[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-328133-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-328133-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","llm-guided-task-semantic-field-factorization-for-industrial-process-forecasting","LLM-Guided Task-Semantic Field Factorization for Industrial Process Forecasting","","Process industries depend on time-series forecasting and soft sensing to estimate quality variables that are difficult to measure online. Limited labeled data, frequently changing operating regimes, and costly scenario-specific retraining or pipeline rebuilding make alignment difficult. The framework leverages available variable tables and process documents that describe names, units, physical meanings, and roles. It builds task-semantic field representations guided offline by an LLM, while online training and inference use conventional time-series backbones activated by semantic context. Experiments show 6.4% average MAE reduction in improved settings, with up to 25.5% reduction, and only minor parameter and inference overhead.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/llm-guided-task-semantic-field-factorization-for-industrial-process-forecasting/328133/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/llm-guided-task-semantic-field-factorization-for-industrial-process-forecasting/328133.png","ImageObject",300,407,{"name":42,"@type":43},"Asher","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-04","2026-09-21",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",11,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What challenge does the method address in industrial process forecasting?","Question",{"text":63,"@type":64},"Industrial forecasting faces scarce labels, frequent operating regime changes, and high cost of retraining or rebuilding alignment pipelines for each scenario.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does Task-Semantic Field Factorization (TSF) use an LLM?",{"text":68,"@type":64},"TSF uses an LLM only offline to construct task-aware variable semantics from task protocols and variable documents before training.",{"name":70,"@type":61,"acceptedAnswer":71},"What is the impact of TSF on forecasting accuracy and overhead?",{"text":72,"@type":64},"TSF reduces MAE by 6.4% on average in improved settings, with the largest reduction reaching 25.5%, while adding only about 1.8–3.0k parameters and minimal additional online inference cost.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},328133,1790612723,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":55,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":4},687197207639,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","LLM-Guided Task-Semantic Field Factorization for Industrial Process Forecasting  \nYoucheng Zong , Student Member, IEEE, Runda Jia, Mingxuan Ren ,  \nand Dakuo He  \narXiv :2607 .06623v 1 [ cs .LG] 7 Jul 2026  \nAbstract—Process industries rely on time-series forecasting and soft sensing to estimate quality variables that are hard to measure online. Labeled data are scarce, operating regimes change frequently, and retraining models or rebuilding alignment pipelines for each scenario is costly. Such settings often provide variable tables and process documents that record variable names, units, physical meanings, and process roles. However, standard time-series backbones usually treat inputs as anonymous numerical columns. Existing text-enhanced methods also rarely make the semantic-logical relations between input variables and the prediction target available to the model within each numerical window. To address this problem, this article proposes Task-Semantic Field Factorization (TSF), a large language model (LLM)-guided framework. TSF builds a task-semantic field from task protocols and variable documents before training and uses the LLM only for offline semantic construction. Online training and inference remain with conventional time-series backbones. During training and inference, the current numerical window activates variable semantics, so semantic information participates in each prediction and supports adaptation to different prediction targets and operating shifts. On multiple complex industrial forecasting and soft-sensing tasks, TSF reduces MAE by 6.4% on average in improved settings, with the largest reduction reaching 25.5%. It adds only about 1.8–3.0k parameters, with less than 0.008 ms/step of additional online inference overhead. These results show that TSFturns existing process documents into measurable forecasting gains across backbones and semantic generators while remaining lightweight for deployment.  \nIndex Terms—large language models, industrial process forecasting, soft sensing, variable semantics, semantic input factorization.  \nI. INTRODUCTION  \nProcess industries rely on time-series forecasting and soft sensing to estimate quality variables that are hard to measure online. These predictions directly affect safety margins, product quality, energy use, and production efficiency. Work on soft sensing and metallurgy decision support shows that data-driven models are now widely used in industrial informatics [1],  \nThis work was supported by the Fundamental Research Funds for the Central Universities, China (N26GFZ006) . (Corresponding author: Runda Jia.)  \nYoucheng Zong, Runda Jia, Mingxuan Ren, and Dakuo He are with the College of Information Science and Engineering, Northeastern University, Shenyang 110004, China (e-mail: [youchengzong@stumail.neu.edu.cn](youchengzong@stumail.neu.edu.cn) ; [jiarunda@ise.neu.edu.cn](jiarunda@ise.neu.edu.cn) ;  \n[renmx@mails.neu.edu.cn](renmx@mails.neu.edu.cn) ; [hedakuo@ise.neu.edu.cn](hedakuo@ise.neu.edu.cn)) .  \n[2] . In real deployments, however, data conditions remain restrictive: high-quality labels are scarce, operating conditions change frequently, and retraining models or rebuilding alignment pipelines for each scenario is costly. Meanwhile, variable tables and process documents are usually already available. They record variable names, units, physical meanings, sampling attributes, and process roles. These documents are a natural source of prior knowledge, but they often remain outside the prediction process.  \nThis gap is most visible at the input layer. Multivariate timeseries backbones can learn temporal dependence, but their inputs are usually just column-ordered numerical windows. In industrial tasks, however, a variable is not an anonymous number. It also carries units, control meaning, and a relation to the target variable. When samples are limited, the model needs to recognize these relations in the current window rather than only memorize the numerical sha","cbCaieh7SOUKMot1","https://ap.wps.com/l/cbCaieh7SOUKMot1","pdf",21767868,"English","# Abstract\n# Introduction\n## Motivation and Problem Setup\n## Role of Variable Documents and Semantics\n## Proposed LLM-Guided TSF Approach","[{\"question\":\"What challenge does the method address in industrial process forecasting?\",\"answer\":\"Industrial forecasting faces scarce labels, frequent operating regime changes, and high cost of retraining or rebuilding alignment pipelines for each scenario.\"},{\"question\":\"How does Task-Semantic Field Factorization (TSF) use an LLM?\",\"answer\":\"TSF uses an LLM only offline to construct task-aware variable semantics from task protocols and variable documents before training.\"},{\"question\":\"What is the impact of TSF on forecasting accuracy and overhead?\",\"answer\":\"TSF reduces MAE by 6.4% on average in improved settings, with the largest reduction reaching 25.5%, while adding only about 1.8–3.0k parameters and minimal additional online inference cost.\"}]","LLM-Guided Task-Semantic Field Factorization for Industrial Process Forecasting | PDF",1789978722,28]