FactFlow: Automatic Fact Sheet Generation and Customization from Tabular Dataset via AI Chain Design&Implementation

2025-02-25

AI Summary

Existing fact-table generation tools exhibit weak semantic understanding and poor user customizability, failing to meet the needs of non-expert users. This paper proposes a semantics-aware, automated fact-brief generation method for tabular data. We introduce, for the first time, a collaborative AI-worker chain architecture and define a task-oriented taxonomy of AI workers. Our approach integrates tabular semantic parsing, natural-language-instruction-driven visualization generation, and closed-loop optimization via user feedback—enabling natural-language-based interactive refinement. It unifies semantic alignment with personalized customization. In a user study involving 18 participants, our method achieves a 37% improvement in fact-brief semantic completeness and a 52% increase in user task completion rate over state-of-the-art baselines, significantly enhancing both interpretability and usability.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Data Mining & Knowledge Management: Data Visualization & Summarization
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

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: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

With the proliferation of data across various domains, there is a critical demand for tools that enable non-experts to derive meaningful insights without deep data analysis skills. To address this need, existing automatic fact sheet generation tools offer heuristic-based solutions to extract facts and generate stories. However, they inadequately grasp the semantics of data and struggle to generate narratives that fully capture the semantics of the dataset or align the fact sheet with specific user needs. Addressing these shortcomings, this paper introduces ool, a novel tool designed for the automatic generation and customisation of fact sheets. ool applies the concept of collaborative AI workers to transform raw tabular dataset into comprehensive, visually compelling fact sheets. We define effective taxonomy to profile AI worker for specialised tasks. Furthermore, ool empowers users to refine these fact sheets through intuitive natural language commands, ensuring the final outputs align closely with individual preferences and requirements. Our user evaluation with 18 participants confirms that ool not only surpasses state-of-the-art baselines in automated fact sheet production but also provides a positive user experience during customization tasks.

Problem

• Automated fact sheet generation
• Semantic data understanding
• User-customized narrative creation

Innovation

• AI chain design
• natural language customization
• collaborative AI workers