Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models

📅 2024-12-10
🏛️ arXiv.org
📈 Citations: 1
Influential: 0
📄 PDF

career value

166K/year
🤖 AI Summary
Data analysts face two primary bottlenecks: SQL generation and visualization selection. Existing approaches exhibit significant limitations in comprehending complex schemas, modeling ambiguous user intents, generalizing across domains, and enabling end-to-end text-to-visualization translation. This paper introduces TiInsight, a domain-agnostic system for automated exploratory data analysis (EDA). Its core contributions are: (1) Hierarchical Data Context (HDC) modeling, which enhances large language models (e.g., GPT-4) to reason over heterogeneous schemas and imprecise user intents; and (2) an end-to-end four-stage EDA pipeline—intent clarification, TiSQL (text-to-SQL), TiChart (automated chart recommendation), and GUI integration. TiSQL achieves 86.3% execution accuracy on Spider and sets a new state-of-the-art on Bird; user studies demonstrate superior performance over human experts. The system’s API is open-sourced and deployed in PingCAP’s production environment.

Technology Category

Application Category

📝 Abstract
Exploratory data analysis (EDA), coupled with SQL, is essential for data analysts involved in data exploration and analysis. However, data analysts often encounter two primary challenges: (1) the need to craft SQL queries skillfully, and (2) the requirement to generate suitable visualization types that enhance the interpretation of query results. Due to its significance, substantial research efforts have been made to explore different approaches to address these challenges, including leveraging large language models (LLMs). However, existing methods fail to meet real-world data exploration requirements primarily due to (1) complex database schema; (2) unclear user intent; (3) limited cross-domain generalization capability; and (4) insufficient end-to-end text-to-visualization capability. This paper presents TiInsight, an automated SQL-based cross-domain exploratory data analysis system. First, we propose hierarchical data context (i.e., HDC), which leverages LLMs to summarize the contexts related to the database schema, which is crucial for open-world EDA systems to generalize across data domains. Second, the EDA system is divided into four components (i.e., stages): HDC generation, question clarification and decomposition, text-to-SQL generation (i.e., TiSQL), and data visualization (i.e., TiChart). Finally, we implemented an end-to-end EDA system with a user-friendly GUI interface in the production environment at PingCAP. We have also open-sourced all APIs of TiInsight to facilitate research within the EDA community. Through extensive evaluations by a real-world user study, we demonstrate that TiInsight offers remarkable performance compared to human experts. Specifically, TiSQL achieves an execution accuracy of 86.3% on the Spider dataset using GPT-4. It also demonstrates state-of-the-art performance on the Bird dataset.
Problem

Research questions and friction points this paper is trying to address.

Automate SQL-based cross-domain exploratory data analysis.
Enhance data visualization through text-to-SQL and text-to-visualization.
Improve cross-domain generalization and user intent clarity in EDA.
Innovation

Methods, ideas, or system contributions that make the work stand out.

LLMs for schema context summarization
End-to-end text-to-visualization system
Hierarchical data context for cross-domain EDA
🔎 Similar Papers
No similar papers found.
J
Jun-Peng Zhu
East China Normal University & PingCAP, China
B
Boyan Niu
PingCAP, China
P
Peng Cai
East China Normal University, China
Z
Zheming Ni
PingCAP, China
J
Jianwei Wan
PingCAP, China
K
Kai Xu
PingCAP, China
J
Jiajun Huang
PingCAP, China
S
Shengbo Ma
PingCAP, China
B
Bing Wang
PingCAP, China
X
Xuan Zhou
East China Normal University, China
G
Guanglei Bao
PingCAP, China
D
Donghui Zhang
PingCAP, China
L
Liu Tang
PingCAP, China
Q
Qi Liu
PingCAP, China