[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86501-en":3,"doc-seo-86501-105":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},86501,1374391975076,"Riley","https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051",8,"Research & Report","Constraint-Aware Hierarchical Search for Regulation-Driven Fine-Grained Classification","Regulation-driven classification assigns an input to a fine-grained class within an explicit regulatory hierarchy, as required in customs tariff classification, export control, and standards-based equipment coding. Unlike semantic text classification, correct labeling depends on rule-defined boundaries, thresholds, exclusions, definitions, and local exceptions, where near-identical inputs may require different labels and retrieved passages may be legally inapplicable. The work formulates regulation-driven fine-grained hierarchical classification with auditable evidence, builds four expert-validated benchmarks, and proposes a constraint-aware hierarchical search that retrieves only valid candidate nodes and follows structured fields to decide each next hop, achieving the best mean accuracy across datasets.","Constraint-Aware Hierarchical Search for Regulation-Driven Fine-Grained Classification  \nSiyu Wanga,b,1 , Wei Tanc,1 and Lulu Chena,∗  \naGusu Laboratory of Materials, Suzhou, China  \nb Chongqing Institute of Engineering, Chongqing Engineering Research Center for Intelligent Applications of Financial Big Data, Chongqing, China cSuzhou Digital China Wuxin Intelligent Technology Co., Ltd., Suzhou, China  \narXiv :2607 . 10588v 1 [ cs .AI] 12 Jul 2026  \nARTICLE INFO  \nKeywords:  \nRegulation-driven classification Hierarchical rule-based reasoning Constraint-aware search  \nAB STRACT  \nTasks such as customs tariff classification, export control categorization, and standards-based equipment coding require assigning an input instance to a fine-grained class under an explicit regulatory hierarchy. Unlike standard text classification, the correct label in these tasks is not determined by semantic similarity alone, but by rule-defined boundaries, threshold conditions, exclusion clauses, definitions, and local exceptions. As a result, two highly similar inputs may require different labels, while a retrieved passage that appears relevant may still be inapplicable under the governing rules. Existing flat classifiers, hierarchical text classification methods, and retrieval-augmented LLM systems are not designed to jointly enforce hierarchical validity, rule consistency, and fine-grained boundary reasoning. In this paper, we formulate this setting as regulation-driven fine-grained hierarchical classification, where an external instance must be assigned to a fine-grained class through a valid path in a regulatory hierarchy and supported by auditable evidence. We construct four benchmark datasets from representative regulation-intensive scenarios and validate the annotations through an expertin-the-loop process. We further propose a constraint-aware hierarchical search framework that converts regulatory documents into a searchable tree, retrieves only valid local candidate nodes, and uses structured regulatory fields with evidence snippets to guide each next-hop decision. Experiments show that our method achieves the best mean accuracy on all four datasets and provides interpretable decision paths, with the largest gains on cases involving fine-grained neighboring categories and rulebased boundary conditions.  \n1. Introduction  \nMany real-world classification problems look deceptively similar to ordinary text classification: given a description of an object, case, or request, a system must assign it to the correct category. In institutional and regulatory settings, however, the category boundary is defined by an external rule system rather than by semantic similarity alone. Such systems often contain structured taxonomies, inclusion criteria, threshold conditions, exclusion clauses, definitions, and local exceptions. A single attribute can redirect the decision to a different branch, and a semantically relevant rule can still be inapplicable if it belongs to the wrong regulatory scope.  \nRecent advances in large language models (LLMs), dense retrieval, and retrieval-augmented generation (RAG) have achieved strong performance on general text classification, question answering, and other knowledge-intensive tasks Karpukhin, Oguz, Min, Lewis, Wu, Edunov, Chen and Yih (2020); Lewis, Perez, Piktus, Petroni, Karpukhin, Goyal, Kuttler, Lewis, Yih, Rocktäschel, Riedel and Kiela (2020); Guu, Lee, Tung, Pasupat and Chang (2020); Gao, Xiong, Gao, Jia, Pan, Bi, Dai, Sun, Wang and Wang (2023); Du, Xu, Zhu, Wang, Wang, Wang and Mao (2026) . However,  \n∗Corresponding author  \n [wangsiyu2022@gusulab.ac.cn](wangsiyu2022@gusulab.ac.cn) (S. Wang); [tanwei@dces.cn](tanwei@dces.cn) (W. Tan); [chenlulu2021@gusulab.ac.cn](chenlulu2021@gusulab.ac.cn) (L. Chen)  \nORCID(s):  \n1 Siyu Wang and Wei Tan contributed equally to this work and should be considered co-first authors.  \nregulatory classification requires a decision to satisfy the hierarchy, the governing rules, and ","cbCaiiYfW6CIUaxe","https://ap.wps.com/l/cbCaiiYfW6CIUaxe","pdf",3384504,4,1,16,"English","en",105,"# Introduction\n# Motivation and Problem Setting\n## Why semantic and flat classifiers fail\n## Concrete customs tariff example\n# Method Overview (Constraint-Aware Hierarchical Search)","[{\"question\":\"What makes regulation-driven fine-grained classification different from ordinary text classification?\",\"answer\":\"Category boundaries are defined by external regulatory rules—hierarchy, thresholds, exclusions, definitions, and local exceptions—rather than semantic similarity alone. As a result, similar inputs can require different labels, and relevant-looking passages can still be legally inapplicable.\"},{\"question\":\"Why can retrieval or LLM-based approaches be unreliable for this task?\",\"answer\":\"Retrievers may return semantically related but legally out-of-scope passages. LLMs may generate plausible codes but can misinterpret local conditions, exclusions, and fine-grained boundary rules needed to legally distinguish neighboring categories.\"},{\"question\":\"How does the proposed constraint-aware hierarchical search improve classification accuracy and interpretability?\",\"answer\":\"It converts regulatory documents into a searchable tree, retrieves only valid local candidate nodes, and uses structured regulatory fields with evidence snippets to guide each next-hop decision. Experiments indicate the method yields the best mean accuracy across four benchmarks and provides interpretable decision paths, especially for fine-grained neighboring categories.\"}]",1784212215,40,{"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},"constraint-aware-hierarchical-search-for-regulation-driven-fine-grained-classification","",{"@graph":36,"@context":85},[37,53,68],{"@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":20},"https://docshare.wps.com/document/constraint-aware-hierarchical-search-for-regulation-driven-fine-grained-classification/86501/",{"url":52,"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","2026-07-25","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 makes regulation-driven fine-grained classification different from ordinary text classification?","Question",{"text":75,"@type":76},"Category boundaries are defined by external regulatory rules—hierarchy, thresholds, exclusions, definitions, and local exceptions—rather than semantic similarity alone. As a result, similar inputs can require different labels, and relevant-looking passages can still be legally inapplicable.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why can retrieval or LLM-based approaches be unreliable for this task?",{"text":80,"@type":76},"Retrievers may return semantically related but legally out-of-scope passages. LLMs may generate plausible codes but can misinterpret local conditions, exclusions, and fine-grained boundary rules needed to legally distinguish neighboring categories.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed constraint-aware hierarchical search improve classification accuracy and interpretability?",{"text":84,"@type":76},"It converts regulatory documents into a searchable tree, retrieves only valid local candidate nodes, and uses structured regulatory fields with evidence snippets to guide each next-hop decision. Experiments indicate the method yields the best mean accuracy across four benchmarks and provides interpretable decision paths, especially for fine-grained neighboring categories.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"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":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":29,"slug":118},7,"Healthcare","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"]