Generating insightful and actionable information from databases is critical in data analysis. This paper introduces a novel approach using Large Language Models (LLMs) to automatically generate textual insights. Given a multi-table database as input, our method leverages LLMs to produce concise, text-based insights that reflect interesting patterns in the tables. Our framework includes a Hypothesis Generator to formulate domain-relevant questions, a Query Agent to answer such questions by generating SQL queries against a database, and a Summarization module to verbalize the insights. The insights are evaluated for both correctness and subjective insightfulness using a hybrid model of human judgment and automated metrics. Experimental results on public and enterprise databases demonstrate that our approach generates more insightful insights than other approaches while maintaining correctness.
@article{arxiv.2503.11664,
title = {An LLM-Based Approach for Insight Generation in Data Analysis},
author = {Alberto Sánchez Pérez and Alaa Boukhary and Paolo Papotti and Luis Castejón Lozano and Adam Elwood},
journal= {arXiv preprint arXiv:2503.11664},
year = {2025}
}