arXiv cs.CL· Abdu Sallouh, Nicholas Popovi\v{c}, Michael F\"{a}rber·· 9 天前AI 评分22
现代标准阿拉伯语（MSA）在 LLM 中主导阿拉伯方言吗？一项表征层分析
Does Modern Standard Arabic (MSA) Dominate Arabic Dialects in LLMs? A Representation-Level Analysis
AI 导读
研究将语言主导性框架扩展到 26 种阿拉伯语变体，发现没有证据表明现代标准阿拉伯语（MSA）在 LLM 内部表征中主导阿拉伯方言。方言表征形成高度重叠的密集空间，归一化互信息相比差异较大的语言明显下降，且最强可分性效应并不局限于中间层，会随架构向更后层偏移。研究认为，MSA 偏置的生成输出并不必然反映内部表征主导，多语言与方言 LLM 分析应区分生成偏置与内部表征几何。
正文 · 原文
Abstract:Large language models (LLMs) often default to Modern Standard Arabic (MSA) when generating Arabic, even when prompted with dialectal Arabic. A natural explanation is that their internal representations are dominated by MSA. We test this hypothesis by adapting the language-dominance framework of Shani and Basirat (2025) (this https URL) to 26 Arabic varieties. Across layers and model families, we find no evidence that MSA acts as a dominant internal representation for Arabic dialects. Instead, dialect representations form a dense and highly overlapping space: normalized mutual information drops sharply compared to patterns reported for more distinct languages. Moreover, the strongest separability effects are not confined to intermediate layers, but can shift toward later layers depending on the architecture. These findings challenge a common interpretation of MSA-biased generation: output preference does not necessarily reveal internal representational dominance. Analyses of multilingual and dialectal LLMs should therefore distinguish generation bias from the geometry of internal representations.
| Comments: | EMNLP 2026 |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.11510 [cs.CL] |
| (or arXiv:2610.11510v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11510 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Nicholas Popovič [view email]
[v1]
Thu, 8 Oct 2026 08:46:47 UTC (6,947 KB)
来源：arXiv cs.CL · arxiv.org