Aug 2026· Proceedings of the VLDB Endowment· Vol 19, pp. 4782-4785· 0 citations· 14 references
TL;DR
iPDB is demonstrated, a system that supports in-database LLM inference using an extended declarative SQL syntax and new optimizations that result in efficient query processing of LLM-enabled SQL queries that outperform state-of-the-art systems.
Abstract
Structured Query Language (SQL) has remained the standard query language for databases, and is highly optimized for processing structured data. However, it is inefficient for applications that leverage the capabilities of large language models (LLMs) to comprehend and extract semantic information from structured and unstructured data. This results in complex engineering and multiple data migration operations that transfer data between the data source and the LLM inference platform to couple them. We demonstrate iPDB, a system that supports in-database LLM inference using an extended declarative SQL syntax and new optimizations that result in efficient query processing of LLM-enabled SQL queries that outperform state-of-the-art systems.
The empirical findings indicate that factorizing ML-aware SQL generation into four distinct stages—query routing, structured intent extraction, model or function selection, and template-guided SQL synthesis—enhances semantic controllability and token efficiency when formulating predictive natural language queries over...
SafeQL is proposed, a search-based refinement paradigm that redefines the role of the DBMS as an active guide in the refinement process, and significantly improves execution accuracy and efficiency compared to regeneration-based methods.
Geonho Lee, Min-Soo Kim· Proceedings of the VLDB Endo...· 0 citations
This paper revisits the connection between Datalog and relational databases, advocating recursive SQL as a backend for Datalog evaluation, and presents a compilation framework that translates Datalog programs, particularly those in the Linear Datalog fragment, into equivalent recursive SQL queries.
Amir Shaikhha, Anna Herlihy, Hung Q. Ngo· 0 citations
Data platforms have evolved by making data-intensive workloads native: SQL and query optimizers eliminated bespoke data-retrieval programs; Lakehouses added first-class support for ML training and serving over the same data. Prescriptive analytics (computing optimal actions subject to constraints over data) is equally...
Matteo Brucato, Fjodor Kholodkov, Soren Little et al.· Proceedings of the VLDB Endo...· 2 citations
AI-native systems are becoming core components of modern data-centric infrastructures, where artificial intelligence is embedded directly into data access, processing, and interpretation workflows. Despite advances in large language models, most research focuses on natural language to SQL generation, while the inverse...
