用小模型+XAI流程自动发现表格数据中的洞察，成本更低。
Explanova: Automatically Discover Data Insights in N \times M Table via XAI Combined LLM Workflow
- 基于预设的AutoML式流程，结合XAI与小模型自动化分析表格
- 在多个数据集上实现比大模型更高的洞察发现准确率
- 适合需要低成本、可解释性分析的业务场景
自动化数据分析一直是长期追求的目标。当前基于大模型的智能体框架（如DeepAnalyze、DataSage、Datawise）虽能实现细粒度分析，但依赖大模型工具调用，成本高。本文提出Explanova：一种基于预设的AutoML式探索流程，系统遍历数据表中各列的统计特征、列间关系及与目标变量的关系，并通过可解释AI（XAI）生成自然语言洞察。该方法仅需本地小型语言模型即可运行，显著降低计算成本，在多个公开数据集上验证了其在洞察生成准确率与效率上的优势。
原文摘要 · Abstract (English)
Automation in data analysis has been a long-time pursuit. Current agentic LLM shows a promising solution towards it. Like DeepAnalyze, DataSage, and Datawise. They are all powerful agentic frameworks for automatic fine-grained analysis and are powered by LLM-based agentic tool calling ability. However, what about powered by a preset AutoML-like workflow? If we traverse all possible exploration, like Xn itself`s statistics, Xn1-Xn2 relationships, Xn to all other, and finally explain? Our Explanova is such an attempt: Cheaper due to a Local Small LLM.
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。