Retrieval and Augmentation of Domain Knowledge for Text-to-SQL Semantic Parsing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914071813554176 |
|---|---|
| author | Patwardhan, Manasi Agarwal, Ayush Bhaisaheb, Shabbirhussain Arora, Aseem Vig, Lovekesh Sarawagi, Sunita |
| author_facet | Patwardhan, Manasi Agarwal, Ayush Bhaisaheb, Shabbirhussain Arora, Aseem Vig, Lovekesh Sarawagi, Sunita |
| contents | The performance of Large Language Models (LLMs) for translating Natural Language (NL) queries into SQL varies significantly across databases (DBs). NL queries are often expressed using a domain specific vocabulary, and mapping these to the correct SQL requires an understanding of the embedded domain expressions, their relationship to the DB schema structure. Existing benchmarks rely on unrealistic, ad-hoc query specific textual hints for expressing domain knowledge. In this paper, we propose a systematic framework for associating structured domain statements at the database level. We present retrieval of relevant structured domain statements given a user query using sub-string level match. We evaluate on eleven realistic DB schemas covering diverse domains across five open-source and proprietary LLMs and demonstrate that (1) DB level structured domain statements are more practical and accurate than existing ad-hoc query specific textual domain statements, and (2) Our sub-string match based retrieval of relevant domain statements provides significantly higher accuracy than other retrieval approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_02394 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Retrieval and Augmentation of Domain Knowledge for Text-to-SQL Semantic Parsing Patwardhan, Manasi Agarwal, Ayush Bhaisaheb, Shabbirhussain Arora, Aseem Vig, Lovekesh Sarawagi, Sunita Computation and Language I.2.7; H.2.3; H.2.8 The performance of Large Language Models (LLMs) for translating Natural Language (NL) queries into SQL varies significantly across databases (DBs). NL queries are often expressed using a domain specific vocabulary, and mapping these to the correct SQL requires an understanding of the embedded domain expressions, their relationship to the DB schema structure. Existing benchmarks rely on unrealistic, ad-hoc query specific textual hints for expressing domain knowledge. In this paper, we propose a systematic framework for associating structured domain statements at the database level. We present retrieval of relevant structured domain statements given a user query using sub-string level match. We evaluate on eleven realistic DB schemas covering diverse domains across five open-source and proprietary LLMs and demonstrate that (1) DB level structured domain statements are more practical and accurate than existing ad-hoc query specific textual domain statements, and (2) Our sub-string match based retrieval of relevant domain statements provides significantly higher accuracy than other retrieval approaches. |
| title | Retrieval and Augmentation of Domain Knowledge for Text-to-SQL Semantic Parsing |
| topic | Computation and Language I.2.7; H.2.3; H.2.8 |
| url | https://arxiv.org/abs/2510.02394 |