ChartEditor: A Reinforcement Learning Framework for Robust Chart Editing

TL;DR

This paper introduces ChartEditVista, a large and diverse benchmark for chart editing, and presents ChartEditor, a reinforcement learning model that improves editing quality by optimizing visual fidelity and code executability.

Contribution

The paper provides a comprehensive, automated benchmark for chart editing and develops a reinforcement learning framework with novel rewards to enhance editing performance.

Findings

ChartEditVista covers 31 chart categories with 7,964 samples.

ChartEditor outperforms similar or larger models in editing tasks.

New evaluation metrics effectively assess layout and textual accuracy.

Abstract

Chart editing reduces manual effort in visualization design. Typical benchmarks limited in data diversity and assume access to complete chart code, which is seldom in real-world scenarios. To address this gap, we present ChartEditVista, a comprehensive benchmark consisting of 7,964 samples spanning 31 chart categories. It encompasses diverse editing instructions and covers nearly all editable chart elements. The inputs in ChartEditVista include only the original chart image and natural language editing instructions, without the original chart codes. ChartEditVista is generated through a fully automated pipeline that produces, edits, and verifies charts, ensuring high-quality chart editing data. Besides, we introduce two novel fine-grained, rule-based evaluation metrics: the layout metric, which evaluates the position, size and color of graphical components; and the text metric, which jointly assesses textual content and font styling. Building on top of ChartEditVista, we present ChartEditor, a model trained using a reinforcement learning framework that incorporates a novel rendering reward to simultaneously enforce code executability and visual fidelity. Through extensive experiments and human evaluations, we demonstrate that ChartEditVista provides a robust evaluation, while ChartEditor consistently outperforms models with similar-scale and larger-scale on chart editing tasks.