[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-515832-105":59,"doc-detail-515832-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","on-the-intuitionistic-logic-of-next-token-prediction","On the (Intuitionistic) Logic of Next-Token Prediction","","Explores how next-token prediction in autoregressive generative neural networks can be grounded in intuitionistic implicational logic. Establishes a proof-theoretic correspondence where predicting a token equates to modus ponens and sequence processing becomes constructive proof extension under the Curry–Howard correspondence. Presents Prolog-based theorem provers to validate core properties, including commutative vs. non-commutative sequencing and single- vs. multi-token prediction variants. Derives an Arrow Language Model that replaces attention with non-commutative operator composition, situating it relative to transformers, state-space models, and recursive LLMs.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/on-the-intuitionistic-logic-of-next-token-prediction/515832/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/on-the-intuitionistic-logic-of-next-token-prediction/515832.png","ImageObject",300,407,{"name":92,"@type":93},"SundayMiles","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-16","2026-10-06",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"How does the paper relate next-token prediction to modus ponens in intuitionistic logic?","Question",{"text":112,"@type":113},"It states that in its framework next-token prediction corresponds to modus ponens, turning sequence processing into constructive proof extension under the Curry–Howard correspondence.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What role do the Prolog-based theorem provers play?",{"text":117,"@type":113},"They validate fundamental properties of the neural models, including relationships between commutative vs. non-commutative sequencing and choices for single-token vs. multi-token prediction.",{"name":119,"@type":110,"acceptedAnswer":120},"What is the Arrow Language Model and how does it differ from attention-based transformers?",{"text":121,"@type":113},"It is a recurrent neural model derived from left-nested intuitionistic implications where each token is an operator transforming a proof state; it replaces similarity-based attention with non-commutative operator composition to carry semantic content and order.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},515832,1791385301,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145,"preview_page_count":19,"preview_urls":146},1099529839202,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","On the (Intuitionistic) Logic of Next-Token Prediction  \nPaul Tarau  \nUniversity of North Texas  \n[Paul.Tarau@unt.edu](Paul.Tarau@unt.edu)  \nWe model in intuitionistic implicational logic the key enabler of today’s GenerativeAI: the next-token prediction in autoregressive causal neural networks.  \nIn our framework, next-token prediction corresponds to modus ponens, and sequence processing becomes constructive proof extension under the Curry–Howard correspondence. Our Prolog-based specialized theorem provers validate fundamental properties of the neural models, among which relations between commutative vs. non-commutative sequencing and single-token vs. multi-token prediction choices.  \nWe derive a neural architecture equivalent to multiplicative RNNs that arises naturally from a proof-theoretic interpretation of next-token prediction as nested intuitionistic implication and position the model relative to transformers, state-space models and recursive LLMs.  \nKeywords: logic-based derivation of neural architectures, intuitionistic implicational logic, tokenas-operator neural models, alternatives to transformer-based foundational models.  \n1 Introduction  \nFoundational Generative AI models involve mechanisms like next token(s) prediction that naturally benefit from unsupervised training on very large data sets at a scale closely matching the total multi-modal content of the internet.  \nThe resulting distribution, encapsulated in the parametric memory of the model, constructively completes the initial sequence derived from the prompt and subsequently generated tokens with a set of probability-weighted next token candidates.  \nThe underlying logic of the derivation of the next token hints to an intuitionistic implicational logic proof of q seen as an implication from assumptions in context E , E → q. This is can be stated as finding away to transform a proof of an assumption context E into a proof of a consequence q. In the neural world this materializes as a transformation of the overall statistical evidence for E into a predicted probability for q.  \nIn the case of the transformer models [10], order information is learned via dedicated positional encodings that complement the parallel attention heads that learn deep dependencies relating to the “past”token sets while having the set of “future tokens” masked. This is a highly effective approach, but it obscures the logical structure of sequence prediction and provides little explanatory connection to symbolic reasoning.  \nWe will explore here an alternative view: next-token prediction as implication completion. We ask whether the task of predicting the next word in a sequence can be understood as extending a proof in intuitionistic propositional logic—and whether this interpretation leads naturally to a viable neural architecture.  \nOur answer is affirmative. Starting from a symbolic encoding of sequences as left-nested intuitionistic implications, we derive a recurrent neural model in which each token acts as an operator transforming  \nW. Faber, L. Giordano, R. Rocha, V. Santos Costa (Eds.):  \n42nd International Conference on Logic Programming (ICLP 2026) EPTCS 450, 2026, pp. 52–66, doi:10.4204/EPTCS.450.4  \n© P. Tarau  \nThis work is licensed under the Creative Commons Attribution License.  \nP. Tarau 53  \na proof state. The resulting architecture, which we call the Arrow Language Model, replaces similaritybased attention with non-commutative operator composition as the carrier of both semantic content and order.  \nOur logic-based insights will also be extended to cover multi-token prediction and it naturally relates to type inference and type inhabitation via the Curry-Howard isomorphism.  \nThe rest of the paper is organized as follows. Section 2 introduces our theorem provers for propositional implicational intuitionistic logic. Section 3 justifies our choice of the logic formalism modeling content and order in the next token prediction. Section 4 illustrates instances of valid","cbCailnETmUoHhOY","https://ap.wps.com/l/cbCailnETmUoHhOY","pdf",242537,15,"English","# Introduction\n# Our tools: implicational intuitionistic logic theorem provers\n# Logic formalism for content and order in next-token prediction\n# Valid formulas for left-nested implicational sequences\n# Information retrieval via implicational subformulas\n# Neural realization of the Arrow Architecture\n# Experiments and validation\n# Limitations and future work\n# Related work\n# Conclusion","[{\"question\":\"How does the paper relate next-token prediction to modus ponens in intuitionistic logic?\",\"answer\":\"It states that in its framework next-token prediction corresponds to modus ponens, turning sequence processing into constructive proof extension under the Curry–Howard correspondence.\"},{\"question\":\"What role do the Prolog-based theorem provers play?\",\"answer\":\"They validate fundamental properties of the neural models, including relationships between commutative vs. non-commutative sequencing and choices for single-token vs. multi-token prediction.\"},{\"question\":\"What is the Arrow Language Model and how does it differ from attention-based transformers?\",\"answer\":\"It is a recurrent neural model derived from left-nested intuitionistic implications where each token is an operator transforming a proof state; it replaces similarity-based attention with non-commutative operator composition to carry semantic content and order.\"}]","On the (Intuitionistic) Logic of Next-Token Prediction | PDF",1791322670,38,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/67f6a60b69c40f68f5be23b695856f0c.webp",983,1272,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/2aa044adf69d8e486c70b09b6bac9d10.webp",982,1270,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/3bd8127ab543560f172881da1bc78937.webp",981,1269,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/a34753d8978fc53344b6522afe72f9be.webp",980,1268]