REGLAT 在 ArGuard 共享任务中的方法：集成 NER 的阿拉伯语有害内容检测模型
摘要
该论文提出一种两阶段方法用于ArGuard 2026共享任务中的阿拉伯语有害内容检测：先用GLiNER提取有害相关实体，再将实体与原始文本输入微调后的MARBERT进行分类，在开发集上取得0.886的macro-F1分数。
arXiv:2610.37265v1 Announce Type: new
Abstract: Detecting harmful content in Arabic is challenging because of dialectal variations and the semantic overlap between different harm categories. This paper presents a two-stage approach for classifying Arabic user prompts into seven categories of harmful content. First, GLiNER is used to extract harm-related entities from each prompt. The extracted entities are then added to the original text and passed to a fine-tuned MARBERT classifier for final classification. The approach combines explicit entity information with the contextual understanding of a pretrained Arabic language model. The system was evaluated on the development set of the ArGuard 2026 shared task. The results achieved a macro-F1 score of 0.886 and an accuracy of 0.897, demonstrating promising performance in fine-grained harmful content detection. The system reported an accuracy of 0.793 and Macro-F score of 0.735 on a blind test set for subtask 1. For subtask 2, it achieved an accuracy of 0.770 and Macro-F score of 0.754. The analysis also showed that distinguishing between related categories remains challenging. These findings suggest that integrating NER with Arabic language models is a promising approach to harmful content detection.
查看缓存全文
缓存时间: 2026/10/28 08:19
# REGLAT at ArGuard Shared Tasks: An Ensemble-Based Model Integrating NER for Harmful Content Detection in Arabic Source: [https://arxiv.org/abs/2610.37265](https://arxiv.org/abs/2610.37265) [View PDF](https://arxiv.org/pdf/2610.37265)[HTML \(experimental\)](https://arxiv.org/html/2610.37265v1) > Abstract:Detecting harmful content in Arabic is challenging because of dialectal variations and the semantic overlap between different harm categories\. This paper presents a two\-stage approach for classifying Arabic user prompts into seven categories of harmful content\. First, GLiNER is used to extract harm\-related entities from each prompt\. The extracted entities are then added to the original text and passed to a fine\-tuned MARBERT classifier for final classification\. The approach combines explicit entity information with the contextual understanding of a pretrained Arabic language model\. The system was evaluated on the development set of the ArGuard 2026 shared task\. The results achieved a macro\-F1 score of 0\.886 and an accuracy of 0\.897, demonstrating promising performance in fine\-grained harmful content detection\. The system reported an accuracy of 0\.793 and Macro\-F score of 0\.735 on a blind test set for subtask 1\. For subtask 2, it achieved an accuracy of 0\.770 and Macro\-F score of 0\.754\. The analysis also showed that distinguishing between related categories remains challenging\. These findings suggest that integrating NER with Arabic language models is a promising approach to harmful content detection\. ## Submission history From: Hamada Nayel \[[view email](https://arxiv.org/show-email/72ddab2a/2610.37265)\] **\[v1\]**Tue, 27 Oct 2026 13:59:11 UTC \(1,917 KB\)
相似文章
SZED 在 ArGuard 共享任务中的方案：面向阿拉伯语仇恨表情包检测的多任务标签注意力与跨模态融合
SZED 在 ArGuard 2026 Track A 提交的方案，融合 MARBERTv2 与 CLIP ViT-L/14 嵌入做二分类，并用多任务标签注意力与级联校准处理细粒度多标签标注，二分类 macro-F1 达 0.7597。论文还报告了跨模态注意力与图文不一致特征未带来提升的负结果。
ArGuard 共享任务：阿拉伯语模因与 LLM 提示中的有害内容检测
ArGuard 是一个专注于检测阿拉伯语模因与 LLM 提示中有害内容的共享任务，突出了细粒度分类中的挑战，并发布数据集以供进一步研究。
AK_QMUL 参加 ArGuard 共享任务：使用单一微调 JAIS 模型检测阿拉伯语有害提示词
AK_QMUL 的论文介绍了其在 ArGuard-2026 共享任务中的提交方案：基于 JAIS-6.7B、采用 4 位 QLoRA 微调的模型，用于阿拉伯语有害提示检测（安全/不安全二分类及七类有害领域分类）。该模型在两项任务中均获第一名，宏平均 F1 分数分别为 0.984 和 0.790。
Nurnberg NLP @ GermEval Shared Task 2026: 通过错误独立LLM投票器在德语社交媒体中检测有害内容
本文提出了一种使用错误独立LLM的九投票器集成系统，用于德语社交媒体中的有害内容检测，通过解决类别不平衡问题，在GermEval 2026共享任务的四个子任务中获得第一名。
TTLab 在 AlexandriaX-2026：一个用于阿拉伯语机器翻译错误片段检测与分类的微调表层标签器
TTLab 展示了一个用于阿拉伯语机器翻译错误片段检测与分类的微调表层标签器，使用 MARBERTv2 在 AlexandriaX-2026 共享任务中获得了第三名。