Interactive Text-to-SQL via Expected Information Gain for Disambiguation

2025-07-08

AI Summary

Text-to-SQL systems frequently generate incorrect SQL queries on complex, real-world databases due to inherent ambiguity in natural language. To address this, we propose an interactive disambiguation framework that models SQL generation as probabilistic inference over multiple candidate queries. At each interaction step, the system dynamically selects the most discriminative clarification question—based on expected information gain—to progressively refine user intent. Our approach integrates probabilistic modeling, natural language processing, and interactive learning, thereby avoiding premature convergence common in single-step generation paradigms. Experiments demonstrate that our method substantially reduces ambiguity and significantly improves execution accuracy across multiple benchmarks, including Spider and CoSQL. The framework enhances both the robustness and practical applicability of semantic parsing in realistic database environments.

Technology Category

Reasoning under Uncertainty: Relational Probabilistic ModelsData Mining & Knowledge Management: Intelligent Query ProcessingNatural Language Processing: Question Answering

Application Category

Search and Retrieval-Augmented AI: Assisted, interactive, and conversational searchSemantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsUser Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Relational databases are foundational to numerous domains, including business intelligence, scientific research, and enterprise systems. However, accessing and analyzing structured data often requires proficiency in SQL, which is a skill that many end users lack. With the development of Natural Language Processing (NLP) technology, the Text-to-SQL systems attempt to bridge this gap by translating natural language questions into executable SQL queries via an automated algorithm. Yet, when operating on complex real-world databases, the Text-to-SQL systems often suffer from ambiguity due to natural ambiguity in natural language queries. These ambiguities pose a significant challenge for existing Text-to-SQL translation systems, which tend to commit early to a potentially incorrect interpretation. To address this, we propose an interactive Text-to-SQL framework that models SQL generation as a probabilistic reasoning process over multiple candidate queries. Rather than producing a single deterministic output, our system maintains a distribution over possible SQL outputs and seeks to resolve uncertainty through user interaction. At each interaction step, the system selects a branching decision and formulates a clarification question aimed at disambiguating that aspect of the query. Crucially, we adopt a principled decision criterion based on Expected Information Gain to identify the clarification that will, in expectation, most reduce the uncertainty in the SQL distribution.

Problem

• Resolving ambiguity in Text-to-SQL translation systems
• Enabling interactive disambiguation via user clarification
• Optimizing query uncertainty reduction using Expected Information Gain

Innovation

• Interactive Text-to-SQL framework for disambiguation
• Probabilistic reasoning over multiple candidate queries
• Expected Information Gain for uncertainty reduction