通过结构差异感知记忆进化，提升复杂文本转SQL的准确性
SDAM: Structure-Difference-Aware Memory Evolution for Complex Text-to-SQL
- 构建结构差异感知推理树识别潜在错误
- 通过矛盾感知反思提取深层语义规则
- 基于模式的内存演化增强数据库结构对齐
文本转SQL旨在将自然语言问题转化为可执行的SQL查询。尽管基于记忆的智能体系统提升了复杂SQL生成能力，但现有记忆设计忽视历史经验，存在结构分析薄弱、语义理解浅层化和模式对齐不佳等问题。为此，我们提出SDAM：通过结构差异感知推理树识别潜在错误，利用矛盾感知反思提取深层语义规则，并采用基于模式的记忆演化机制实现记忆与数据库模式的绑定，以增强结构一致性。我们将SDAM集成到名为SDAM-SQL的文本转SQL框架中。实验表明，SDAM-SQL在BIRD-dev和Spider-test上分别较主流方法提升2.0和0.4，验证了其有效性。
原文摘要 · Abstract (English)
Text-to-SQL aims to convert natural language questions into executable SQL queries. While memory-based agent system improves complex SQL generation, existing memory design neglect historical experience and suffer from weak structure analysis, shallow semantic understanding, and poor schema alignment. To address these challenges, we propose SDAM. Specifically, SDAM identifies potential errors via a structure-difference aware reasoning tree, extracts deep semantic rules through contradiction-aware reflection, and enhances structural consistency using a schema-grounded memory evolution mechanism to bind memory with database schemas. We integrate SDAM into a Text-to-SQL framework named SDAM-SQL. Experiment shows that SDAM-SQL achieves 2.0 and 0.4 improvement on BIRD-dev and Spider-test compared with mainstream Text-to-SQL methods, showing the effectiveness of SDAM-SQL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。