UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplification
This addresses the problem of complex schema handling in multi-table databases for text-to-SQL systems, offering a scalable solution without data access or fine-tuning, though it is incremental as it builds on existing LLM-based methods.
The paper tackles the challenge of multi-table text-to-SQL generation by introducing UNJOIN, a two-stage framework that simplifies schema representation to improve retrieval and SQL logic generation, achieving state-of-the-art results on SPIDER and BIRD datasets.
Recent advances in large language models (LLMs) have greatly improved Text-to-SQL performance for single-table queries. But, it remains challenging in multi-table databases due to complex schema and relational operations. Existing methods often struggle with retrieving the right tables and columns, generating accurate JOINs and UNIONs, and generalizing across diverse schemas. To address these issues, we introduce UNJOIN, a two-stage framework that decouples the retrieval of schema elements from SQL logic generation. In the first stage, we merge the column names of all tables in the database into a single-table representation by prefixing each column with its table name. This allows the model to focus purely on accurate retrieval without being distracted by the need to write complex SQL logic. In the second stage, the SQL query is generated on this simplified schema and mapped back to the original schema by reconstructing JOINs, UNIONs, and relational logic. Evaluations on SPIDER and BIRD datasets show that UNJOIN matches or exceeds the state-of-the-art baselines. UNJOIN uses only schema information, which does not require data access or fine-tuning, making it scalable and adaptable across databases.