Explanova: Automatically Discover Data Insights in N \times M Table via XAI Combined LLM Workflow

2026-01-18

AI Summary

This work addresses the challenge of automatically generating interpretable insights from N×M tabular data in a cost-effective manner by proposing a lightweight, AutoML-style analytical framework that integrates explainable artificial intelligence (XAI) with local small-scale large language models (LLMs). The approach employs a predefined workflow to systematically explore univariate statistics, pairwise relationships, and multivariate associations, thereby eliminating reliance on expensive large models or manual intervention. In contrast to existing methods that leverage powerful LLM-based agents, this framework substantially reduces computational costs while preserving analytical depth and enhancing result interpretability, enabling efficient and transparent end-to-end insight generation from tabular data.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

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.

Problem

• automated data analysis
• data insights
• explainable AI
• LLM workflow
• AutoML

Innovation

• Explanova
• XAI
• Local Small LLM
• Automated Data Insight
• AutoML-like Workflow