AmbiSQL: Interactive Ambiguity Detection and Resolution for Text-to-SQL

TL;DR

AmbiSQL is an interactive system that detects ambiguities in natural language questions for Text-to-SQL translation, guiding users to clarify intent and improve SQL accuracy, addressing a key challenge in LLM-based systems.

Contribution

It introduces a fine-grained ambiguity taxonomy and an interactive disambiguation approach integrated with a commercial Text-to-SQL backend.

Findings

Disambiguation improves SQL generation quality.

40 ambiguous queries from real-world benchmarks demonstrate effectiveness.

User-guided clarification reduces errors in LLM-based Text-to-SQL systems.

Abstract

Text-to-SQL systems translate natural language questions into SQL queries, providing substantial value for non-expert users. While large language models (LLMs) show promising results for this task, they remain error-prone. Query ambiguity has been recognized as a major obstacle in LLM-based Text-to-SQL systems, leading to misinterpretation of user intent and inaccurate SQL generation. To this end, we present AmbiSQL, an interactive system that automatically detects query ambiguities and guides users through intuitive multiple-choice questions to clarify their intent. It introduces a fine-grained ambiguity taxonomy for identifying ambiguities arising from both database elements and LLM reasoning, and subsequently incorporates user feedback to rewrite ambiguous questions. In this demonstration, AmbiSQL is integrated with XiYan-SQL, our commercial Text-to-SQL backend. We provide 40 ambiguous queries collected from two real-world benchmarks that SIGMOD'26 attendees can use to explore how disambiguation improves SQL generation quality. Participants can also apply the system to their own databases and natural language questions. The codebase and demo video are available at: https://github.com/JustinzjDing/AmbiSQL and https://www.youtube.com/watch?v=rbB-0ZKwYkk.