NL2Color: Refining Color Palettes for Charts with Natural Language

Chuhan Shi, Weiwei Cui, Chengzhong Liu, Chengbo Zheng, Haidong Zhang, Qiong Luo, Xiaojuan Ma

Room: 105

2023-10-25T22:36:00ZGMT-0600Change your timezone on the schedule page
Exemplar figure, described by caption below
Examples of color palette refinement by NL2Color. (a)-(d) show four pairs of an original chart (left) and a new chart (right) refined by NL2Color according to the request. (e) shows an original chart (left) and three new charts (right) NL2Color generated according to three refinement requests. The color palette of each chart is displayed above the chart. The original charts are collected from Vega-Lite.
Fast forward
Full Video

chart, color palette, natural language, large language model


Choice of color is critical to creating effective charts with an engaging, enjoyable, and informative reading experience. However, designing a good color palette for a chart is a challenging task for novice users who lack related design expertise. For example, they often find it difficult to articulate their abstract intentions and translate these intentions into effective editing actions to achieve a desired outcome. In this work, we present NL2Color, a tool that allows novice users to modify chart color palettes using natural language expressions of their desired outcomes. We first collected and categorized a dataset of 131 triplets, each consisting of an original color palette of a chart, an editing intent, and a new color palette designed by human experts according to the intent. Our tool employs a large language model (LLM) to substitute the colors in original palettes and produce new color palettes by selecting some of the triplets as few-shot prompts. To evaluate our tool, we conducted a comprehensive two-stage evaluation, including a crowd-sourcing study (N=71) and a within-subjects user study (N=12). The results indicate that the quality of the color palettes revised by NL2Color has no significantly large difference from those designed by human experts. The participants who used NL2Color obtained revised color palettes to their satisfaction in a shorter period and with less effort.