[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86241-en":3,"doc-seo-86241-105":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},86241,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Communicating Chess Strategies in Natural Language","Chess engines deliver superhuman move strength, yet their strategy rationale is hard for humans—even skilled players—to understand. This work introduces chess strategy verbalization: describing engine-derived strategies in natural language. A pipeline is proposed for generating verbalized strategy descriptions, alongside an evaluation framework for objective assessment. Experiments show natural language enables interpretable communication for both humans and LLMs, while also revealing limits in concept-only descriptions and in LLM-based evaluation versus human judgment.","Communicating Chess Strategies in Natural Language  \nLangyuan Cui and Chun Kai Ling and Hwee Tou Ng  \nDepartment of Computer Science  \nNational University of Singapore  \n13 Computing Drive, Singapore 117417 [langyuan.c@u.nus.edu](langyuan.c@u.nus.edu), [chunkail@nus.edu.sg](chunkail@nus.edu.sg), [dcsnght@nus.edu.sg](dcsnght@nus.edu.sg)  \narXiv :2607 . 1 1486v 1 [ cs .CL] 13 Jul 2026  \nAbstract  \nChess engines have long achieved superhuman playing strength. However, the underlying strategy behind their move suggestions is difficult for human players, even skilled ones, to comprehend. Motivated by this, we propose the task of chess strategy verbalization, which is to describe chess strategies in natural language. We design (i) a pipeline for verbalizing strategies and (ii) an evaluation framework for objective evaluation of generated strategy descriptions.  \nOur experiments show that natural language is a promising and interpretable medium for communicating strategic information to both human and LLM players. We glean additional interesting insights, including (a) the importance of evaluating strategies beyond the mainline,(b) the limitations of pure concept-based descriptions, and (c) the limitations of relying on LLMs rather than humans for evaluation.  \n1 Introduction  \nOnce touted as a bastion of human intellect that would never be matched by machines (Hsu et al., 1990), chess playing is an activity where machines now dominate. From the classic IBM engine Deep Blue (Campbell et al., 2002) to modern bots built upon methods such as AlphaZero (Silver et al., 2018), the sheer strength of chess engines has dramatically transformed the chess landscape.1 Yet, while engines excel at move recommendations and evaluations, the crucial question of how to interpret or understand the output of these powerful chess engines is a topic of ongoing research.2  \n1After 50 years, the World Computer Chess Championships was retired in 2024 on the grounds that creating stronger engines no longer held any research value (International Computer Games Association, 2024) .  \n2In a recent interview, five-time world champion Viswanathan Anand remarked “... we [humans] have lost the ability to argue with it [chess engines] . I don’t think we have lost the ability to disagree with it, but we have lost the ability to explain why”(Wait and Anand, 2026) .  \nA wide range of work has studied explaining engine output, including feature learning to explain move recommendations (Puri et al., 2019 ; Fritz and Fürnkranz, 2021 ; Spinnato, 2025), concept extraction that makes such features more human interpretable (McGrath et al., 2022 ; Schut et al., 2025), and commentary generation that expresses explanations in fluent natural language (Jhamtani et al., 2018 ; Zang et al., 2019 ; Kim et al., 2025) .  \nIn this paper, we study chess strategy verbalization: the task of faithfully communicating chess engine-derived strategies in natural language. Our primary focus is to output natural language descriptions of strategies that are pedagogically useful in amplifying and enhancing the strength of players. In contrast, existing work in concept and commentary generation seeks to justify why a given move/variation/strategy “makes sense”, with improvement in quality of play being secondary.  \nA central challenge here is that existing strategy representations are either too detailed or too abstract. Engines typically output search trees and evaluations that are accurate but cumbersome to interpret. Conversely, high-level concepts are more interpretable but lack detail about concrete moves to be taken—both now and in the future. Strategy verbalization must therefore balance informativeness and brevity. Furthermore, even evaluating strategy descriptions requires care, as plausiblesounding descriptions can omit key details, leading to highly suboptimal downstream outcomes.  \nIn our work, we propose frameworks for generating and evaluating chess strategy verbalization, as illustrate","cbCaibLz9jdWmID7","https://ap.wps.com/l/cbCaibLz9jdWmID7","pdf",661060,1,21,"English","en",105,"# Introduction\n# Related Work","[{\"question\":\"What problem does chess strategy verbalization address?\",\"answer\":\"It addresses how to communicate the strategy behind chess engine move suggestions in natural language so humans can understand it and players can use it effectively.\"},{\"question\":\"What framework is proposed to generate strategy descriptions?\",\"answer\":\"The work proposes a pipeline that combines chess engines with LLMs to selectively verbalize important branches of the engine strategy rather than describing everything or only high-level ideas.\"},{\"question\":\"How are the generated strategy descriptions evaluated?\",\"answer\":\"An evaluation framework measures how well a player can follow the description across both main-line and off-main-line opponent responses, using downstream utility rather than surface-text similarity.\"}]",1784209736,53,{"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},"communicating-chess-strategies-in-natural-language","",{"@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/communicating-chess-strategies-in-natural-language/86241/",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},"What problem does chess strategy verbalization address?","Question",{"text":75,"@type":76},"It addresses how to communicate the strategy behind chess engine move suggestions in natural language so humans can understand it and players can use it effectively.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What framework is proposed to generate strategy descriptions?",{"text":80,"@type":76},"The work proposes a pipeline that combines chess engines with LLMs to selectively verbalize important branches of the engine strategy rather than describing everything or only high-level ideas.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the generated strategy descriptions evaluated?",{"text":84,"@type":76},"An evaluation framework measures how well a player can follow the description across both main-line and off-main-line opponent responses, using downstream utility rather than surface-text similarity.","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"]