[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-273862-105":59,"doc-detail-273862-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","benchmarking-patent-drafting-from-inventor-style-disclosures-abstract","Benchmarking Patent Drafting from Inventor-Style Disclosures - Abstract","","Large language models can draft individual patent components but still do not address the central real-world task: generating a complete, legally coherent patent application from early-stage invention materials. Existing benchmarks mostly assume later, highly structured, or already legalistic inputs. Dis2Pat is introduced to mirror realistic workflows by requiring patent application generation from de-legalized inventor-style disclosures with figures. A locally deployable multi-agent baseline, Patent-MAF, is proposed for privacy-aware drafting, and benchmarks show improved performance over evaluated open-source models and competitiveness with closed models.",{"@graph":69,"@context":123},[70,84,106],{"@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/benchmarking-patent-drafting-from-inventor-style-disclosures-abstract/273862/",{"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/benchmarking-patent-drafting-from-inventor-style-disclosures-abstract/273862.png","ImageObject",300,407,{"name":92,"@type":93},"Ophelia","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-09-15",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",17,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What is the core challenge Dis2Pat targets in patent drafting?","Question",{"text":113,"@type":114},"Generating a complete and legally coherent patent application directly from early-stage invention materials, not just drafting individual components.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does Dis2Pat make patent generation more realistic?",{"text":118,"@type":114},"It requires generating full patent applications from de-legalized, inventor-style disclosures accompanied by figures, matching practical workflows.",{"name":120,"@type":111,"acceptedAnswer":121},"What is Patent-MAF and why is it proposed?",{"text":122,"@type":114},"Patent-MAF is a multi-agent framework designed for locally deployable patent drafting to satisfy strong privacy requirements while serving as a strong baseline.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},273862,1789473050,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},7971461741311,"https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826","Benchmarking Patent Drafting from Inventor-Style Disclosures  \nLekang Jiang 1 , Wenjun Sun 123 , Stephan Goetz 1  \n1University of Cambridge 2National Science Library, Chinese Academy of Sciences  \n3Department of Information Resources Management, School of Economics and Management, University of Chinese Academy of Sciences  \n{lj408, ws462, [smg84}@cam.ac.uk](smg84}@cam.ac.uk)  \narXiv : 2608 .2 1249v 1 [cs .CL] 2 1 Aug 2026  \nAbstract  \nWhile recent large language models (LLMs) have achieved promising results on individual patent drafting tasks, they fundamentally fail to investigate the core challenge of realworld patent drafting: generating a complete and legally coherent patent application directly from early-stage invention materials. Prior work predominantly assumes later-stage, highly structured, or already legalistic inputs. However, real patenting workflows begin withinformal, de-legalized disclosures authored by inventors. To bridge the gap, we introduce Dis2Pat, a disclosure-to-patent dataset that reflects realistic patenting workflows by requiring the generation of complete patent applications directly from inventor-style, de-legalized disclosures. Given the inherent difficulty of longform, legally constrained patent drafting and the strong privacy requirements, we further propose a strong baseline named Patent-MAF. It is a multi-agent framework for locally deployable patent drafting. Benchmark results reveal that current LLMs exhibit limitations in patent drafting, while Patent-MAF provides a strong baseline that consistently outperforms evaluated open-source models and remains competitive with large closed-source models. 1  \n1 Introduction  \nPatent drafting is a critical yet costly process that transforms an inventor’s technical ideas into legally enforceable documents consisting of claims anda detailed specification (European Patent Office, 2000) . Claims define the legal scope of a patent, while the specification provides comprehensive descriptions of the invention and its specific embodiments, typically with reference to the accompanying drawings (Jiang and Goetz, 2025) . Although recent advances in large language models (LLMs) have achieved promising results on individual patent drafting tasks—such as claim generation  \n1 [https://github.com/scylj1/Patent-MAF](https://github.com/scylj1/Patent-MAF)  \n(Jiang et al., 2025d,a,b) and specification writing (Wang et al., 2024a ; Yang et al., 2026 ; Shea and Yu, 2025)—the generation of a complete patent application from early-stage invention materials remains an open problem.  \nA key challenge arises from the mismatch between existing benchmarks and real-world patent drafting workflows. In practice, inventors typically submit informal invention disclosures describing the problem, core idea, implementation details, and illustrative figures; patent attorneys then translate these materials into legally structured claims and specifications (LLP, 2023) . However, most prior datasets and models operate on later-stage or highly structured inputs, such as full specifications for claim generation (Jiang et al., 2025d) or claims for specification drafting (Wang et al., 2024a) . As a result, current systems are often evaluated in settings that bypass the most challenging aspect of patent drafting: translating inventor-style disclosures into legally structured patent applications.  \nRecent work has begun to explore end-to-end patent generation, including draft-to-patent (Wanget al., 2024b) and paper-to-patent settings (Knappich et al., 2025) . Although these approaches move closer to holistic drafting, their inputs are typically authored in formal or technical styles that differ substantially from authentic invention disclosures. Moreover, although patent figures play a central role in conveying technical structure and features in specific embodiments, especially in mechanical and system-oriented inventions, most existing datasets either omit figures or incorporate them only in lim","cbCaideXzK1lELPw","https://ap.wps.com/l/cbCaideXzK1lELPw","pdf",306796,15,"English","# Abstract\n# Introduction\n## Patent drafting task and legal structure\n## Mismatch between benchmarks and real workflows\n## Related end-to-end patent generation and multimodal figures\n## Dis2Pat dataset and Patent-MAF baseline","[{\"question\":\"What is the core challenge Dis2Pat targets in patent drafting?\",\"answer\":\"Generating a complete and legally coherent patent application directly from early-stage invention materials, not just drafting individual components.\"},{\"question\":\"How does Dis2Pat make patent generation more realistic?\",\"answer\":\"It requires generating full patent applications from de-legalized, inventor-style disclosures accompanied by figures, matching practical workflows.\"},{\"question\":\"What is Patent-MAF and why is it proposed?\",\"answer\":\"Patent-MAF is a multi-agent framework designed for locally deployable patent drafting to satisfy strong privacy requirements while serving as a strong baseline.\"}]","Benchmarking Patent Drafting from Inventor-Style Disclosures - Abstract | PDF",38]