\"Antonio Gravina\",\"Luca Tedeschini\",\"Luca Babboni\"]","published":"2026-07-05T17:03:08Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[]","has_code":false,"code_links":[{"ID":613983,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T03:14:33.014478982Z","DeletedAt":null,"paper_id":5937747,"paper_url":"https://arxiv.org/abs/2607.04410","paper_title":"AI Wizards at EXIST 2026: Hierarchical Soft-Label Learning for Multimodal Sexism Identification in Memes","repo_url":"https://github.com/NLP-AI-Wizards/EXIST-2026","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}