发表机构
Harbin Institute of Technology（哈尔滨工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有文本转SQL记忆设计的缺陷，提出SDAM方法，集成至SDAM-SQL框架，在BIRD-dev和Spider-test数据集上实现指标提升，验证了方法有效性。
AI 中文摘要
文本转SQL旨在将自然语言问题转换为可执行的SQL查询。尽管基于记忆的智能体系统可提升复杂SQL生成效果，但现有记忆设计忽视历史经验，存在结构分析薄弱、语义理解浅显、模式对齐不佳等问题。为解决这些挑战，我们提出SDAM：该方法通过结构差异感知推理树识别潜在错误，借助矛盾感知反思提取深层语义规则，还采用基于模式的记忆演化机制增强结构一致性，将记忆与数据库模式绑定。我们将SDAM集成至名为SDAM-SQL的文本转SQL框架中。实验表明，SDAM-SQL在BIRD-dev和Spider-test数据集上较主流文本转SQL方法分别提升2.0和0.4，验证了其有效性。
英文摘要
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.
Comments19 pages, 5 figures, 12tables
