EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge 文章

ArXiv CS.CL2026-06-03NEWSen作者: Chengxi Liao, Tao Xu, Zulong Chen, Chuanfei Xu, Yiyan Wang, Xinyun Wang, Yanlong Zhang, Xiaojun Chen, Zhibo Yang, Zeyi Wen

摘要

arXiv:2606.03363v1 Announce Type: new Abstract: Text-to-SQL enables natural language access to databases, and recent LLMs have substantially advanced its capabilities. Existing benchmarks such as Spider, BIRD, and Spider~2.0 evaluate schema generalization, large-scale databases, and realistic workflows, but largely overlook enterprise scenarios where SQL generation depends on private business knowledge, such as internal metrics, reporting conventions, and organizational rules. We introduce EntSQL, an enterprise-oriented Text-to-SQL benchmark for evaluating long-context grounding over proprietary business documents. EntSQL contains 1,066 aligned Chinese-English semantic examples across five business domains, with most examples requiring domain knowledge beyond the question and schema and involving complex SQL structures. On English inputs, the best evaluated system reaches only 15.

相关事件

暂无数据

相关公司

暂无数据

相关人物

暂无数据