[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85928-en":3,"doc-seo-85928-105":29,"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":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85928,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","When Reasoning Hurts Legal Drafting The Verbalization Bottleneck in Patent Claim Generation","Patent claim drafting is a difficult legal drafting process demanding technical expertise, exact linguistic control, strict adherence to formal conventions, and careful preservation of complex logical relationships. The paper evaluates whether Chain-of-Thought (CoT) prompting improves patent claim generation and proposes a task-specific CoT approach. Results show reasoning-enhanced prompting can raise claim quality, yet implicit CoT outperforms explicit CoT. Explicit reasoning creates an information bottleneck via detail abstraction, pattern disruption, and cascading error propagation.","When Reasoning Hurts Legal Drafting: The Verbalization Bottleneck in Patent Claim Generation  \nLekang Jiang 1 Wenjun Sun 1 2 Stephan Goetz 1  \narXiv :2607 . 10480v 1 [ cs .CL] 11 Jul 2026  \nAbstract  \nPatent claim drafting is a challenging legal drafting task that requires technical expertise, precise linguistic control, strict adherence to formal conventions, and the preservation of complex logical relationships among claim elements.  \nWhile Chain-of-Thought (CoT) prompting has been widely used to improve the reasoning capabilities of large language models (LLMs), recent evidence suggests that its benefits may be limited, or even negative, in highly structured or patternsensitive tasks. Therefore, this paper investigates whether CoT prompting benefits patent claim generation. We propose a task-specific CoT method for patent claim generation and evaluate its effectiveness through both automatic metrics and human expert assessment. Our results show that reasoning-enhanced prompting can improve claim quality. Moreover, we demonstrate a counterintuitive but important empirical finding: implicit CoT, where reasoning is kept internal rather than explicitly verbalized, consistently outperforms explicit CoT. Through systematic analysis, we show that explicit CoT can introduce an unnecessary information bottleneck for claim generation. Verbalized reasoning may compromise the quality of final outputs through three specific mechanisms:  \nabstraction of critical details, disruption of internalized generation patterns, and cascading error propagation. Our findings provide new insights into legal tasks and CoT applications.  \n1. Introduction  \nThe automated generation of long-form, structured text, such as legal contracts, technical manuals, and patent docu- 1University of Cambridge 2National Science Library, Chinese Academy of Sciences; Department of Information Resources Man  \nagement, School of Economics and Management, University of Chinese Academy of Sciences. Correspondence to: Lekang Jiang \u003C[lj408@cam.ac.uk](lj408@cam.ac.uk)>.  \nAccepted to AI for Law Workshop @ ICML 2026 . Copyright 2026 by the author(s).  \nments, represents a significant frontier in natural language processing (NLP) (Zhao et al., 2023 ; Jiang & Goetz, 2025) . Such tasks demand not only exceptional linguistic proficiency but also stringent requirements on logical reasoning, strict adherence to structural conventions, and the integration of domain-specific knowledge. Patent claim drafting stands as a prime example of this challenge (Jiang et al., 2025d ; Wang et al., 2024) .  \nPatent documents are important for protecting intellectual property (IP) and disclosing technical innovations. A central component of these documents is the claim set, which defines the legal scope of protection granted to the patent holder. Thus, writing high-quality claims is a critical task in patent drafting, which requires precise language to capture the essence of the invention while remaining legally enforceable. A patent claim must articulate the core novelty of an invention using hierarchical, logically rigorous, and legally precise language (European Patent Office, 2000) . The complexity of this process is further compounded by its long contexts with over 1,000 tokens on average (Suzgun et al., 2024) . The challenges make the manual drafting time-consuming and intellectually intensive even for human experts. Thus, the automation of the patent drafting process, especially for claims, is important.  \nDespite the advancements of large language models (LLMs) in general-purpose text generation, the application to highly structured and complex tasks such as patent drafting often shows suboptimal results, characterized by logical imprecision, structural inconsistencies, or deviation from core requirements (Jiang & Goetz, 2025) . To unlock and guide the deeper reasoning capabilities of LLMs, the Chain-ofThought (CoT) prompting technique has emerged as a powerful method (Wei et al., 2022 ; Ko","cbCaifaqTqY9Av3l","https://ap.wps.com/l/cbCaifaqTqY9Av3l","pdf",310561,1,13,"English","en",105,"# Introduction\n# Related Work\n## CoT Prompting","[{\"question\":\"Why is patent claim drafting considered challenging for both humans and models?\",\"answer\":\"It requires technical expertise, precise legal language, strict structural conventions, and the maintenance of complex logical relationships among claim elements. Long contexts and domain-specific knowledge further increase difficulty.\"},{\"question\":\"How does implicit CoT differ from explicit CoT in this paper?\",\"answer\":\"Implicit CoT guides the model to reason internally while outputting only the final claims. Explicit CoT requires intermediate reasoning steps to be written out before generating the claims.\"},{\"question\":\"What mechanisms explain why explicit CoT can reduce claim quality?\",\"answer\":\"The paper attributes the drop to an information bottleneck caused by (1) abstraction of legally critical details, (2) disruption of internalized generation patterns, and (3) cascading error propagation across reasoning steps.\"}]",1784207217,33,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"when-reasoning-hurts-legal-drafting-the-verbalization-bottleneck-in-patent-claim-generation","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/when-reasoning-hurts-legal-drafting-the-verbalization-bottleneck-in-patent-claim-generation/85928/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","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},"Why is patent claim drafting considered challenging for both humans and models?","Question",{"text":75,"@type":76},"It requires technical expertise, precise legal language, strict structural conventions, and the maintenance of complex logical relationships among claim elements. Long contexts and domain-specific knowledge further increase difficulty.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does implicit CoT differ from explicit CoT in this paper?",{"text":80,"@type":76},"Implicit CoT guides the model to reason internally while outputting only the final claims. Explicit CoT requires intermediate reasoning steps to be written out before generating the claims.",{"name":82,"@type":73,"acceptedAnswer":83},"What mechanisms explain why explicit CoT can reduce claim quality?",{"text":84,"@type":76},"The paper attributes the drop to an information bottleneck caused by (1) abstraction of legally critical details, (2) disruption of internalized generation patterns, and (3) cascading error propagation across reasoning steps.","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":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]