[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85043-en":3,"doc-seo-85043-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85043,1099514067415,"Rowan","https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502",8,"Research & Report","Concretized Proposition Prompting Resolves Composition-Knowledge Dichotomy in Large Language Models","Large language models often fail to jointly optimize compositionality and knowledgeability, which limits reasoning reliability across domains. The study defines this tension as the Composition–Knowledge Dichotomy and introduces Concretized Proposition Prompting (CPP), a framework that explicitly concretizes propositions relevant to each question. Results show substantial reasoning gains, especially on medical benchmarks that require precise factual grounding, while remaining competitive on math benchmarks that reward deductive structure. Additional experiments confirm scalability across foundation models and parameter sizes, offering a unified paradigm for organized, factually grounded answers.","Concretized Proposition Prompting Resolves Composition-Knowledge Dichotomy in Large Language Models  \nChanghun Lee 1 ,2 *†, Minguk Jeon2 * , Jongkyung Shin2 and Chiehyeon Lim2 ,3  \n[cl4670@cumc.columbia.edu](cl4670@cumc.columbia.edu1)[1](cl4670@cumc.columbia.edu1) , [chlim@posco-inc.com](chlim@posco-inc.com3)[3](chlim@posco-inc.com3)  \n{changhun, rzbsys, shinjk1156, [chlim}](chlim}@unist.ac.kr 2)[@unist.ac.kr](chlim}@unist.ac.kr 2)[ 2](chlim}@unist.ac.kr 2)  \n1 Columbia University 2UNIST 3POSCO Holdings  \narXiv :2607 .080 18v 1 [ cs .AI] 9 Jul 2026  \nAbstract  \nLLMs often struggle to balance compositionality with knowledgeability, a challenge we define as Composition-Knowledge Dichotomy.  \nTo address this, we propose Concretized Proposition Prompting (CPP), a framework that explicitly concretizes propositions relevant to questions. The results demonstrate that CPP significantly enhances reasoning performance, particularly in medical benchmarks where precise knowledge is paramount, while being competitive on math benchmarks where deductive reasoning is prioritized. Additional experiments reveal that CPP is scalable to various foundation models and parameter sizes, being a fundamental paradigm that bridges the gap between composition- and knowledge-based approaches. Consequently, CPP resolves the composition-knowledge dichotomy by providing a solid foundation for logically organized and factually grounded reasoning.  \n1 Introduction  \nDespite the great success of large language models (LLMs) (Achiam et al., 2023 ; Touvron et al., 2023 ; Comanici et al., 2025), there still remains a gap between human intelligence and LLMs in terms of their reasoning capabilities. The recently proposed chain-of-thought (CoT) prompting methods (Wei et al., 2022 ; Chowdhery et al., 2022 ; Kojima et al., 2022) have significantly narrowed this gap. The core idea of CoT prompting is to combine rationale generation (Ling et al., 2017) with fewshot prompting (Brown et al., 2020) in a way that so-called ‘thoughts’ are provided to LLMs in the format of \u003Cinput, thoughts, output> .  \nThough CoT prompting can improve the reasoning capabilities of LLMs (Zhou et al., 2022 ; Xia et al., 2025), it still has critical limitations. For example, it cannot match human performance at  \n* Equal contribution † Corresponding author  \ncommonsense and multi-step reasoning (Sprague et al., 2024), is not as useful as in areas beyond math (Kambhampati et al., 2024), can even hurt performance (Wang et al., 2024 ; Nakkiran et al., 2025), and incur computational costs more than the performance gains it delivers (Sprague et al., 2025) . Furthermore, since the CoT is generated by LLMs that are vulnerable to hallucination, it has a risk of inducing erroneous post-hoc rationalization (i.e., exquisite hallucination) for the LLMs taking those hallucinated CoT to generate incorrect answers (Huang et al., 2025a ; Cheng et al., 2025 ; Lewis-Lim et al., 2025 ; Arcuschin et al., 2025) .  \nIn response to these limitations, advanced CoT techniques have been suggested. One main approach focuses on organizing the structure of LLM reasoning. For example, Least-to-Most prompting breaks down a complex problem into simpler subproblems (Zhou et al., 2022), Plan-and-Solve devises a plan first and solves a problem next (Wanget al., 2023), Thread of Thought segments chaotic contexts into manageable parts (Zhou et al., 2023), Meta-Prompting prioritizes the structured template for how to think over specific examples of what to think (Zhang et al., 2023) . Another approach focuses on retrieving evidence useful for LLM reasoning. Analogical prompting generates problemspecific exemplars or knowledge before solving problems (Yasunaga et al., 2023), Self-Knowledge Explicitation (SKE) explicitly generates verifiable knowledge (Huang et al., 2025b), and System-2-Attention regenerates the problem-relevant contexts (Weston and Sukhbaatar, 2023) .  \nBoth approaches have successfully enhanced the reasoning capabili","cbCaij1lcQ9gEj2T","https://ap.wps.com/l/cbCaij1lcQ9gEj2T","pdf",1399682,5,1,25,"English","en",105,"# Abstract\n# Introduction\n# Preliminaries","[{\"question\":\"What problem does the paper address in large language models?\",\"answer\":\"The paper targets a gap between compositional reasoning and knowledge grounding, defined as the Composition–Knowledge Dichotomy.\"},{\"question\":\"What is Concretized Proposition Prompting (CPP)?\",\"answer\":\"CPP is a prompting framework that explicitly concretizes propositions relevant to a question, integrating logical organization with factual truth value.\"},{\"question\":\"On which tasks does CPP work best and how is it evaluated?\",\"answer\":\"CPP shows clear improvements on medical benchmarks where precise knowledge is crucial, and remains competitive on math benchmarks that prioritize deductive reasoning; evaluations cover multiple QA datasets across commonsense, math, and medicine.\"}]",1784200582,63,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"concretized-proposition-prompting-resolves-composition-knowledge-dichotomy-in-large-language-models","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/concretized-proposition-prompting-resolves-composition-knowledge-dichotomy-in-large-language-models/85043/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the paper address in large language models?","Question",{"text":76,"@type":77},"The paper targets a gap between compositional reasoning and knowledge grounding, defined as the Composition–Knowledge Dichotomy.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What is Concretized Proposition Prompting (CPP)?",{"text":81,"@type":77},"CPP is a prompting framework that explicitly concretizes propositions relevant to a question, integrating logical organization with factual truth value.",{"name":83,"@type":74,"acceptedAnswer":84},"On which tasks does CPP work best and how is it evaluated?",{"text":85,"@type":77},"CPP shows clear improvements on medical benchmarks where precise knowledge is crucial, and remains competitive on math benchmarks that prioritize deductive reasoning; evaluations cover multiple QA datasets across commonsense, math, and medicine.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":20,"slug":138},19,"General","general"]