{"slug": "generalizing-llms-to-plts-probabilistic-language-tries", "title": "Generalizing LLMs to PLTs: Probabilistic Language Tries", "summary": "Researchers introduced probabilistic language tries (PLTs), a unified framework that represents prefix structures from generative models, enabling optimal lossless compression, policy representation for decision-making, and memoization for inference reuse. The framework includes a prior-guided caching theorem that reduces transformer attention costs from O(n^2) to expected O(log N) under reuse, demonstrated across chess, web search, robotics, and LLM inference.", "body_md": "# Computer Science > Machine Learning\n\n[Submitted on 29 Mar 2026]\n\n# Title:Probabilistic Language Tries: A Unified Framework for Compression, Decision Policies, and Execution Reuse\n\n[View PDF](/pdf/2604.06228)\n\n[HTML (experimental)](https://arxiv.org/html/2604.06228v1)\n\nAbstract:We introduce probabilistic language tries (PLTs), a unified representation that makes explicit the prefix structure implicitly defined by any generative model over sequences. By assigning to each outgoing edge the conditional probability of the corresponding token or action, a PLT simultaneously serves as: (i) an optimal lossless compressor via frequency-weighted interval encoding, generalizing arithmetic coding to model-conditioned distributions; (ii) a policy representation for sequential decision problems including games, search, and robotic control; and (iii) a memoization index that lets repeated inference queries be answered by structured retrieval rather than full model execution.\n\nThe central technical result is a prior-guided caching theorem: under a stationary generative distribution, a PLT-guided cache achieves strictly lower expected inference cost than any empirical-frequency cache for all query counts below a threshold that grows with the concentration of the prior. This converts O(n^2) transformer attention cost into an expected cost of p_r * O(log N) + (1 - p_r) * O(n^2), where p_r is the prior-estimated reuse probability and N is the artifact store size.\n\nWe further introduce a hybrid compression architecture decomposing any dataset into a PLT-covered majority and a sparse residual store, connecting arithmetic coding with Kolmogorov-style program representations and rate-distortion theory. We instantiate the framework across chess, web search, robotics, organizational workflows, and LLM inference, demonstrating that compression, decision making, and computational reuse are all derived from a single probability measure on sequence space.\n\n### Current browse context:\n\ncs.LG\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))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))# 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/generalizing-llms-to-plts-probabilistic-language-tries", "canonical_source": "https://arxiv.org/abs/2604.06228", "published_at": "2026-07-10 16:07:47+00:00", "updated_at": "2026-07-10 16:35:22.506130+00:00", "lang": "en", "topics": ["machine-learning", "large-language-models", "ai-research", "artificial-intelligence"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/generalizing-llms-to-plts-probabilistic-language-tries", "markdown": "https://wpnews.pro/news/generalizing-llms-to-plts-probabilistic-language-tries.md", "text": "https://wpnews.pro/news/generalizing-llms-to-plts-probabilistic-language-tries.txt", "jsonld": "https://wpnews.pro/news/generalizing-llms-to-plts-probabilistic-language-tries.jsonld"}}