MemeScouts@LT-EDI 2026：问对问题——针对弱监督的提示方法用于表情包仇恨言论检测
MemeScouts@LT-EDI 2026: Asking the Right Questions -- Prompted Weak Supervision for Meme Hate Speech Detection
AI总结：
本文提出一种提示弱监督方法，通过分解表情包理解为基于问题的标注函数，提升多语言多模态仇恨言论检测效果，尤其在中文和印地语中表现突出。
摘要：
检测表情包中的仇恨言论具有挑战性，因为其多模态性质和微妙、文化相关的线索，如讽刺和语境。尽管最近的视觉-语言模型（VLMs）能够联合推理文本和图像，但端到端提示可能脆弱，因为单个预测必须解决目标、立场、隐含性和讽刺。这些挑战在多语言环境下更加明显。我们提出了一种提示弱监督（PWS）方法，将表情包理解分解为针对特定问题的标注函数，具有受限制的答案选项，用于LT-EDI 2026共享任务中的同性恋恐惧和跨性别恐惧检测。使用量化后的Qwen3-VLM来通过回答特定问题提取特征，我们的方法在直接VLM分类上表现更优，尤其在中文和印地语中获得显著提升，英文排名第一，中文第二，印地语第三。通过错误驱动的LF扩展和特征剪枝进行迭代优化，减少冗余并提高泛化能力。我们的结果突显了提示弱监督在多语言多模态仇恨言论检测中的有效性。
英文摘要：
Detecting hate speech in memes is challenging due to their multimodal nature and subtle, culturally grounded cues such as sarcasm and context. While recent vision-language models (VLMs) enable joint reasoning over text and images, end-to-end prompting can be brittle, as a single prediction must resolve target, stance, implicitness, and irony. These challenges are amplified in multilingual settings. We propose a prompted weak supervision (PWS) approach that decomposes meme understanding into targeted, question-based labeling functions with constrained answer options for homophobia and transphobia detection in the LT-EDI 2026 shared task. Using a quantized Qwen3-VLM to extract features by answering targeted questions, our method outperforms direct VLM classification, with substantial gains for Chinese and Hindi, ranking 1st in English, 2nd in Chinese, and 3rd in Hindi. Iterative refinement via error-driven LF expansion and feature pruning reduces redundancy and improves generalization. Our results highlight the effectiveness of prompted weak supervision for multilingual multimodal hate speech detection.
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。
