Castle: Causal Cascade Updates in Relational Databases with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Su, Yongye, Zhang, Yucheng, Shi, Zeru, Ribeiro, Bruno, Bertino, Elisa
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909911821058048
author Su, Yongye
Zhang, Yucheng
Shi, Zeru
Ribeiro, Bruno
Bertino, Elisa
author_facet Su, Yongye
Zhang, Yucheng
Shi, Zeru
Ribeiro, Bruno
Bertino, Elisa
contents This work introduces Castle, the first framework for schema-only cascade update generation using large language models (LLMs). Despite recent advances in LLMs for Text2SQL code generation, existing approaches focus primarily on SELECT queries, neglecting the challenges of SQL update operations and their ripple effects. Traditional CASCADE UPDATE constraints are static and unsuitable for modern, denormalized databases, which demand dynamic, context-aware updates. Castle enables natural language instructions to trigger multi-column, causally consistent SQL UPDATE statements, without revealing table content to the model. By framing UPDATE SQL generation as a divide-and-conquer task with LLMs' reasoning capacity, Castle can determine not only which columns must be directly updated, but also how those updates propagate through the schema, causing cascading updates -- all via nested queries and substructures that ensure data confidentiality. We evaluate it on real-world causal update scenarios, demonstrating its ability to produce accurate SQL updates, and thereby highlighting the reasoning ability of LLMs in automated DBMS.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14762
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Castle: Causal Cascade Updates in Relational Databases with Large Language Models
Su, Yongye
Zhang, Yucheng
Shi, Zeru
Ribeiro, Bruno
Bertino, Elisa
Databases
This work introduces Castle, the first framework for schema-only cascade update generation using large language models (LLMs). Despite recent advances in LLMs for Text2SQL code generation, existing approaches focus primarily on SELECT queries, neglecting the challenges of SQL update operations and their ripple effects. Traditional CASCADE UPDATE constraints are static and unsuitable for modern, denormalized databases, which demand dynamic, context-aware updates. Castle enables natural language instructions to trigger multi-column, causally consistent SQL UPDATE statements, without revealing table content to the model. By framing UPDATE SQL generation as a divide-and-conquer task with LLMs' reasoning capacity, Castle can determine not only which columns must be directly updated, but also how those updates propagate through the schema, causing cascading updates -- all via nested queries and substructures that ensure data confidentiality. We evaluate it on real-world causal update scenarios, demonstrating its ability to produce accurate SQL updates, and thereby highlighting the reasoning ability of LLMs in automated DBMS.
title Castle: Causal Cascade Updates in Relational Databases with Large Language Models
topic Databases
url https://arxiv.org/abs/2511.14762