Document Type
Conference Proceeding
Publication Title
Advances in Database Technology (Proceedings of the 28th International Conference on Extending Database Technology)
Abstract
We present LogicLM, an OLAP-style interactive data analysis system that leverages large language models (LLMs) and is configured using Logica, an enhanced logic programming language with aggregation support that compiles to SQL. LogicLM uses an LLM to translate natural language queries by end users into executable code for automatically generating data visualizations. For each natural-language query, LogicLM provides a verifiable OLAP-based configuration that users can view and modify to help ensure results are reliable and accurate. This configuration, with measures, dimensions, and filters defined as logical predicates, offers a unified and user-friendly approach to naturallanguage data exploration, while keeping end users in control of the analysis process.
Pages
1086-1089
html
DOI
https://doi.org/10.48786/edbt.2025.95
Publisher
OpenProceedings.org
Volume
28
Issue
3
Publication Date
3-10-2025
Keywords
Software, Information Systems, Computer Science Applications
Disciplines
Computer Sciences | Data Science
ISBN
978-3893180998
ISSN
2367-2005
Recommended Citation
Skvortsov, E., Mirjafari, S., Garg, O., Xia, Y., Bowers, S., & Ludäscher, B.. (2025). LogicLM: Robust Application of Large Language Models with Logic Programming for Data Analytics. 1086–1089. https://doi.org/10.48786/edbt.2025.95
Upload File
wf_yes
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Comments
This content was originally presented at the 28th International Conference on Extending Database Technology (EDBT), held from March 25-28, 2025, in Barcelona, Spain.