"Question→SQL→Wiki" Dynamic Wiki Graph for NL2SQL

Abstract

To bridge the semantic gap in NL2SQL (Natural Language to SQL) tasks, this study proposes a "Question→SQL→Wiki" framework that leverages a dynamic Wiki Graph as an intermediate reasoning layer. Departing from conventional NL2SQL approaches that rely solely on end-to-end mapping, our method utilizes Large Language Models (LLMs) to translate natural language questions into SQL queries, subsequently parsing these queries to construct a context-specific Wiki Graph. Unlike static knowledge graphs, this architecture emulates the associative and incremental nature of encyclopedic systems, explicitly modeling both database schemas and query-specific logic. By transforming abstract linguistic intent into a structured, wiki-style representation prior to execution, the framework significantly enhances schema linking and logical correctness. Experiments demonstrate that this graph-augmented paradigm improves the accuracy and robustness of NL2SQL systems, offering a scalable solution for complex query generation over relational databases.