An LLM-Based Approach for Insight Generation in Data Analysis
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929761324892160 |
|---|---|
| author | Pérez, Alberto Sánchez Boukhary, Alaa Papotti, Paolo Lozano, Luis Castejón Elwood, Adam |
| author_facet | Pérez, Alberto Sánchez Boukhary, Alaa Papotti, Paolo Lozano, Luis Castejón Elwood, Adam |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_11664 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An LLM-Based Approach for Insight Generation in Data Analysis Pérez, Alberto Sánchez Boukhary, Alaa Papotti, Paolo Lozano, Luis Castejón Elwood, Adam Artificial Intelligence Computation and Language Databases 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. |
| title | An LLM-Based Approach for Insight Generation in Data Analysis |
| topic | Artificial Intelligence Computation and Language Databases |
| url | https://arxiv.org/abs/2503.11664 |