UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910964897546240 |
|---|---|
| author | Ganesan, Poojah Jha, Rajat Aayush Roth, Dan Gupta, Vivek |
| author_facet | Ganesan, Poojah Jha, Rajat Aayush Roth, Dan Gupta, Vivek |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_18122 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplification Ganesan, Poojah Jha, Rajat Aayush Roth, Dan Gupta, Vivek Computation and Language 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. |
| title | UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplification |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.18122 |