用大模型分析阿拉伯语文本和表情包中的希望、仇恨与情绪，提升内容审核精度。
Detecting Hope, Hate, and Emotion in Arabic Textual Speech and Multi-modal Memes Using Large Language Models
- 采用微调的大模型处理阿拉伯语文本与表情包，结合多模态信息进行情感识别。
- GPT-4o-mini 和 Gemini Flash 2.5 分别在三类任务中取得最高 72.1%、57.8%、79.6% 的宏平均 F1。
- 解决方案在 MAHED 2025 挑战赛中获第一名，适合阿拉伯语内容安全治理场景。
社交媒体和在线交流平台的兴起推动了阿拉伯语文本和表情包作为主要数字表达形式的发展。尽管这些内容可能具有幽默性和信息性，但也越来越多被用于传播攻击性语言和仇恨言论。因此，对阿拉伯语文本和表情包内容进行精准分析的需求日益增长。本文探索大型语言模型在识别此类内容中希望、仇恨言论、攻击性语言及情绪表达方面的潜力。我们评估了基础 LLM、微调后的 LLM 以及预训练嵌入模型的表现，使用的是阿拉伯NLP MAHED 2025 挑战赛提出的阿拉伯语文本与表情包数据集。结果表明，经阿拉伯语文本微调的 GPT-4o-mini 以及经阿拉伯语表情包微调的 Gemini Flash 2.5 表现最优，在任务1、2、3上分别达到 72.1%、57.8% 和 79.6% 的宏平均 F1 分数，并在该挑战赛中获得总体第一。所提方案为文本与表情包提供了更细致的理解，有助于构建高效准确的阿拉伯语内容审核系统。
原文摘要 · Abstract (English)
The rise of social media and online communication platforms has led to the spread of Arabic textual posts and memes as a key form of digital expression. While these contents can be humorous and informative, they are also increasingly being used to spread offensive language and hate speech. Consequently, there is a growing demand for precise analysis of content in Arabic text and memes. This paper explores the potential of large language models to effectively identify hope, hate speech, offensive language, and emotional expressions within such content. We evaluate the performance of base LLMs, fine-tuned LLMs, and pre-trained embedding models. The evaluation is conducted using a dataset of Arabic textual speech and memes proposed in the ArabicNLP MAHED 2025 challenge. The results underscore the capacity of LLMs such as GPT-4o-mini, fine-tuned with Arabic textual speech, and Gemini Flash 2.5, fine-tuned with Arabic memes, to deliver the superior performance. They achieve up to 72.1%, 57.8%, and 79.6% macro F1 scores for tasks 1, 2, and 3, respectively, and secure first place overall in the Mahed 2025 challenge. The proposed solutions offer a more nuanced understanding of both text and memes for accurate and efficient Arabic content moderation systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。