{"slug": "disentangling-linguistic-relatedness-from-task-alignment-in-cross-lingual", "title": "Disentangling Linguistic Relatedness from Task Alignment in Cross-Lingual Transfer", "summary": "A study fine-tuning seven large language models on Arabic found no evidence of Semitic-specific cross-lingual transfer; gains were driven by task-format alignment rather than linguistic relatedness.", "body_md": "# Computer Science > Computation and Language\n\n[Submitted on 26 Apr 2026]\n\n# Title:Disentangling Linguistic Relatedness from Task Alignment in Cross-Lingual Transfer\n\n[View PDF](/pdf/2606.19346)\n\n[HTML (experimental)](https://arxiv.org/html/2606.19346v1)\n\nAbstract:We study cross-lingual transfer by fine-tuning seven large language models (4B--671B parameters) on Arabic and evaluating zero-shot reading comprehension on Semitic languages and non-Semitic controls. Across dense and Mixture-of-Experts architectures, we find no evidence of Semitic-specific transfer: models with weak baselines improve dramatically across all languages, while strong-baseline models show only marginal gains regardless of language family. A chain-of-thought ablation reinforces this finding -- the same models that benefit most from fine-tuning benefit equally from inference-time reasoning, suggesting both mechanisms address task-format alignment rather than cross-lingual knowledge transfer.\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/disentangling-linguistic-relatedness-from-task-alignment-in-cross-lingual", "canonical_source": "https://arxiv.org/abs/2606.19346", "published_at": "2026-06-19 04:00:00+00:00", "updated_at": "2026-06-19 04:04:40.043358+00:00", "lang": "en", "topics": ["large-language-models", "natural-language-processing", "ai-research"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/disentangling-linguistic-relatedness-from-task-alignment-in-cross-lingual", "markdown": "https://wpnews.pro/news/disentangling-linguistic-relatedness-from-task-alignment-in-cross-lingual.md", "text": "https://wpnews.pro/news/disentangling-linguistic-relatedness-from-task-alignment-in-cross-lingual.txt", "jsonld": "https://wpnews.pro/news/disentangling-linguistic-relatedness-from-task-alignment-in-cross-lingual.jsonld"}}