{"slug": "informational-antilocality-and-the-locality-bias-in-llms", "title": "Informational Antilocality and the Locality Bias in LLMs", "summary": "A study submitted to arXiv on 27 Aug 2026 found that transformer-based language models (LLMs) achieve comparable cross-entropy loss on k-antilocal languages regardless of antilocality, but converge more slowly on more antilocal languages, supporting the idea that non-local dependencies are harder to learn, with evidence from learning speed rather than learning success.", "body_md": "# Computer Science > Computation and Language\n\n[Submitted on 27 Aug 2026]\n\n# Title:Informational Antilocality and the Locality Bias in LLMs\n\n[View PDF](/pdf/2608.27760)\n\n[HTML (experimental)](https://arxiv.org/html/2608.27760v1)\n\nAbstract:We consider the ability of transformer-based language models (LLMs) to learn what we call k-antilocal languages, i.e., languages that have no mutual information across any span of $k$ contiguous symbols. We construct such languages with increasing $k$, finding that LLMs trained on them achieve comparable cross-entropy loss regardless of antilocality, but converge more slowly on more antilocal languages. Our findings support the idea that non-local dependencies are more difficult to learn, but the evidence for this bias comes from learning speed rather than learning success.\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/informational-antilocality-and-the-locality-bias-in-llms", "canonical_source": "https://arxiv.org/abs/2608.27760", "published_at": "2026-08-31 04:00:00+00:00", "updated_at": "2026-08-31 04:24:33.721475+00:00", "lang": "en", "topics": ["large-language-models", "ai-research"], "entities": ["arXiv"], "alternates": {"html": "https://wpnews.pro/news/informational-antilocality-and-the-locality-bias-in-llms", "markdown": "https://wpnews.pro/news/informational-antilocality-and-the-locality-bias-in-llms.md", "text": "https://wpnews.pro/news/informational-antilocality-and-the-locality-bias-in-llms.txt", "jsonld": "https://wpnews.pro/news/informational-antilocality-and-the-locality-bias-in-llms.jsonld"}}