arXiv：cs.CL· Hy Nguyen, Nabi Rezvani, Robin Vujanic·· 4 小时前AI 评分40
AptMQL-Bench：从 Text-to-SQL 到 Text-to-MQL 的访问模式 Schema 设计与无损数据迁移
AptMQL-Bench: From Text-to-SQL to Text-to-MQL via Access-Pattern Schema Design and Data-Preserving Migration
AI 导读
研究团队提出由编码智能体驱动、带人工验证的转换流程，将 BIRD 基准转为面向文档数据库的 Text-to-MQL 基准 AptMQL-Bench，包含 21 个文档型数据库和 3,186 条自然语言请求及对应 MQL 查询，数据从 SQLite 无损迁移。
正文
Abstract:Document databases such as MongoDB are core infrastructure for modern applications, and natural-language interfaces to them---text-to-MQL---would let non-experts query complex, semi-structured data without mastering the query language. Progress on this task depends on high-quality benchmarks, which are most practically obtained by converting an existing text-to-SQL benchmark to the document setting. Unfortunately, existing efforts rely on heuristics for mechanical conversion: the document schema mirrors the relational foreign-key graph, and each query mirrors its source SQL. As a result in our experiments, these approaches fail to migrate 6 of 21 BIRD databases outright, silently drop up to 25.9\% of rows on others, and yield schemas whose ground-truth queries run over an order of magnitude slower as the data scales. We instead propose a conversion pipeline, driven by coding agents with human-in-the-loop verification, that designs each document schema from expected access patterns and rewrites queries to be MongoDB-native. Applying it to BIRD, we build an access-pattern-based text-to-MQL benchmark (AptMQL-Bench). It includes 21 document-oriented databases, 3,186 natural-language requests, and their associated MQL queries---whose databases are migrated from SQLite without data loss and scale efficiently. The strongest model, Claude Opus 4.5, achieves only 57.38\% accuracy without external knowledge evidence and 70.34\% with it. This indicates that realistic text-to-MQL generation remains challenging.
| Subjects: | Computation and Language (cs.CL); Databases (cs.DB) |
| Cite as: | arXiv:2610.02770 [cs.CL] |
| (or arXiv:2610.02770v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02770 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ngoc Gia Hy Nguyen [view email]
[v1]
Fri, 2 Oct 2026 03:54:06 UTC (1,442 KB)
来源：arXiv：cs.CL · arxiv.org