HCAICVMay 31, 2025

ChartGen: Scaling Chart Understanding Via Code-Guided Synthetic Chart Generation

arXiv:2507.19492v15 citationsh-index: 23Has Code
Originality Synthesis-oriented
AI Analysis

This addresses the problem of limited datasets for chart understanding and code generation in AI, though it is incremental as it builds on existing methods for synthetic data creation.

The authors tackled the lack of benchmarks for chart-to-code reconstruction by developing ChartGen, an automated pipeline that generates 222.5K synthetic chart-image code pairs from 13K seed images, and they found that evaluating six VLMs on a 4.3K subset revealed significant room for improvement.

Chart-to-code reconstruction -- the task of recovering executable plotting scripts from chart images -- provides important insights into a model's ability to ground data visualizations in precise, machine-readable form. Yet many existing multimodal benchmarks largely focus primarily on answering questions about charts or summarizing them. To bridge this gap, we present ChartGen, a fully-automated pipeline for code-guided synthetic chart generation. Starting from seed chart images, ChartGen (i) prompts a vision-language model (VLM) to reconstruct each image into a python script, and (ii) iteratively augments that script with a code-oriented large language model (LLM). Using ChartGen, we create 222.5K unique chart-image code pairs from 13K seed chart images, and present an open-source synthetic chart dataset covering 27 chart types, 11 plotting libraries, and multiple data modalities (image, code, text, CSV, DocTags). From this corpus, we curate a held-out chart-to-code evaluation subset of 4.3K chart image-code pairs, and evaluate six open-weight VLMs (3B - 26B parameters), highlighting substantial room for progress. We release the pipeline, prompts, and the dataset to help accelerate efforts towards robust chart understanding and vision-conditioned code generation: https://github.com/SD122025/ChartGen/

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes