[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84701-en":3,"doc-seo-84701-105":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},84701,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","TabQueryBench：面向合成表格数据的以查询为中心基准","Synthetic tabular data enable data sharing, access-restricted model development, and rapid prototyping of analytical workflows, yet common evaluations emphasize distributional similarity, correlations, privacy, and downstream utility. TabQueryBench addresses a gap by benchmarking query-centric fidelity using SQL-shaped analytical queries as structure-aware assessors. From 12 public query sources, it builds 44 reusable cross-domain templates and instantiates them with a policy-guided template-to-SQL pipeline over 49 datasets and 11 generative models. Results reveal limits on query-centric accuracy, high-cardinality discretes, local queries, tail fidelity, and a fidelity–cost tradeoff.","TabQueryBench: A Query-Centric Benchmark for Synthetic Tabular Data  \nJialin Zhang†,¶ Fenghao Dong‡ Yajie Zhou§  \nVyas Sekar‡ Shinan Liu†  \n†University of Hong Kong ¶ Tongji University ‡Carnegie Mellon University § University of Maryland, College Park  \n[fredzhang@tongji.edu.cn](fredzhang@tongji.edu.cn) , {fenghaod, [vsekar}@andrew.cmu.edu](vsekar}@andrew.cmu.edu) , [leszhou@umd.edu](leszhou@umd.edu) , shinan6@hku.hk  \narXiv :2607 .03926v 1 [ cs .DB] 4 Jul 2026  \nABSTRACT  \nSynthetic tabular data support use cases like data sharing, model development under access restrictions, and rapid prototyping of analytical workflows. Modern generative models are evaluated by their statistical similarity, correlation structure, privacy, and downstream machine-learning utility. However, such evaluations leave a gap: they rarely test the structure that matters for analytical queries. We present TabQueryBench1 , a query-centric benchmark that uses SQL-shaped analytical queries as structural assessors for synthetic data fidelity. It provides an extensible foundation for query-centric synthetic-data evaluation. From 12 public sources of analytical queries, TabQueryBench taxonomizes recurring crossdomain logic into 44 reusable query templates and grounds them to each dataset via a policy-guided template-to-SQL pipeline. This makes queries schema-aware while preserving comparability across generative models. Across 49 datasets and 11 generative models, it activates 10–12 templates per dataset, producing more than 100 executable SQL queries per dataset. Our systematic experiments show five main patterns. First, current tabular generative models can have good distance-based fidelity, but they still fall short on query-centric fidelity: RealTabFormer achieves the highest query-centric fidelity, but it only reaches 0 . 75± 0 . 15 (REAL data score is 1 . 00) . Second, tabular generative models struggle with very high-cardinality discrete support. Third, SOTA generative models preserve good global conditional query-centric fidelity, but fail more on local queries. Fourth, tail fidelity deteriorates as queries move toward the extreme tail; even the best generative model recovers only about 40.7% of real rare values. Finally, there is a fidelity-cost tradeoff in tabular data generation: BayesNet offers the strongest tradeoff, with slightly lower query-centric fidelity but much lower generation cost.  \n1 INTRODUCTION  \nSynthetic tabular data are now used for data sharing [5, 30, 46], model development under access restrictions [5, 8, 46], and rapid algorithm or system prototyping [21, 36, 45, 69] . As these use cases mature, benchmarking matters more, because what makes synthetic data useful in these settings is not distributional resemblance alone, but the preservation of the analytical properties that the database community has long treated as the core measure of data quality [9, 14, 31, 42, 48, 50, 65, 66] .  \nSynthetic data consumers often care less about synthetic records as standalone samples. They care more about the functions that those records make possible. A useful synthetic dataset does not merely approximate marginal distributions. It should ideally expose a  \n1TabQueryBench is open-sourced at [https://github.com/TabQueryBench/](https://github.com/TabQueryBench/)[ ](https://github.com/TabQueryBench/)TabQueryBench and [https://huggingface.co/datasets/TabQueryBench2026/](https://huggingface.co/datasets/TabQueryBench2026/)[ ](https://huggingface.co/datasets/TabQueryBench2026/)[TabQueryBench/tree/main](TabQueryBench/tree/main)  \ncontrolled approximation of hidden dataset attributes, such as table structure, column relationships, valid joins, and executable queries [36, 45, 69] . This structural view is important for (1) collaboration, where a partner wants to preview the structure and quality of a sensitive dataset before accessing the real data [5, 46]; (2) software and data-system testing, where engineers need realistic schemas, constraints, e","cbCaipxAsewM8EQn","https://ap.wps.com/l/cbCaipxAsewM8EQn","pdf",1563617,1,17,"English","en",105,"# Abstract\n# Introduction\n## Use cases for synthetic tabular data\n## Limitations of existing evaluation methods\n## Query-centric benchmarking idea: TabQueryBench","[{\"question\":\"TabQueryBench的核心目标是什么？\",\"answer\":\"TabQueryBench提出一种以查询为中心的基准，用SQL形态的分析查询作为结构化评测器，评估合成表格数据在分析查询层面的保真度。\"},{\"question\":\"TabQueryBench如何生成可执行的评测SQL查询？\",\"answer\":\"从公开分析查询源提取跨领域逻辑模板（共44个），并通过策略引导的template-to-SQL流水线，将模板在每个数据集上实例化，产生多条可执行SQL查询。\"},{\"question\":\"实验结果表明当前表格生成模型有哪些主要不足？\",\"answer\":\"实验显示：模型可能在距离类指标上表现较好，但在以查询为中心的保真度上仍不足；同时对高基数离散支持、局部查询以及查询落在极端尾部时的尾部保真度更差，并存在保真度与生成成本的权衡。\"}]",1784197736,43,{"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},"tabquerybench-a-query-centric-benchmark-for-synthetic-tabular-data","",{"@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/tabquerybench-a-query-centric-benchmark-for-synthetic-tabular-data/84701/",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},"TabQueryBench的核心目标是什么？","Question",{"text":75,"@type":76},"TabQueryBench提出一种以查询为中心的基准，用SQL形态的分析查询作为结构化评测器，评估合成表格数据在分析查询层面的保真度。","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"TabQueryBench如何生成可执行的评测SQL查询？",{"text":80,"@type":76},"从公开分析查询源提取跨领域逻辑模板（共44个），并通过策略引导的template-to-SQL流水线，将模板在每个数据集上实例化，产生多条可执行SQL查询。",{"name":82,"@type":73,"acceptedAnswer":83},"实验结果表明当前表格生成模型有哪些主要不足？",{"text":84,"@type":76},"实验显示：模型可能在距离类指标上表现较好，但在以查询为中心的保真度上仍不足；同时对高基数离散支持、局部查询以及查询落在极端尾部时的尾部保真度更差，并存在保真度与生成成本的权衡。","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"]