arXiv cs.CL· Ahmed M. Fetouh, Mariam Labib, Nsrin Ashraf, Omer Dawood, Hamada Nayel·· 13 小时前AI 评分22
REGLAT 在 ArGuard 共享任务：融合 NER 的集成模型用于阿拉伯语有害内容检测
REGLAT at ArGuard Shared Tasks: An Ensemble-Based Model Integrating NER for Harmful Content Detection in Arabic
AI 导读
REGLAT 团队提出两阶段方法，先用 GLiNER 抽取提示词中的有害实体并拼回原文，再交由微调的 MARBERT 分类器将阿拉伯语用户提示词分为七类有害内容。
正文 · 原文
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.
| Comments: | System description paper for REGLAT submission for ArGuard shared task 2026 |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.37265 [cs.CL] |
| (or arXiv:2610.37265v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37265 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hamada Nayel [view email]
[v1]
Tue, 27 Oct 2026 13:59:11 UTC (1,917 KB)
来源：arXiv cs.CL · arxiv.org