Infogen: Generating Complex Statistical Infographics from Documents

2025-07-26

AI Summary

Existing large language models (LLMs) struggle to autonomously generate complex, multi-chart statistical infographics—comprising diverse sub-charts—that are contextually accurate, visually coherent, and insight-rich from text-dense documents. Method: This work introduces the novel “text-to-complex-infographic generation” task, establishes the first dedicated benchmark dataset, Infodat, and proposes a two-stage framework: (1) fine-tuning an LLM to produce structured metadata—including title, key insights, sub-chart data, and layout specifications; and (2) converting this metadata into executable, renderable code. Contribution/Results: We formally define the task, release the first domain-specific benchmark (Infodat), and present an end-to-end generation framework. Our method achieves state-of-the-art performance on Infodat, significantly outperforming leading open- and closed-source LLMs. This advances AI-driven information visualization toward high-fidelity, multi-chart, semantically consistent outputs.

Technology Category

• Natural Language Processing: Information Extraction
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Data Visualization & Summarization

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Statistical infographics are powerful tools that simplify complex data into visually engaging and easy-to-understand formats. Despite advancements in AI, particularly with LLMs, existing efforts have been limited to generating simple charts, with no prior work addressing the creation of complex infographics from text-heavy documents that demand a deep understanding of the content. We address this gap by introducing the task of generating statistical infographics composed of multiple sub-charts (e.g., line, bar, pie) that are contextually accurate, insightful, and visually aligned. To achieve this, we define infographic metadata that includes its title and textual insights, along with sub-chart-specific details such as their corresponding data and alignment. We also present Infodat, the first benchmark dataset for text-to-infographic metadata generation, where each sample links a document to its metadata. We propose Infogen, a two-stage framework where fine-tuned LLMs first generate metadata, which is then converted into infographic code. Extensive evaluations on Infodat demonstrate that Infogen achieves state-of-the-art performance, outperforming both closed and open-source LLMs in text-to-statistical infographic generation.

Problem

• Generating complex infographics from text-heavy documents
• Ensuring contextual accuracy and visual alignment in infographics
• Creating a benchmark dataset for text-to-infographic metadata generation

Innovation

• Two-stage framework for infographic generation
• Fine-tuned LLMs generate metadata first
• Converts metadata into infographic code