阿拉伯语大模型方言引导研究：稀疏神经元与分布式方向的作用

Computer Science > Computation and Language arXiv:2607.03936 (cs) [Submitted on 4 Jul 2026 (v1), last revised 6 Sep 2026 (this version, v3)] Title:Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs Authors:Kareem Elozeiri, Mervat Abassy, Omar Kallas, Fahim Dalvi, Preslav Nakov, Kentaro Inui, Nadir Durrani View a PDF of the paper titled Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs, by Kareem Elozeiri and 6 other authors View PDF HTML (experimental) Abstract:Dialectal data are scarce relative to Modern Standard Arabic (MSA), causing Arabic LLMs to overproduce MSA and struggle with dialectally accurate generation. This raises a fundamental interpretability question about where and how dialectal features are encoded within model internals and whether these representations can improve dialect generation without fine-tuning. We study two inference-time approaches as interpretability probes and control mechanisms. First, neuron-level analysis identifies sparse populations that encode dialect-specific features and tests whether amplifying or suppressing them steers model outputs toward target dialects. Second, vector steering extracts dialect-specific activation directions and injects them during inference, motivated by feature entanglement at the neuron level. We find that these neurons are real but only partially explanatory. They occupy under 1\% of MLP dimensions but span only 5\% to 21\% of the residual dialect direction. This limited coverage is causally consequential. Neuron steering reinforces dialect in some varieties when the prompt is already dialectal but cannot induce it from MSA prompts, whereas vector steering succeeds in both settings. Arabic dialects are therefore steerable mainly through distributed rather than localized representations Subjects: Computation and Language (cs.CL) Cite as: arXiv:2607.03936 [cs.CL] (or arXiv:2607.03936v3 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2607.03936 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Kareem Elozeiri [view email] [v1] Sat, 4 Jul 2026 16:04:44 UTC (2,779 KB) [v2] Thu, 3 Sep 2026 07:16:21 UTC (1,221 KB) [v3] Sun, 6 Sep 2026 15:39:09 UTC (1,220 KB) Full-text links: Access Paper: View a PDF of the paper titled Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs, by Kareem Elozeiri and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2026-07 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)