Data-Aware Socratic Query Refinement in Database Systems

TL;DR

This paper introduces Data-Aware Socratic Guidance (DASG), a dialogue-based framework that actively clarifies natural language queries in database systems to improve accuracy and efficiency through cost-aware interactions.

Contribution

It presents a novel interactive query refinement method that integrates clarification as a core database operation, optimizing dialogue decisions based on expected cost reductions.

Findings

Improved query precision in multiple datasets.

Efficient clarification reduces ambiguity without excessive interaction.

Demonstrates active system participation in query formulation.

Abstract

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.