研究人员开发了多种新方法来改进 Text-to-SQL 系统，该系统将自然语言问题转换为 SQL 查询。这些方法侧重于增强模式链接和利用执行反馈来优化 SQL 生成。GATE、ACE-SQL、CAPER 和 SIRIUS-SQL 等技术旨在应对复杂数据库模式和不明确查询带来的挑战，从而生成更准确、更鲁棒的 SQL 输出。 AI
影响 Text-to-SQL 系统的这些进步可以通过实现更准确、更可靠的数据库自然语言查询，显著提高非技术用户的数据可访问性和分析能力。
排序理由 多篇学术论文介绍了 Text-to-SQL 系统的新方法。
AI 生成摘要 · Google Gemini · 来自 8 个来源。 我们如何撰写摘要 →
arXiv:2606.06825v1 Announce Type: cross Abstract: Reinforcement learning has recently shown promise in improving large language models for Text-to-SQL generation, yet existing methods typically optimize one-shot rewards defined over a single SQL state. Such rewards provide limite…
arXiv:2606.05634v1 Announce Type: new Abstract: Real-world text-to-SQL is often under-specified until user phrases are grounded in how the database stores values. Prior work attempts to address this by requiring a semantic layer to specify groundings in advance, but such specific…
arXiv:2606.05906v1 Announce Type: new Abstract: Text-to-SQL maps natural language questions to executable SQL queries. Modern databases often contain large and complex schemas, making schema linking a critical step for accurate SQL generation. Existing methods either rely on full…
Reinforcement learning has recently shown promise in improving large language models for Text-to-SQL generation, yet existing methods typically optimize one-shot rewards defined over a single SQL state. Such rewards provide limited guidance for iterative SQL correction and are in…
Text-to-SQL maps natural language questions to executable SQL queries. Modern databases often contain large and complex schemas, making schema linking a critical step for accurate SQL generation. Existing methods either rely on full-schema generation, which leaves schema linking …
arXiv:2606.03327v1 Announce Type: cross Abstract: Text-to-SQL systems are typically evaluated by query-level execution correctness, but this terminal signal provides little guidance about which intermediate SQL decision caused success or failure. Token-level dense supervision is …
Text-to-SQL systems are typically evaluated by query-level execution correctness, but this terminal signal provides little guidance about which intermediate SQL decision caused success or failure. Token-level dense supervision is also ill-suited: SQL tokens do not align with comp…
arXiv:2606.01246v1 Announce Type: new Abstract: Text-to-SQL on complex schemas is unreliable on a single pass, so recent systems generate multiple SQL candidates and let voting filter out errors. Yet voting alone is not enough, because the multi-candidate recipe has three coupled…