Aligned Multi-View Scripts for Universal Chart-to-Code Generation

TL;DR

This paper introduces Chart2NCode, a large dataset of charts with aligned scripts in multiple languages, and proposes CharLuMA, a multimodal model that effectively generates executable chart code across Python, R, and LaTeX.

Contribution

The work provides a new multi-language chart-to-code dataset and a parameter-efficient model that improves cross-language code generation fidelity and executability.

Findings

CharLuMA outperforms open-source baselines in code accuracy and visual fidelity.

Balanced multi-language supervision enhances performance across all target languages.

The adapter design enables sharing core understanding while allowing language-specific specialization.

Abstract

Chart-to-code generation converts a chart image into an executable plotting script, enabling faithful reproduction and editable visualizations. Existing methods are largely Python-centric, limiting practical use and overlooking a critical source of supervision: the same chart can be expressed by semantically equivalent scripts in different plotting languages. To fill this gap, we introduce Chart2NCode, a dataset of 176K charts paired with aligned scripts in Python, R, and LaTeX that render visually equivalent outputs, constructed via a metadata-to-template pipeline with rendering verification and human quality checks. Building on a LLaVA-style architecture, we further propose CharLuMA, a parameter-efficient adaptation module that augments the multimodal projector with a language-conditioned mixture of low-rank subspaces, allowing the model to share core chart understanding while specializing code generation to the target language through lightweight routing. Extensive experiments show consistent gains in executability and visual fidelity across all languages, outperforming strong open-source baselines and remaining competitive with proprietary systems. Further analyses reveal that balanced multi-language supervision benefits all languages and that the adapter allocates a compact shared core plus language-specific capacity. Codes and data are available at https://github.com/Zhihan72/CharLuMA.