[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81705-en":3,"doc-seo-81705-105":30,"detail-sidebar-cat-0-en-105":91},{"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},81705,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Controllable Narrative Rendering for Enhanced Assisted Writing","Despite strong large language model (LLM) performance in basic writing support, creative writing is blocked by a recurring binary failure: systems oscillate between safe, surface-level remedial polishing and destructive, uncontrolled plot expansion. This creates a persistent trade-off between narrative fidelity and descriptive intensity. LOOM is an assisted writing framework built on the story–discourse distinction, using a three-layer pipeline to enforce intent control and render density without breaking the original event structure. Comprehensive LLM metrics and human evaluation show superior quality, factual integrity, and richer description.","Controllable Narrative Rendering for Enhanced  \nAssisted Writing  \nMingzhe Lu 1,2 , Yanbing Liu 1,2 , Jiayue Wu 1,2 , Jiarui Zhang 1,2 , Qihao Wang 1,2 , Yue Hu 1,2 , Yunpeng Li 1,2,* , Yangyan Xu3  \n1Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China  \n2 School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China  \n3HiThink Research  \n* Corresponding author: [liyunpeng@iie.ac.cn](liyunpeng@iie.ac.cn)  \narXiv :2607 .00009v1 [ cs .CL] 5 May 2026  \nAbstract—Despite the remarkable proficiency of large language models (LLMs) in basic writing assistance, their utility in creative writing is fundamentally hindered by a persistent binary failure. This issue manifests as an oscillation between safe, surfacelevel editing, referred to as remedial polishing, and destructive, uncontrolled plot expansion. This dilemma defines a critical trade-off between narrative fidelity and descriptive intensity. We propose LOOM, an assisted writing framework grounded in thenarratological distinction between story and discourse. Loom employs a three-layer pipeline that operationalizes an intentcentered semiotic chain-of-thought to enforce precise control over narrative intent and rendering density. This architecture separates the generation of perceptual material from syntactic insertion, ensuring that enhancement occurs without violating the original event structure. Our comprehensive evaluation, which includes LLM-based metrics and human assessment, demonstrates that Loom successfully resolves this fundamental tension. Loom achieves the highest overall quality score, yielding substantial gains in factual integrity and descriptive intensity compared to state-of-the-art baselines.  \nIndex Terms—Narrative Rendering, Writing Assistance, Controllable Text Generation  \nI. INTRODUCTION  \nWriting assistance technologies have advanced rapidly since the advent of large language models (LLMs), showing proficiency in grammatical correction, fluency enhancement, and stylistic rewriting [1], [2] . In both general and professional contexts, these tools act as sophisticated editors, resolving linguistic friction and ensuring structural soundness. Stateof-the-art models have largely solved the problem of textual correctness by mastering the foundational layers of writing, often described as “faithfulness” and “fluency”.  \nDespite these capabilities, existing paradigms remain grounded in what we characterize as remedial polishing. In this mode, systems focus on surface-level editing, polishing form, or rephrasing expressions to enhance clarity. However, creative writing demands a fundamental shift from strictly “fixing”text to actively shaping the reader’s experience [3], a process we define as narrative rendering. Unlike remedial polishing, rendering seeks to transform the perceptual texture [4], which encompasses atmosphere, mood, and sensory detail, without altering the underlying story events.  \nTo illustrate this distinction, consider the narrative event:“He walked into the room.” A deep rendering might depict the air as “stale and heavy as if the walls had been holding their breath,” invoking tension; alternatively, it might describe“sunlight pooling along the floor,” evoking warmth. Both renderings create strikingly different reading experiences while strictly preserving the same factual action.  \nHowever, achieving this specific level of control remains a formidable challenge. General-purpose models tasked with enhancement either default to safe, surface-level editing [5], which amounts to remedial polishing, or generate uncontrolled plot expansions when prompted for expressivity, often effectively hallucinating new events [6] . Consequently, there remains no computational framework capable of precisely controlling enhancement within the perceptual layer without compromising the factual integrity of the source.  \nThis limitation reflects a conflation of two distinct narratological layers: the story (what ha","cbCaibK9R8oeB56t","https://ap.wps.com/l/cbCaibK9R8oeB56t","pdf",5219627,2,1,6,"English","en",105,"# Introduction\n# Related Work","[{\"question\":\"What problem does LOOM aim to solve in assisted writing?\",\"answer\":\"LOOM targets the persistent failure mode where models either perform safe surface editing (remedial polishing) or produce uncontrolled plot expansion that changes events.\"},{\"question\":\"How does LOOM maintain narrative fidelity while increasing descriptive intensity?\",\"answer\":\"LOOM separates perception material generation from syntactic insertion through a three-layer pipeline based on the story–discourse distinction, preserving the original event structure while enhancing rendering.\"},{\"question\":\"How is LOOM evaluated to verify its effectiveness?\",\"answer\":\"The document reports evaluation using LLM-based metrics, human assessment, and ablation studies, showing improved overall quality, higher factual integrity, and increased descriptive intensity versus state-of-the-art baselines.\"}]",1784175530,15,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"controllable-narrative-rendering-for-enhanced-assisted-writing","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/controllable-narrative-rendering-for-enhanced-assisted-writing/81705/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does LOOM aim to solve in assisted writing?","Question",{"text":75,"@type":76},"LOOM targets the persistent failure mode where models either perform safe surface editing (remedial polishing) or produce uncontrolled plot expansion that changes events.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does LOOM maintain narrative fidelity while increasing descriptive intensity?",{"text":80,"@type":76},"LOOM separates perception material generation from syntactic insertion through a three-layer pipeline based on the story–discourse distinction, preserving the original event structure while enhancing rendering.",{"name":82,"@type":73,"acceptedAnswer":83},"How is LOOM evaluated to verify its effectiveness?",{"text":84,"@type":76},"The document reports evaluation using LLM-based metrics, human assessment, and ablation studies, showing improved overall quality, higher factual integrity, and increased descriptive intensity versus state-of-the-art baselines.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]