让数据库主动提问澄清模糊查询，提升准确率同时不增加负担
Data-Aware Socratic Query Refinement in Database Systems
- 将对话澄清作为优化决策，只在收益大于成本时提问
- 通过语义模糊度、模式匹配信心等指标量化查询歧义
- 适合需要高精度自然语言查询的交互式数据分析场景
本文提出数据感知苏格拉底引导（DASG），一种基于对话的查询增强框架，将交互式澄清作为数据库系统的一类核心操作，以解决自然语言查询中的歧义问题。DASG将对话视为优化决策，仅当预期执行成本降低超过交互开销时才提出澄清问题。系统通过语言模糊性、模式对齐置信度以及关系型与向量后端的预估成本来量化歧义。算法结合语义相关性、目录信息增益和潜在成本削减，选择最优澄清策略。我们在三个数据集上评估该框架，结果表明DASG在保持效率的同时提升了查询精度，建立了一种系统主动参与查询构建的协作式分析范式。
原文摘要 · Abstract (English)
In this paper, we propose Data-Aware Socratic Guidance (DASG), a dialogue-based query enhancement framework that embeds \linebreak interactive clarification as a first-class operator within database systems to resolve ambiguity in natural language queries. DASG treats dialogue as an optimization decision, asking clarifying questions only when the expected execution cost reduction exceeds the interaction overhead. The system quantifies ambiguity through linguistic fuzziness, schema grounding confidence, and projected costs across relational and vector backends. Our algorithm selects the optimal clarifications by combining semantic relevance, catalog-based information gain, and potential cost reduction. We evaluate our proposed framework on three datasets. The results show that DASG demonstrates improved query precision while maintaining efficiency, establishing a cooperative analytics paradigm where systems actively participate in query formulation rather than passively translating user requests.
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。