Jul 2026· Anais do XXV Workshop em Desempenho de Sistemas Computacionais e de Comunicação (WPerformance 2026)· pp. 13-23· 0 citations· 8 references
TL;DR
Validation through nine use cases demonstrates the architecture is functionally effective, generating accurate database queries matching ground-truth and identifying invalid relationships without exposing raw transactional data to the LLM.
Abstract
This research addresses organizational data transformation by integrating Information Science (IS) and Natural Language Processing (NLP).We argue that Large Language Model (LLM) failures in data interaction tasks (instantiated via text-to-sql), such as hallucinations, stem from applications detached from information governance. We propose an interdisciplinary architecture employing a Knowledge Graph as an Intelligent Proxy to centralize metadata and ontologies. Validation through nine use cases demonstrates the architecture is functionally effective, generating accurate database queries matching ground-truth and identifying invalid relationships without exposing raw transactional data to the LLM.
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.
Udesh Kumarasinghe, Tyler Liu, Ahmed R. Mahmood et al.· Proceedings of the VLDB Endo...· 0 citations
Large Language Models (LLMs) are being increasingly used in everyday applications. A major challenge in the context of LLMs or Artificial Intelligence (AI) in general is to ensure privacy when using them, meaning that personally identifiable information (PII) is removed from any text that enters an LLM. These challenge...
An intelligent Q&A system based on a traceable knowledge graph and prompt enhancement technology that guides large language models to accurately output corresponding page URLs in response to user queries is proposed.
A literature-based architectural framework for reliable knowledge retrieval systems that separates external knowledge management from LLM-based reasoning and generation is developed and indicates that reliable LLM deployment should be treated as an end-to-end architectural problem rather than solely a model-performance...
Bharat Kumar Reddy Karumuri· International Journal of Eng...· 0 citations
A modular text-to-SQL pipe-line is presented for a real Intel telemetry use case and an ablation study of prompt augmentation, schema annotations, few-shot examples, and iterative SQL validation under varying schema exposure settings is conducted.
O. Bouattour, J. Weiner, Fabian Wenz et al.· 0 citations
CHAD-ASK is introduced, a novel plugin for Morph-KGC, a Python-based RML data conversion engine that converts raw tabular survey data into fully compliant RDF triples, allowing researchers to perform complex metadata conversion without direct interaction with code or mapping languages.
Sebastian Barzaghi, Arianna Moretti, Ivan Heibi et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
