Enhancing SQL Query Generation with Neurosymbolic Reasoning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916369460625408 |
|---|---|
| author | Princis, Henrijs David, Cristina Mycroft, Alan |
| author_facet | Princis, Henrijs David, Cristina Mycroft, Alan |
| contents | Neurosymbolic approaches blend the effectiveness of symbolic reasoning with the flexibility of neural networks. In this work, we propose a neurosymbolic architecture for generating SQL queries that builds and explores a solution tree using Best-First Search, with the possibility of backtracking. For this purpose, it integrates a Language Model (LM) with symbolic modules that help catch and correct errors made by the LM on SQL queries, as well as guiding the exploration of the solution tree. We focus on improving the performance of smaller open-source LMs, and we find that our tool, Xander, increases accuracy by an average of 10.9% and reduces runtime by an average of 28% compared to the LM without Xander, enabling a smaller LM (with Xander) to outperform its four-times larger counterpart (without Xander). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_13888 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing SQL Query Generation with Neurosymbolic Reasoning Princis, Henrijs David, Cristina Mycroft, Alan Databases Artificial Intelligence Software Engineering I.2 Neurosymbolic approaches blend the effectiveness of symbolic reasoning with the flexibility of neural networks. In this work, we propose a neurosymbolic architecture for generating SQL queries that builds and explores a solution tree using Best-First Search, with the possibility of backtracking. For this purpose, it integrates a Language Model (LM) with symbolic modules that help catch and correct errors made by the LM on SQL queries, as well as guiding the exploration of the solution tree. We focus on improving the performance of smaller open-source LMs, and we find that our tool, Xander, increases accuracy by an average of 10.9% and reduces runtime by an average of 28% compared to the LM without Xander, enabling a smaller LM (with Xander) to outperform its four-times larger counterpart (without Xander). |
| title | Enhancing SQL Query Generation with Neurosymbolic Reasoning |
| topic | Databases Artificial Intelligence Software Engineering I.2 |
| url | https://arxiv.org/abs/2408.13888 |