发表机构
University of Luxembourg; University of Alicante（卢森堡大学; 阿利坎特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究通过批判性综述指出当前阿拉伯语NLP的XAI存在方法、任务、语言学三方面差距，提出涵盖多维度的分类体系并给出基于语言学的阿拉伯语XAI研究议程。
AI 中文摘要
可解释人工智能（XAI）目前是自然语言处理（NLP）领域的核心主题，但阿拉伯语NLP在三个相互关联的层面仍缺乏充分的可解释性。首先存在方法差距：阿拉伯语XAI过度依赖LIME、SHAP、注意力可视化、显著性等少量事后解释技术，而通用NLP XAI提供了更丰富的诊断、反事实、探测、基于理由及以人为中心的方法。其次存在任务差距：现有阿拉伯语XAI研究集中于分类任务，尤其是情感分析、仇恨/冒犯性语言检测、假新闻与垃圾邮件检测，对生成、检索、翻译、摘要、结构化预测及对话任务的覆盖较弱。第三存在语言学差距：许多解释仅识别有影响力的词元，却极少解释阿拉伯语特有的现象，如形态学、附着语素、方言变异、双言现象、正字法歧义、元音符号、语码转换、命名实体、文化参考或古典语及宗教语域。本结构化批判性综述综合了文本、语音及多模态场景下阿拉伯语XAI的相关文献，认为阿拉伯语NLP不仅需要对模型决策的解释，还需要符合阿拉伯语作为语言、文化及社会技术对象本质的解释。我们引入了涵盖任务、方法、语言单位、变体、目标及评估实践的分类体系，并提出了基于语言学的阿拉伯语XAI研究议程。
英文摘要
Explainable AI (XAI) is now a major theme in NLP; however, Arabic NLP remains under-explained in three connected senses. First, there is a method gap: Arabic XAI relies heavily on a small set of post-hoc techniques such as LIME, SHAP, attention visualization, and saliency, while broader NLP XAI offers richer diagnostic, counterfactual, probing, rationale-based, and human-centered methods. Second, there is a task gap: existing Arabic XAI work is concentrated in classification tasks, especially sentiment analysis, hate/offensive language detection, fake news, and spam, with weaker coverage of generation, retrieval, translation, summarization, structured prediction, and dialogue. Third, there is a linguistic gap: many explanations identify influential tokens, but rarely explain Arabic-specific phenomena such as morphology, clitics, dialectal variation, diglossia, orthographic ambiguity, diacritics, code-switching, named entities, cultural references, or Classical and religious registers. This critical structured survey synthesizes the reviewed literature on Arabic XAI across text, speech, and multimodal settings. We argue that Arabic NLP does not only need explanations of model decisions; it needs explanations that are faithful to Arabic as a linguistic, cultural, and sociotechnical object. We introduce a taxonomy of tasks, methods, linguistic units, varieties, goals, and evaluation practices, and propose a research agenda for linguistically grounded Arabic XAI.
Comments11 pages
