用大模型自动从数据库中挖掘有用洞察，既准确又够“有见地”。
An LLM-Based Approach for Insight Generation in Data Analysis
- 分三步：提问题、写SQL查数据、把结果转成文字洞察
- 在真实数据库上生成的洞察比现有方法更深入且正确率高
- 适合需要快速从数据中提炼关键发现的研究或业务人员
从数据库中生成有意义且可操作的信息是数据分析的核心。本文提出一种基于大语言模型（LLM）的新方法，可自动产出反映表格中有趣模式的简洁文本洞察。给定多表数据库输入，该框架包含假设生成器以提出领域相关问题、查询代理生成SQL查询并回答问题、以及摘要模块将结果转化为自然语言洞察。通过结合人工评估与自动化指标对洞察的准确性与主观价值进行双重评价。在公开和企业级数据库上的实验表明，该方法生成的洞察在深度与正确性方面均优于现有方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。